Token | there |
Token ID | 612 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ria | +0.037 |
ING | +0.037 |
groom | +0.036 |
tap | +0.035 |
elcome | +0.034 |
Neg logit contributions | |
sometimes | -0.020 |
Sometimes | -0.019 |
rob | -0.018 |
maybe | -0.018 |
dinosaurs | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
ING | +0.029 |
ria | +0.029 |
tap | +0.028 |
groom | +0.027 |
ume | +0.027 |
Neg logit contributions | |
sometimes | -0.017 |
Sometimes | -0.016 |
maybe | -0.015 |
dinosaurs | -0.014 |
then | -0.014 |
Token | other |
Token ID | 584 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
ria | +0.018 |
ING | +0.018 |
ume | +0.017 |
groom | +0.017 |
tap | +0.017 |
Neg logit contributions | |
sometimes | -0.017 |
Sometimes | -0.015 |
maybe | -0.015 |
dinosaurs | -0.015 |
then | -0.014 |
Token | long |
Token ID | 890 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ria | +0.054 |
ING | +0.051 |
ume | +0.049 |
slight | +0.048 |
elcome | +0.048 |
Neg logit contributions | |
sometimes | -0.061 |
dinosaurs | -0.055 |
maybe | -0.054 |
Sometimes | -0.053 |
then | -0.051 |
Token | sh |
Token ID | 427 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ING | +0.022 |
tap | +0.021 |
groom | +0.021 |
pet | +0.021 |
ater | +0.021 |
Neg logit contributions | |
Sometimes | -0.023 |
sometimes | -0.023 |
maybe | -0.022 |
rob | -0.022 |
eighty | -0.020 |
Token | rim |
Token ID | 3036 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
groom | +0.052 |
ria | +0.049 |
human | +0.045 |
bundle | +0.045 |
hand | +0.044 |
Neg logit contributions | |
sometimes | -0.066 |
cast | -0.061 |
Sometimes | -0.059 |
besides | -0.058 |
rob | -0.056 |
Token | ps |
Token ID | 862 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
ria | +0.145 |
Care | +0.140 |
Girl | +0.138 |
slight | +0.137 |
ING | +0.134 |
Neg logit contributions | |
sometimes | -0.095 |
dinosaurs | -0.083 |
cast | -0.082 |
maybe | -0.075 |
under | -0.072 |
Token | in |
Token ID | 287 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ria | +0.024 |
ING | +0.023 |
groom | +0.022 |
ume | +0.022 |
slight | +0.022 |
Neg logit contributions | |
sometimes | -0.017 |
maybe | -0.015 |
Sometimes | -0.015 |
then | -0.014 |
dinosaurs | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ING | +0.029 |
ria | +0.029 |
tap | +0.028 |
groom | +0.028 |
ume | +0.028 |
Neg logit contributions | |
sometimes | -0.022 |
maybe | -0.020 |
Sometimes | -0.020 |
rob | -0.019 |
cast | -0.019 |
Token | ocean |
Token ID | 9151 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ria | +0.036 |
ING | +0.034 |
ume | +0.033 |
elcome | +0.032 |
groom | +0.032 |
Neg logit contributions | |
sometimes | -0.041 |
Sometimes | -0.036 |
dinosaurs | -0.035 |
maybe | -0.035 |
then | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ria | +0.057 |
ING | +0.057 |
groom | +0.053 |
ume | +0.053 |
tap | +0.052 |
Neg logit contributions | |
sometimes | -0.053 |
Sometimes | -0.047 |
maybe | -0.047 |
dinosaurs | -0.045 |
then | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
ria | +0.022 |
ING | +0.021 |
ume | +0.020 |
groom | +0.020 |
slight | +0.020 |
Neg logit contributions | |
sometimes | -0.021 |
maybe | -0.018 |
Sometimes | -0.018 |
dinosaurs | -0.018 |
then | -0.017 |
Token | They |
Token ID | 1119 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
ING | +0.015 |
ria | +0.015 |
ume | +0.014 |
tap | +0.014 |
groom | +0.014 |
Neg logit contributions | |
sometimes | -0.009 |
maybe | -0.008 |
Sometimes | -0.008 |
dinosaurs | -0.008 |
then | -0.007 |
Token | see |
Token ID | 766 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
tap | +0.016 |
ING | +0.015 |
groom | +0.015 |
copy | +0.015 |
pet | +0.015 |
Neg logit contributions | |
sometimes | -0.023 |
Sometimes | -0.023 |
rob | -0.022 |
dinosaurs | -0.022 |
maybe | -0.022 |
Token | many |
Token ID | 867 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
tap | +0.009 |
pet | +0.008 |
groom | +0.008 |
human | +0.008 |
hand | +0.008 |
Neg logit contributions | |
rob | -0.010 |
cast | -0.009 |
sometimes | -0.009 |
eighty | -0.009 |
Sometimes | -0.009 |
Token | sh |
Token ID | 427 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
sometimes | +0.006 |
Sometimes | +0.005 |
maybe | +0.005 |
dinosaurs | +0.005 |
then | +0.005 |
Neg logit contributions | |
ria | -0.004 |
ING | -0.004 |
ume | -0.004 |
groom | -0.004 |
tap | -0.004 |
Token | rim |
Token ID | 3036 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
groom | +0.043 |
ria | +0.042 |
ING | +0.040 |
ume | +0.038 |
lamb | +0.038 |
Neg logit contributions | |
sometimes | -0.060 |
cast | -0.056 |
rob | -0.056 |
Sometimes | -0.053 |
besides | -0.052 |
Token | ps |
Token ID | 862 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ria | +0.141 |
Care | +0.136 |
slight | +0.135 |
ING | +0.134 |
groom | +0.130 |
Neg logit contributions | |
sometimes | -0.092 |
dinosaurs | -0.080 |
cast | -0.080 |
maybe | -0.075 |
for | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
ria | +0.008 |
ING | +0.008 |
groom | +0.007 |
ume | +0.007 |
slight | +0.007 |
Neg logit contributions | |
sometimes | -0.006 |
maybe | -0.005 |
Sometimes | -0.005 |
then | -0.005 |
dinosaurs | -0.005 |
Token | fish |
Token ID | 5916 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
ria | +0.017 |
ING | +0.017 |
groom | +0.015 |
ume | +0.015 |
tap | +0.015 |
Neg logit contributions | |
sometimes | -0.028 |
Sometimes | -0.026 |
maybe | -0.025 |
dinosaurs | -0.024 |
then | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
ria | +0.021 |
ING | +0.020 |
slight | +0.019 |
Care | +0.019 |
iya | +0.019 |
Neg logit contributions | |
sometimes | -0.016 |
dinosaurs | -0.013 |
maybe | -0.013 |
Sometimes | -0.012 |
then | -0.012 |
Token | crabs |
Token ID | 49172 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
ING | +0.017 |
ria | +0.016 |
groom | +0.016 |
tap | +0.016 |
copy | +0.015 |
Neg logit contributions | |
sometimes | -0.025 |
Sometimes | -0.024 |
maybe | -0.023 |
rob | -0.022 |
dinosaurs | -0.022 |
Token | Pete |
Token ID | 17542 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ING | +0.003 |
ria | +0.003 |
ume | +0.002 |
ater | +0.002 |
ady | +0.002 |
Neg logit contributions | |
sometimes | -0.001 |
maybe | -0.001 |
Sometimes | -0.001 |
then | -0.001 |
dinosaurs | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
ING | +0.043 |
ria | +0.043 |
ume | +0.041 |
Care | +0.041 |
slight | +0.040 |
Neg logit contributions | |
sometimes | -0.028 |
maybe | -0.023 |
then | -0.023 |
Sometimes | -0.021 |
dinosaurs | -0.021 |
Token | ever |
Token ID | 1683 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
sometimes | +0.012 |
then | +0.010 |
now | +0.009 |
dinosaurs | +0.009 |
maybe | +0.009 |
Neg logit contributions | |
ING | -0.018 |
ria | -0.018 |
oing | -0.018 |
ower | -0.018 |
estone | -0.017 |
Token | seen |
Token ID | 1775 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
sometimes | +0.015 |
maybe | +0.013 |
then | +0.013 |
dinosaurs | +0.013 |
Sometimes | +0.012 |
Neg logit contributions | |
ria | -0.019 |
ING | -0.018 |
ower | -0.017 |
ume | -0.017 |
tap | -0.017 |
Token | sh |
Token ID | 427 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
sometimes | +0.008 |
maybe | +0.007 |
Sometimes | +0.007 |
dinosaurs | +0.007 |
then | +0.006 |
Neg logit contributions | |
ria | -0.011 |
ING | -0.011 |
ume | -0.011 |
groom | -0.011 |
slight | -0.011 |
Token | rim |
Token ID | 3036 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
groom | +0.027 |
human | +0.025 |
ria | +0.024 |
gard | +0.023 |
snail | +0.023 |
Neg logit contributions | |
sometimes | -0.045 |
cast | -0.041 |
Sometimes | -0.040 |
besides | -0.039 |
then | -0.039 |
Token | ps |
Token ID | 862 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ria | +0.125 |
Care | +0.121 |
slight | +0.119 |
ING | +0.119 |
groom | +0.118 |
Neg logit contributions | |
sometimes | -0.094 |
cast | -0.080 |
maybe | -0.080 |
dinosaurs | -0.079 |
then | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
ria | +0.004 |
ING | +0.004 |
groom | +0.004 |
ume | +0.004 |
slight | +0.004 |
Neg logit contributions | |
sometimes | -0.003 |
maybe | -0.002 |
Sometimes | -0.002 |
then | -0.002 |
dinosaurs | -0.002 |
Token | his |
Token ID | 465 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
ria | +0.014 |
ING | +0.014 |
groom | +0.014 |
tap | +0.014 |
ume | +0.014 |
Neg logit contributions | |
sometimes | -0.008 |
Sometimes | -0.007 |
maybe | -0.006 |
dinosaurs | -0.006 |
then | -0.006 |
Token | dad |
Token ID | 9955 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
ING | +0.015 |
ria | +0.015 |
ume | +0.014 |
Care | +0.014 |
elcome | +0.014 |
Neg logit contributions | |
sometimes | -0.021 |
maybe | -0.019 |
Sometimes | -0.019 |
dinosaurs | -0.019 |
then | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
sometimes | +0.014 |
then | +0.012 |
maybe | +0.012 |
Sometimes | +0.010 |
dinosaurs | +0.010 |
Neg logit contributions | |
ING | -0.021 |
ria | -0.021 |
ume | -0.020 |
Care | -0.020 |
estone | -0.019 |
Token | dad |
Token ID | 9955 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ING | +0.017 |
ria | +0.017 |
ume | +0.016 |
Care | +0.016 |
elcome | +0.016 |
Neg logit contributions | |
sometimes | -0.026 |
maybe | -0.024 |
Sometimes | -0.024 |
dinosaurs | -0.024 |
then | -0.024 |
Token | happily |
Token ID | 18177 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
sometimes | +0.006 |
maybe | +0.006 |
Sometimes | +0.006 |
then | +0.005 |
dinosaurs | +0.005 |
Neg logit contributions | |
ria | -0.007 |
ING | -0.007 |
groom | -0.006 |
ume | -0.006 |
tap | -0.006 |
Token | eating |
Token ID | 6600 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
sometimes | +0.009 |
then | +0.008 |
maybe | +0.007 |
dinosaurs | +0.007 |
under | +0.007 |
Neg logit contributions | |
ING | -0.012 |
ria | -0.012 |
slight | -0.011 |
ower | -0.011 |
abba | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
ING | +0.033 |
ria | +0.033 |
tap | +0.032 |
groom | +0.032 |
ume | +0.031 |
Neg logit contributions | |
sometimes | -0.025 |
Sometimes | -0.023 |
maybe | -0.022 |
dinosaurs | -0.021 |
rob | -0.020 |
Token | sh |
Token ID | 427 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ria | +0.023 |
ING | +0.023 |
ume | +0.022 |
groom | +0.021 |
elcome | +0.021 |
Neg logit contributions | |
sometimes | -0.022 |
maybe | -0.020 |
Sometimes | -0.019 |
dinosaurs | -0.019 |
then | -0.019 |
Token | rim |
Token ID | 3036 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
groom | +0.025 |
ING | +0.023 |
copy | +0.023 |
ria | +0.022 |
Care | +0.022 |
Neg logit contributions | |
sometimes | -0.033 |
rob | -0.031 |
cast | -0.030 |
Sometimes | -0.030 |
besides | -0.029 |
Token | ps |
Token ID | 862 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ria | +0.125 |
Care | +0.123 |
ING | +0.122 |
slight | +0.117 |
groom | +0.116 |
Neg logit contributions | |
sometimes | -0.094 |
maybe | -0.082 |
dinosaurs | -0.078 |
cast | -0.077 |
for | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
sometimes | +0.004 |
maybe | +0.003 |
then | +0.003 |
Sometimes | +0.003 |
dinosaurs | +0.003 |
Neg logit contributions | |
ria | -0.006 |
ING | -0.006 |
groom | -0.006 |
slight | -0.006 |
ume | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ING | +0.002 |
ria | +0.002 |
ume | +0.002 |
ater | +0.002 |
estone | +0.002 |
Neg logit contributions | |
sometimes | -0.001 |
maybe | -0.001 |
then | -0.001 |
Sometimes | -0.001 |
dinosaurs | -0.001 |
Token | realized |
Token ID | 6939 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
sometimes | +0.010 |
maybe | +0.009 |
Sometimes | +0.008 |
then | +0.008 |
dinosaurs | +0.008 |
Neg logit contributions | |
ING | -0.014 |
ria | -0.014 |
ume | -0.014 |
tap | -0.013 |
groom | -0.013 |
Token | why |
Token ID | 1521 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
sometimes | +0.004 |
Sometimes | +0.004 |
maybe | +0.004 |
dinosaurs | +0.004 |
rob | +0.003 |
Neg logit contributions | |
ria | -0.010 |
ING | -0.010 |
tap | -0.009 |
groom | -0.009 |
ume | -0.009 |
Token | there |
Token ID | 612 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ria | +0.009 |
ING | +0.009 |
ume | +0.009 |
groom | +0.009 |
slight | +0.008 |
Neg logit contributions | |
sometimes | -0.008 |
maybe | -0.007 |
Sometimes | -0.007 |
then | -0.007 |
dinosaurs | -0.007 |
Token | are |
Token ID | 389 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
sometimes | +0.002 |
maybe | +0.002 |
Sometimes | +0.002 |
then | +0.002 |
dinosaurs | +0.002 |
Neg logit contributions | |
ria | -0.003 |
groom | -0.002 |
ING | -0.002 |
ater | -0.002 |
oing | -0.002 |
Token | some |
Token ID | 617 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ING | +0.001 |
ria | +0.001 |
groom | +0.001 |
ume | +0.001 |
tap | +0.001 |
Neg logit contributions | |
sometimes | -0.001 |
Sometimes | -0.001 |
maybe | -0.001 |
dinosaurs | -0.001 |
then | -0.001 |
Token | nice |
Token ID | 3621 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
sometimes | +0.004 |
maybe | +0.004 |
Sometimes | +0.004 |
dinosaurs | +0.004 |
then | +0.004 |
Neg logit contributions | |
ria | -0.004 |
ING | -0.004 |
ume | -0.004 |
oing | -0.004 |
elcome | -0.004 |
Token | sh |
Token ID | 427 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ria | +0.044 |
ING | +0.043 |
elcome | +0.039 |
oxy | +0.039 |
iba | +0.039 |
Neg logit contributions | |
sometimes | -0.043 |
dinosaurs | -0.038 |
maybe | -0.037 |
Sometimes | -0.037 |
then | -0.035 |
Token | rim |
Token ID | 3036 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
groom | +0.024 |
ria | +0.023 |
ING | +0.022 |
copy | +0.022 |
pet | +0.021 |
Neg logit contributions | |
sometimes | -0.038 |
rob | -0.034 |
cast | -0.033 |
Sometimes | -0.033 |
dinosaurs | -0.032 |
Token | ps |
Token ID | 862 |
Feature activation | -8.76e-03 |
Pos logit contributions | |
ria | +0.123 |
ING | +0.117 |
Care | +0.117 |
slight | +0.117 |
groom | +0.114 |
Neg logit contributions | |
sometimes | -0.094 |
dinosaurs | -0.083 |
cast | -0.081 |
maybe | -0.081 |
Sometimes | -0.076 |
Token | here |
Token ID | 994 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
sometimes | +0.000 |
Sometimes | +0.000 |
maybe | +0.000 |
dinosaurs | +0.000 |
then | +0.000 |
Neg logit contributions | |
ING | -0.000 |
ria | -0.000 |
ume | -0.000 |
groom | -0.000 |
tap | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
sometimes | +0.010 |
Sometimes | +0.009 |
maybe | +0.009 |
dinosaurs | +0.008 |
rob | +0.008 |
Neg logit contributions | |
ING | -0.014 |
ria | -0.014 |
groom | -0.013 |
ume | -0.013 |
tap | -0.013 |
Token | I |
Token ID | 314 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
sometimes | +0.012 |
maybe | +0.010 |
Sometimes | +0.010 |
then | +0.010 |
dinosaurs | +0.009 |
Neg logit contributions | |
ria | -0.016 |
ING | -0.016 |
ater | -0.015 |
ady | -0.015 |
oing | -0.015 |
Token | 've |
Token ID | 1053 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
ria | +0.012 |
ING | +0.012 |
groom | +0.011 |
ume | +0.011 |
elcome | +0.011 |
Neg logit contributions | |
sometimes | -0.011 |
maybe | -0.010 |
Sometimes | -0.010 |
then | -0.010 |
dinosaurs | -0.009 |
Token | stove |
Token ID | 27635 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ria | +0.025 |
ING | +0.025 |
ume | +0.024 |
elcome | +0.024 |
groom | +0.023 |
Neg logit contributions | |
sometimes | -0.025 |
maybe | -0.022 |
dinosaurs | -0.022 |
then | -0.022 |
Sometimes | -0.021 |
Token | - |
Token ID | 532 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
ria | +0.028 |
ING | +0.028 |
groom | +0.026 |
ume | +0.026 |
slight | +0.026 |
Neg logit contributions | |
sometimes | -0.022 |
maybe | -0.019 |
Sometimes | -0.019 |
then | -0.018 |
dinosaurs | -0.018 |
Token | two |
Token ID | 734 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ING | +0.025 |
ria | +0.025 |
ume | +0.023 |
ater | +0.023 |
estone | +0.023 |
Neg logit contributions | |
sometimes | -0.012 |
maybe | -0.011 |
Sometimes | -0.010 |
then | -0.010 |
dinosaurs | -0.009 |
Token | more |
Token ID | 517 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
sometimes | +0.004 |
maybe | +0.004 |
dinosaurs | +0.004 |
Sometimes | +0.004 |
then | +0.004 |
Neg logit contributions | |
ria | -0.005 |
ING | -0.005 |
ume | -0.004 |
groom | -0.004 |
elcome | -0.004 |
Token | sh |
Token ID | 427 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
sometimes | +0.007 |
maybe | +0.006 |
Sometimes | +0.006 |
dinosaurs | +0.006 |
then | +0.006 |
Neg logit contributions | |
ING | -0.007 |
ria | -0.007 |
ume | -0.007 |
groom | -0.007 |
elcome | -0.007 |
Token | rim |
Token ID | 3036 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
groom | +0.025 |
ING | +0.025 |
ria | +0.024 |
snail | +0.023 |
tap | +0.023 |
Neg logit contributions | |
sometimes | -0.037 |
rob | -0.034 |
cast | -0.033 |
Sometimes | -0.033 |
then | -0.032 |
Token | ps |
Token ID | 862 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
ria | +0.110 |
ING | +0.109 |
Care | +0.105 |
slight | +0.103 |
groom | +0.102 |
Neg logit contributions | |
sometimes | -0.101 |
maybe | -0.089 |
dinosaurs | -0.087 |
cast | -0.085 |
Sometimes | -0.084 |
Token | ! |
Token ID | 0 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
sometimes | +0.001 |
then | +0.001 |
maybe | +0.001 |
dinosaurs | +0.001 |
Sometimes | +0.001 |
Neg logit contributions | |
ria | -0.002 |
ING | -0.002 |
groom | -0.002 |
ater | -0.002 |
iya | -0.002 |
Token | His |
Token ID | 2399 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ater | +0.041 |
groom | +0.041 |
ria | +0.041 |
copy | +0.040 |
ING | +0.039 |
Neg logit contributions | |
Sometimes | -0.020 |
sometimes | -0.019 |
maybe | -0.018 |
From | -0.016 |
Tim | -0.016 |
Token | dad |
Token ID | 9955 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
ING | +0.028 |
ria | +0.026 |
ume | +0.026 |
Care | +0.025 |
estone | +0.025 |
Neg logit contributions | |
sometimes | -0.032 |
maybe | -0.030 |
then | -0.030 |
dinosaurs | -0.029 |
Sometimes | -0.029 |
Token | had |
Token ID | 550 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
sometimes | +0.015 |
then | +0.013 |
maybe | +0.013 |
Sometimes | +0.012 |
dinosaurs | +0.012 |
Neg logit contributions | |
ING | -0.026 |
ria | -0.025 |
ume | -0.024 |
estone | -0.024 |
ater | -0.024 |
Token | Maybe |
Token ID | 13300 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ria | +0.010 |
ING | +0.010 |
elcome | +0.009 |
ume | +0.009 |
groom | +0.009 |
Neg logit contributions | |
sometimes | -0.010 |
Sometimes | -0.009 |
maybe | -0.009 |
then | -0.008 |
dinosaurs | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
rob | +0.021 |
sometimes | +0.021 |
Sometimes | +0.020 |
cast | +0.019 |
dinosaurs | +0.019 |
Neg logit contributions | |
ING | -0.026 |
tap | -0.025 |
ria | -0.025 |
groom | -0.025 |
pet | -0.024 |
Token | is |
Token ID | 318 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
ria | +0.034 |
ING | +0.033 |
groom | +0.032 |
ume | +0.031 |
elcome | +0.031 |
Neg logit contributions | |
sometimes | -0.021 |
Sometimes | -0.017 |
maybe | -0.017 |
then | -0.016 |
dinosaurs | -0.016 |
Token | not |
Token ID | 407 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
sometimes | +0.009 |
maybe | +0.008 |
Sometimes | +0.007 |
then | +0.007 |
dinosaurs | +0.007 |
Neg logit contributions | |
ria | -0.012 |
ING | -0.012 |
ume | -0.011 |
oing | -0.011 |
estone | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ria | +0.013 |
ING | +0.012 |
Care | +0.012 |
ume | +0.012 |
Girl | +0.011 |
Neg logit contributions | |
sometimes | -0.008 |
maybe | -0.007 |
dinosaurs | -0.006 |
Sometimes | -0.006 |
then | -0.006 |
Token | friendly |
Token ID | 8030 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
ume | +0.025 |
ING | +0.025 |
ria | +0.025 |
ady | +0.024 |
iver | +0.024 |
Neg logit contributions | |
sometimes | -0.036 |
maybe | -0.033 |
dinosaurs | -0.032 |
Sometimes | -0.031 |
then | -0.031 |
Token | snail |
Token ID | 47374 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ady | +0.079 |
ume | +0.079 |
ria | +0.077 |
ft | +0.076 |
Care | +0.076 |
Neg logit contributions | |
sometimes | -0.124 |
maybe | -0.110 |
then | -0.106 |
for | -0.106 |
Sometimes | -0.103 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ria | +0.027 |
ING | +0.027 |
groom | +0.025 |
ume | +0.025 |
tap | +0.025 |
Neg logit contributions | |
sometimes | -0.025 |
Sometimes | -0.023 |
maybe | -0.023 |
dinosaurs | -0.021 |
then | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ING | +0.036 |
ria | +0.035 |
tap | +0.034 |
ume | +0.033 |
Care | +0.033 |
Neg logit contributions | |
sometimes | -0.033 |
dinosaurs | -0.029 |
rob | -0.028 |
Sometimes | -0.028 |
maybe | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ING | +0.032 |
ria | +0.032 |
tap | +0.030 |
elcome | +0.030 |
Care | +0.030 |
Neg logit contributions | |
sometimes | -0.032 |
dinosaurs | -0.028 |
maybe | -0.028 |
Sometimes | -0.027 |
rob | -0.027 |
Token | Ben |
Token ID | 11696 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ria | +0.029 |
groom | +0.028 |
slight | +0.028 |
ING | +0.027 |
ume | +0.027 |
Neg logit contributions | |
sometimes | -0.032 |
then | -0.028 |
Sometimes | -0.028 |
maybe | -0.027 |
besides | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ria | +0.018 |
ING | +0.018 |
Care | +0.017 |
tap | +0.016 |
ume | +0.016 |
Neg logit contributions | |
sometimes | -0.020 |
dinosaurs | -0.019 |
maybe | -0.018 |
rob | -0.017 |
Sometimes | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
ria | +0.003 |
rys | +0.003 |
moth | +0.003 |
slight | +0.003 |
elcome | +0.003 |
Neg logit contributions | |
sometimes | -0.005 |
then | -0.005 |
Sometimes | -0.005 |
maybe | -0.005 |
eighty | -0.004 |
Token | Where |
Token ID | 8496 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ria | +0.016 |
ING | +0.015 |
tap | +0.015 |
ume | +0.015 |
itter | +0.015 |
Neg logit contributions | |
sometimes | -0.016 |
Sometimes | -0.013 |
maybe | -0.013 |
then | -0.013 |
rob | -0.012 |
Token | is |
Token ID | 318 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ING | +0.003 |
ria | +0.003 |
ume | +0.003 |
elcome | +0.003 |
a | +0.003 |
Neg logit contributions | |
sometimes | -0.002 |
rob | -0.002 |
cast | -0.002 |
Sometimes | -0.002 |
dinosaurs | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ria | +0.011 |
ING | +0.011 |
ume | +0.011 |
groom | +0.011 |
slight | +0.011 |
Neg logit contributions | |
sometimes | -0.007 |
maybe | -0.006 |
Sometimes | -0.006 |
dinosaurs | -0.006 |
then | -0.005 |
Token | cool |
Token ID | 3608 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
ria | +0.044 |
ING | +0.044 |
ume | +0.040 |
groom | +0.040 |
tap | +0.039 |
Neg logit contributions | |
sometimes | -0.070 |
Sometimes | -0.064 |
maybe | -0.064 |
dinosaurs | -0.061 |
then | -0.061 |
Token | thing |
Token ID | 1517 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
ria | +0.086 |
oxy | +0.084 |
ume | +0.080 |
itter | +0.078 |
oing | +0.078 |
Neg logit contributions | |
sometimes | -0.113 |
then | -0.097 |
maybe | -0.096 |
cast | -0.095 |
dinosaurs | -0.095 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ING | +0.015 |
ria | +0.015 |
groom | +0.014 |
ume | +0.014 |
tap | +0.014 |
Neg logit contributions | |
sometimes | -0.011 |
Sometimes | -0.010 |
maybe | -0.010 |
dinosaurs | -0.009 |
then | -0.009 |
Token | Sara |
Token ID | 24799 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
sometimes | +0.002 |
Sometimes | +0.002 |
dinosaurs | +0.002 |
maybe | +0.002 |
cast | +0.002 |
Neg logit contributions | |
ING | -0.003 |
ria | -0.003 |
groom | -0.003 |
ume | -0.003 |
tap | -0.003 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ria | +0.016 |
ume | +0.016 |
ING | +0.016 |
slight | +0.015 |
rys | +0.015 |
Neg logit contributions | |
sometimes | -0.010 |
then | -0.009 |
maybe | -0.008 |
Sometimes | -0.007 |
dinosaurs | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
sometimes | +0.006 |
Sometimes | +0.005 |
maybe | +0.005 |
dinosaurs | +0.005 |
then | +0.005 |
Neg logit contributions | |
ING | -0.006 |
ria | -0.006 |
groom | -0.005 |
ume | -0.005 |
tap | -0.005 |
Token | this |
Token ID | 428 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
ING | +0.025 |
groom | +0.024 |
pet | +0.024 |
copy | +0.024 |
ume | +0.024 |
Neg logit contributions | |
rob | -0.023 |
sometimes | -0.020 |
Sometimes | -0.020 |
narrative | -0.019 |
cast | -0.019 |
Token | would |
Token ID | 561 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
ING | +0.003 |
ria | +0.003 |
ume | +0.003 |
slight | +0.003 |
oxy | +0.003 |
Neg logit contributions | |
sometimes | -0.002 |
maybe | -0.002 |
Sometimes | -0.002 |
then | -0.002 |
dinosaurs | -0.002 |
Token | happen |
Token ID | 1645 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
sometimes | +0.024 |
maybe | +0.021 |
then | +0.020 |
Sometimes | +0.020 |
dinosaurs | +0.019 |
Neg logit contributions | |
ING | -0.018 |
ria | -0.018 |
ume | -0.017 |
slight | -0.017 |
ady | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ria | +0.017 |
ING | +0.017 |
groom | +0.016 |
tap | +0.016 |
copy | +0.016 |
Neg logit contributions | |
sometimes | -0.014 |
Sometimes | -0.013 |
rob | -0.013 |
maybe | -0.013 |
dinosaurs | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ria | +0.010 |
ING | +0.010 |
ume | +0.010 |
groom | +0.010 |
tap | +0.009 |
Neg logit contributions | |
sometimes | -0.007 |
maybe | -0.006 |
Sometimes | -0.006 |
dinosaurs | -0.005 |
then | -0.005 |
Token | cute |
Token ID | 13779 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
ING | +0.025 |
ria | +0.024 |
ume | +0.023 |
estone | +0.023 |
itter | +0.023 |
Neg logit contributions | |
sometimes | -0.033 |
maybe | -0.029 |
then | -0.028 |
Sometimes | -0.028 |
dinosaurs | -0.027 |
Token | veil |
Token ID | 30615 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ume | +0.090 |
Care | +0.086 |
itter | +0.085 |
ram | +0.085 |
ady | +0.085 |
Neg logit contributions | |
sometimes | -0.096 |
for | -0.085 |
then | -0.084 |
unic | -0.081 |
now | -0.080 |
Token | he |
Token ID | 339 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
ING | +0.052 |
ria | +0.051 |
groom | +0.049 |
ume | +0.048 |
slight | +0.048 |
Neg logit contributions | |
sometimes | -0.032 |
maybe | -0.028 |
Sometimes | -0.027 |
then | -0.026 |
dinosaurs | -0.025 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
sometimes | +0.010 |
Sometimes | +0.010 |
maybe | +0.009 |
dinosaurs | +0.009 |
rob | +0.008 |
Neg logit contributions | |
ria | -0.015 |
ING | -0.015 |
groom | -0.015 |
tap | -0.014 |
ume | -0.014 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
sometimes | +0.014 |
maybe | +0.013 |
Sometimes | +0.013 |
dinosaurs | +0.012 |
then | +0.012 |
Neg logit contributions | |
ING | -0.013 |
ria | -0.013 |
tap | -0.012 |
Care | -0.012 |
ume | -0.012 |
Token | upon |
Token ID | 2402 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
rob | +0.079 |
dinosaurs | +0.071 |
sometimes | +0.070 |
bones | +0.069 |
eighty | +0.067 |
Neg logit contributions | |
ria | -0.035 |
a | -0.032 |
hand | -0.031 |
itter | -0.030 |
op | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Sometimes | +0.004 |
maybe | +0.004 |
sometimes | +0.004 |
Tim | +0.004 |
then | +0.004 |
Neg logit contributions | |
ater | -0.009 |
groom | -0.009 |
estone | -0.009 |
ady | -0.009 |
iver | -0.009 |
Token | slowly |
Token ID | 6364 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
sometimes | +0.004 |
then | +0.003 |
maybe | +0.003 |
Sometimes | +0.003 |
dinosaurs | +0.003 |
Neg logit contributions | |
ING | -0.004 |
ume | -0.004 |
ria | -0.004 |
estone | -0.004 |
oing | -0.004 |
Token | stepped |
Token ID | 10764 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
sometimes | +0.016 |
then | +0.015 |
maybe | +0.013 |
Sometimes | +0.012 |
under | +0.011 |
Neg logit contributions | |
ING | -0.021 |
ower | -0.020 |
ria | -0.020 |
iver | -0.019 |
ater | -0.019 |
Token | into |
Token ID | 656 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ria | +0.011 |
ING | +0.011 |
groom | +0.010 |
ume | +0.010 |
tap | +0.010 |
Neg logit contributions | |
sometimes | -0.011 |
Sometimes | -0.010 |
maybe | -0.010 |
dinosaurs | -0.010 |
then | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ria | +0.047 |
ING | +0.047 |
groom | +0.045 |
tap | +0.045 |
ume | +0.045 |
Neg logit contributions | |
sometimes | -0.032 |
Sometimes | -0.029 |
maybe | -0.028 |
dinosaurs | -0.027 |
then | -0.026 |
Token | warm |
Token ID | 5814 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
ria | +0.031 |
ING | +0.031 |
ume | +0.029 |
elcome | +0.028 |
groom | +0.028 |
Neg logit contributions | |
sometimes | -0.045 |
Sometimes | -0.041 |
maybe | -0.040 |
dinosaurs | -0.040 |
then | -0.040 |
Token | water |
Token ID | 1660 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
oxy | +0.093 |
ume | +0.091 |
ria | +0.091 |
ING | +0.090 |
ft | +0.087 |
Neg logit contributions | |
sometimes | -0.097 |
then | -0.086 |
dinosaurs | -0.083 |
Sometimes | -0.082 |
cast | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
ria | +0.066 |
ING | +0.066 |
slight | +0.062 |
Care | +0.062 |
oxy | +0.062 |
Neg logit contributions | |
sometimes | -0.035 |
then | -0.028 |
Sometimes | -0.027 |
maybe | -0.027 |
dinosaurs | -0.025 |
Token | started |
Token ID | 2067 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
sometimes | +0.001 |
then | +0.001 |
maybe | +0.001 |
Sometimes | +0.001 |
cast | +0.001 |
Neg logit contributions | |
ING | -0.001 |
ria | -0.001 |
ume | -0.001 |
ady | -0.001 |
ater | -0.001 |
Token | swimming |
Token ID | 14899 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ING | +0.075 |
ater | +0.071 |
oxy | +0.069 |
iver | +0.069 |
ume | +0.068 |
Neg logit contributions | |
sometimes | -0.027 |
for | -0.019 |
then | -0.019 |
Sometimes | -0.019 |
he | -0.018 |
Token | towards |
Token ID | 3371 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
ING | +0.032 |
ria | +0.032 |
tap | +0.031 |
copy | +0.030 |
groom | +0.030 |
Neg logit contributions | |
sometimes | -0.033 |
Sometimes | -0.031 |
maybe | -0.031 |
dinosaurs | -0.030 |
rob | -0.029 |
Token | came |
Token ID | 1625 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
ria | +0.018 |
ING | +0.018 |
groom | +0.017 |
ume | +0.017 |
iya | +0.016 |
Neg logit contributions | |
sometimes | -0.019 |
maybe | -0.017 |
then | -0.016 |
Sometimes | -0.016 |
dinosaurs | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
ria | +0.024 |
ume | +0.024 |
groom | +0.024 |
ING | +0.024 |
iya | +0.023 |
Neg logit contributions | |
sometimes | -0.011 |
under | -0.009 |
then | -0.008 |
Sometimes | -0.008 |
for | -0.008 |
Token | knocked |
Token ID | 13642 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
sometimes | +0.019 |
Sometimes | +0.017 |
maybe | +0.017 |
dinosaurs | +0.016 |
then | +0.016 |
Neg logit contributions | |
ING | -0.020 |
ria | -0.020 |
ume | -0.018 |
groom | -0.018 |
tap | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
sometimes | +0.001 |
maybe | +0.001 |
dinosaurs | +0.001 |
Sometimes | +0.001 |
rob | +0.000 |
Neg logit contributions | |
ria | -0.001 |
ING | -0.001 |
Care | -0.001 |
tap | -0.001 |
ume | -0.001 |
Token | se |
Token ID | 384 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
ria | +0.028 |
ING | +0.027 |
ume | +0.026 |
elcome | +0.025 |
ady | +0.025 |
Neg logit contributions | |
sometimes | -0.048 |
maybe | -0.043 |
Sometimes | -0.043 |
then | -0.042 |
dinosaurs | -0.042 |
Token | ag |
Token ID | 363 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
ING | +0.002 |
ria | +0.002 |
groom | +0.002 |
ume | +0.002 |
tap | +0.002 |
Neg logit contributions | |
sometimes | -0.002 |
Sometimes | -0.002 |
maybe | -0.002 |
rob | -0.002 |
dinosaurs | -0.002 |
Token | ull |
Token ID | 724 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
groom | +0.090 |
ria | +0.088 |
ING | +0.085 |
slight | +0.084 |
lamb | +0.083 |
Neg logit contributions | |
sometimes | -0.095 |
Sometimes | -0.082 |
maybe | -0.080 |
then | -0.079 |
cast | -0.077 |
Token | off |
Token ID | 572 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
ria | +0.032 |
ING | +0.030 |
iya | +0.030 |
groom | +0.029 |
ume | +0.029 |
Neg logit contributions | |
sometimes | -0.028 |
then | -0.023 |
maybe | -0.023 |
Sometimes | -0.023 |
under | -0.022 |
Token | course |
Token ID | 1781 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
ING | +0.020 |
ria | +0.020 |
groom | +0.019 |
ady | +0.019 |
ume | +0.019 |
Neg logit contributions | |
sometimes | -0.013 |
Sometimes | -0.011 |
maybe | -0.011 |
then | -0.011 |
dinosaurs | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
sometimes | +0.037 |
then | +0.031 |
under | +0.030 |
for | +0.029 |
Tim | +0.028 |
Neg logit contributions | |
ria | -0.071 |
groom | -0.071 |
slight | -0.069 |
ram | -0.067 |
mare | -0.066 |
Token | The |
Token ID | 383 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
sometimes | +0.008 |
Sometimes | +0.006 |
maybe | +0.006 |
dinosaurs | +0.006 |
then | +0.006 |
Neg logit contributions | |
ria | -0.016 |
ING | -0.016 |
groom | -0.015 |
ume | -0.015 |
tap | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
ria | +0.012 |
ING | +0.012 |
groom | +0.012 |
ume | +0.011 |
tap | +0.011 |
Neg logit contributions | |
sometimes | -0.008 |
Sometimes | -0.008 |
maybe | -0.007 |
dinosaurs | -0.007 |
then | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
ria | +0.019 |
ING | +0.019 |
Care | +0.019 |
tap | +0.018 |
ady | +0.018 |
Neg logit contributions | |
sometimes | -0.021 |
dinosaurs | -0.020 |
cast | -0.019 |
rob | -0.019 |
maybe | -0.019 |
Token | A |
Token ID | 32 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
groom | +0.012 |
ING | +0.011 |
ria | +0.011 |
iya | +0.011 |
tap | +0.011 |
Neg logit contributions | |
sometimes | -0.013 |
Sometimes | -0.012 |
maybe | -0.011 |
then | -0.011 |
besides | -0.010 |
Token | pretty |
Token ID | 2495 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
sometimes | +0.016 |
maybe | +0.015 |
dinosaurs | +0.014 |
Sometimes | +0.014 |
then | +0.014 |
Neg logit contributions | |
ady | -0.016 |
oxy | -0.016 |
ume | -0.016 |
iver | -0.016 |
ING | -0.016 |
Token | se |
Token ID | 384 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ING | +0.047 |
ume | +0.046 |
ria | +0.046 |
oxy | +0.045 |
Care | +0.045 |
Neg logit contributions | |
sometimes | -0.063 |
then | -0.058 |
maybe | -0.057 |
dinosaurs | -0.057 |
Sometimes | -0.056 |
Token | ag |
Token ID | 363 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
ria | +0.002 |
ING | +0.002 |
ater | +0.002 |
ume | +0.002 |
ady | +0.002 |
Neg logit contributions | |
sometimes | -0.003 |
Sometimes | -0.003 |
maybe | -0.003 |
dinosaurs | -0.003 |
then | -0.003 |
Token | ull |
Token ID | 724 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ria | +0.064 |
ING | +0.064 |
ume | +0.060 |
groom | +0.059 |
slight | +0.057 |
Neg logit contributions | |
sometimes | -0.115 |
Sometimes | -0.106 |
maybe | -0.105 |
then | -0.102 |
dinosaurs | -0.101 |
Token | swoop |
Token ID | 38527 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
ria | +0.028 |
ING | +0.028 |
ume | +0.026 |
groom | +0.026 |
tap | +0.025 |
Neg logit contributions | |
sometimes | -0.029 |
Sometimes | -0.026 |
maybe | -0.026 |
dinosaurs | -0.025 |
then | -0.025 |
Token | ed |
Token ID | 276 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
sometimes | +0.001 |
under | +0.001 |
then | +0.001 |
everywhere | +0.001 |
cast | +0.000 |
Neg logit contributions | |
ria | -0.001 |
weed | -0.001 |
iver | -0.001 |
slight | -0.001 |
tap | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ING | +0.001 |
ria | +0.001 |
tap | +0.001 |
pet | +0.001 |
groom | +0.001 |
Neg logit contributions | |
sometimes | -0.001 |
Sometimes | -0.001 |
maybe | -0.001 |
rob | -0.001 |
dinosaurs | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
sometimes | +0.003 |
Sometimes | +0.002 |
maybe | +0.002 |
dinosaurs | +0.002 |
rob | +0.002 |
Neg logit contributions | |
ING | -0.004 |
ria | -0.004 |
tap | -0.004 |
groom | -0.004 |
ume | -0.003 |
Token | pond |
Token ID | 16723 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
sometimes | +0.004 |
then | +0.004 |
maybe | +0.004 |
now | +0.004 |
dinosaurs | +0.004 |
Neg logit contributions | |
ady | -0.005 |
ume | -0.004 |
iver | -0.004 |
ING | -0.004 |
estone | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
ria | +0.054 |
ING | +0.052 |
oxy | +0.050 |
groom | +0.050 |
ume | +0.050 |
Neg logit contributions | |
sometimes | -0.037 |
then | -0.030 |
Sometimes | -0.029 |
maybe | -0.029 |
under | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
ria | +0.011 |
ING | +0.011 |
groom | +0.011 |
ater | +0.011 |
copy | +0.011 |
Neg logit contributions | |
sometimes | -0.006 |
Sometimes | -0.006 |
maybe | -0.006 |
then | -0.005 |
dinosaurs | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ume | +0.029 |
ING | +0.029 |
ria | +0.028 |
ater | +0.028 |
oxy | +0.027 |
Neg logit contributions | |
sometimes | -0.014 |
then | -0.012 |
maybe | -0.010 |
Sometimes | -0.009 |
cast | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
sometimes | +0.005 |
Sometimes | +0.004 |
maybe | +0.004 |
then | +0.004 |
dinosaurs | +0.004 |
Neg logit contributions | |
ING | -0.009 |
ria | -0.009 |
ume | -0.009 |
groom | -0.008 |
tap | -0.008 |
Token | peaceful |
Token ID | 12309 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
sometimes | +0.003 |
then | +0.003 |
maybe | +0.003 |
Sometimes | +0.003 |
dinosaurs | +0.003 |
Neg logit contributions | |
ume | -0.004 |
ING | -0.004 |
ady | -0.004 |
estone | -0.004 |
oxy | -0.003 |
Token | pond |
Token ID | 16723 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ING | +0.093 |
ume | +0.093 |
ady | +0.090 |
ria | +0.089 |
oxy | +0.089 |
Neg logit contributions | |
sometimes | -0.090 |
then | -0.081 |
Sometimes | -0.076 |
maybe | -0.072 |
for | -0.072 |
Token | with |
Token ID | 351 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
ING | +0.043 |
ria | +0.043 |
ume | +0.041 |
groom | +0.041 |
slight | +0.041 |
Neg logit contributions | |
sometimes | -0.027 |
then | -0.022 |
maybe | -0.021 |
Sometimes | -0.020 |
dinosaurs | -0.020 |
Token | lots |
Token ID | 6041 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
ria | +0.014 |
ING | +0.013 |
ume | +0.013 |
ater | +0.012 |
estone | +0.012 |
Neg logit contributions | |
sometimes | -0.009 |
Sometimes | -0.008 |
maybe | -0.008 |
dinosaurs | -0.007 |
then | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ria | +0.003 |
ING | +0.003 |
elcome | +0.003 |
groom | +0.003 |
mare | +0.003 |
Neg logit contributions | |
sometimes | -0.001 |
maybe | -0.001 |
Sometimes | -0.001 |
then | -0.001 |
dinosaurs | -0.001 |
Token | water |
Token ID | 1660 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ria | +0.028 |
ING | +0.027 |
ume | +0.025 |
elcome | +0.025 |
groom | +0.025 |
Neg logit contributions | |
sometimes | -0.036 |
Sometimes | -0.032 |
maybe | -0.032 |
dinosaurs | -0.031 |
then | -0.031 |
Token | where |
Token ID | 810 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
sometimes | +0.004 |
then | +0.004 |
maybe | +0.004 |
Sometimes | +0.003 |
dinosaurs | +0.003 |
Neg logit contributions | |
ING | -0.007 |
ria | -0.007 |
ume | -0.007 |
estone | -0.007 |
ater | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
ria | +0.020 |
groom | +0.019 |
snail | +0.019 |
tap | +0.019 |
spoken | +0.019 |
Neg logit contributions | |
rob | -0.016 |
Sometimes | -0.014 |
eighty | -0.013 |
sometimes | -0.013 |
dinosaurs | -0.012 |
Token | could |
Token ID | 714 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
ING | +0.008 |
ria | +0.008 |
groom | +0.007 |
tap | +0.007 |
slight | +0.007 |
Neg logit contributions | |
sometimes | -0.005 |
Sometimes | -0.005 |
maybe | -0.005 |
dinosaurs | -0.005 |
rob | -0.004 |
Token | feel |
Token ID | 1254 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ria | +0.000 |
ING | +0.000 |
ume | +0.000 |
ady | +0.000 |
ater | +0.000 |
Neg logit contributions | |
sometimes | -0.001 |
maybe | -0.001 |
then | -0.001 |
Sometimes | -0.000 |
now | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ria | +0.038 |
ING | +0.037 |
oxy | +0.035 |
ume | +0.035 |
groom | +0.035 |
Neg logit contributions | |
sometimes | -0.021 |
maybe | -0.018 |
Sometimes | -0.017 |
then | -0.016 |
dinosaurs | -0.015 |
Token | warm |
Token ID | 5814 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
ria | +0.027 |
ING | +0.025 |
ume | +0.025 |
itter | +0.024 |
oing | +0.024 |
Neg logit contributions | |
sometimes | -0.037 |
then | -0.033 |
maybe | -0.032 |
Sometimes | -0.032 |
dinosaurs | -0.032 |
Token | sand |
Token ID | 6450 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ria | +0.090 |
oxy | +0.086 |
ume | +0.086 |
itter | +0.086 |
ING | +0.085 |
Neg logit contributions | |
sometimes | -0.102 |
then | -0.091 |
for | -0.083 |
under | -0.079 |
he | -0.078 |
Token | beneath |
Token ID | 11061 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ria | +0.057 |
ING | +0.056 |
ume | +0.053 |
Care | +0.052 |
groom | +0.052 |
Neg logit contributions | |
sometimes | -0.047 |
maybe | -0.041 |
then | -0.039 |
cast | -0.039 |
Sometimes | -0.039 |
Token | his |
Token ID | 465 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ING | +0.008 |
ria | +0.008 |
groom | +0.007 |
tap | +0.007 |
ume | +0.007 |
Neg logit contributions | |
sometimes | -0.004 |
Sometimes | -0.003 |
maybe | -0.003 |
dinosaurs | -0.003 |
then | -0.003 |
Token | claws |
Token ID | 28421 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ria | +0.026 |
Care | +0.025 |
Girl | +0.024 |
ume | +0.024 |
mare | +0.023 |
Neg logit contributions | |
sometimes | -0.029 |
then | -0.027 |
dinosaurs | -0.027 |
everywhere | -0.026 |
for | -0.025 |
Token | once |
Token ID | 1752 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
ria | +0.006 |
ING | +0.006 |
ram | +0.006 |
groom | +0.006 |
oxy | +0.006 |
Neg logit contributions | |
sometimes | -0.004 |
then | -0.003 |
maybe | -0.003 |
Sometimes | -0.003 |
cast | -0.003 |
Token | glad |
Token ID | 9675 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
ING | +0.014 |
ater | +0.014 |
estone | +0.013 |
ria | +0.013 |
oing | +0.013 |
Neg logit contributions | |
sometimes | -0.008 |
maybe | -0.008 |
then | -0.007 |
Sometimes | -0.007 |
now | -0.006 |
Token | I |
Token ID | 314 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
ING | +0.018 |
ria | +0.018 |
ume | +0.017 |
groom | +0.017 |
slight | +0.017 |
Neg logit contributions | |
sometimes | -0.016 |
Sometimes | -0.014 |
maybe | -0.014 |
dinosaurs | -0.013 |
then | -0.013 |
Token | could |
Token ID | 714 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ING | +0.020 |
ria | +0.020 |
ume | +0.019 |
groom | +0.019 |
slight | +0.019 |
Neg logit contributions | |
sometimes | -0.013 |
maybe | -0.011 |
then | -0.010 |
Sometimes | -0.010 |
dinosaurs | -0.009 |
Token | help |
Token ID | 1037 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
ria | +0.004 |
ING | +0.004 |
ume | +0.004 |
Care | +0.004 |
iya | +0.004 |
Neg logit contributions | |
sometimes | -0.004 |
then | -0.003 |
maybe | -0.003 |
now | -0.003 |
Sometimes | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
sometimes | +0.000 |
maybe | +0.000 |
then | +0.000 |
Sometimes | +0.000 |
dinosaurs | +0.000 |
Neg logit contributions | |
slight | -0.000 |
ING | -0.000 |
ria | -0.000 |
ume | -0.000 |
ady | -0.000 |
Token | tad |
Token ID | 36264 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
ria | +0.029 |
ING | +0.028 |
ume | +0.028 |
ady | +0.027 |
oing | +0.027 |
Neg logit contributions | |
sometimes | -0.041 |
dinosaurs | -0.038 |
Sometimes | -0.037 |
maybe | -0.036 |
then | -0.035 |
Token | p |
Token ID | 79 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
ria | +0.091 |
ING | +0.085 |
iya | +0.085 |
groom | +0.081 |
mare | +0.080 |
Neg logit contributions | |
sometimes | -0.094 |
maybe | -0.083 |
Sometimes | -0.079 |
then | -0.079 |
for | -0.075 |
Token | oles |
Token ID | 4316 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ria | +0.055 |
ING | +0.054 |
slight | +0.053 |
iya | +0.053 |
groom | +0.052 |
Neg logit contributions | |
sometimes | -0.057 |
maybe | -0.048 |
then | -0.048 |
for | -0.046 |
Sometimes | -0.045 |
Token | ". |
Token ID | 1911 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
ria | +0.063 |
ING | +0.061 |
Care | +0.058 |
oxy | +0.057 |
iya | +0.057 |
Neg logit contributions | |
sometimes | -0.049 |
maybe | -0.041 |
then | -0.040 |
Sometimes | -0.039 |
dinosaurs | -0.036 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ING | +0.026 |
ria | +0.026 |
groom | +0.025 |
ater | +0.025 |
slight | +0.025 |
Neg logit contributions | |
sometimes | -0.017 |
Sometimes | -0.015 |
maybe | -0.015 |
then | -0.014 |
dinosaurs | -0.013 |
Token | One |
Token ID | 3198 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
sometimes | +0.007 |
maybe | +0.006 |
Sometimes | +0.006 |
then | +0.006 |
dinosaurs | +0.006 |
Neg logit contributions | |
ING | -0.007 |
ria | -0.007 |
ume | -0.006 |
tap | -0.006 |
Care | -0.006 |
Token | She |
Token ID | 3347 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
unk | +0.008 |
ING | +0.008 |
aa | +0.008 |
itter | +0.008 |
ower | +0.008 |
Neg logit contributions | |
sometimes | -0.006 |
then | -0.004 |
Sometimes | -0.004 |
maybe | -0.004 |
besides | -0.004 |
Token | w |
Token ID | 266 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
ria | +0.007 |
ING | +0.006 |
groom | +0.006 |
tap | +0.006 |
elcome | +0.006 |
Neg logit contributions | |
sometimes | -0.008 |
Sometimes | -0.007 |
maybe | -0.007 |
dinosaurs | -0.007 |
rob | -0.007 |
Token | aded |
Token ID | 5286 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ria | +0.005 |
ING | +0.005 |
groom | +0.005 |
tap | +0.005 |
glimpse | +0.005 |
Neg logit contributions | |
sometimes | -0.006 |
Sometimes | -0.006 |
maybe | -0.006 |
then | -0.006 |
dinosaurs | -0.006 |
Token | into |
Token ID | 656 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ING | +0.044 |
ria | +0.044 |
ume | +0.041 |
groom | +0.041 |
tap | +0.041 |
Neg logit contributions | |
sometimes | -0.037 |
Sometimes | -0.032 |
maybe | -0.032 |
dinosaurs | -0.031 |
then | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
tap | +0.043 |
ria | +0.043 |
ING | +0.042 |
groom | +0.041 |
copy | +0.041 |
Neg logit contributions | |
sometimes | -0.035 |
Sometimes | -0.033 |
maybe | -0.031 |
rob | -0.031 |
dinosaurs | -0.030 |
Token | warm |
Token ID | 5814 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
ria | +0.031 |
ING | +0.031 |
ume | +0.029 |
oxy | +0.029 |
groom | +0.029 |
Neg logit contributions | |
sometimes | -0.037 |
Sometimes | -0.033 |
then | -0.032 |
maybe | -0.032 |
dinosaurs | -0.031 |
Token | ocean |
Token ID | 9151 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
oxy | +0.095 |
ria | +0.094 |
ume | +0.092 |
ING | +0.092 |
ram | +0.088 |
Neg logit contributions | |
sometimes | -0.090 |
then | -0.079 |
Sometimes | -0.076 |
dinosaurs | -0.076 |
cast | -0.074 |
Token | water |
Token ID | 1660 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ria | +0.054 |
ING | +0.053 |
ume | +0.051 |
Care | +0.051 |
slight | +0.050 |
Neg logit contributions | |
sometimes | -0.028 |
then | -0.023 |
maybe | -0.022 |
dinosaurs | -0.021 |
Sometimes | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
ria | +0.047 |
ING | +0.046 |
ume | +0.044 |
groom | +0.044 |
slight | +0.043 |
Neg logit contributions | |
sometimes | -0.029 |
maybe | -0.024 |
then | -0.024 |
Sometimes | -0.024 |
dinosaurs | -0.023 |
Token | She |
Token ID | 1375 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
ater | +0.016 |
ING | +0.015 |
groom | +0.015 |
ria | +0.015 |
ram | +0.015 |
Neg logit contributions | |
Sometimes | -0.008 |
sometimes | -0.008 |
maybe | -0.007 |
then | -0.006 |
Tim | -0.006 |
Token | saw |
Token ID | 2497 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
ria | +0.014 |
ING | +0.014 |
groom | +0.013 |
tap | +0.013 |
ume | +0.013 |
Neg logit contributions | |
sometimes | -0.014 |
Sometimes | -0.013 |
maybe | -0.012 |
dinosaurs | -0.012 |
then | -0.011 |
Token | special |
Token ID | 2041 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ING | +0.014 |
ria | +0.014 |
groom | +0.013 |
ume | +0.013 |
ater | +0.013 |
Neg logit contributions | |
sometimes | -0.011 |
maybe | -0.010 |
then | -0.010 |
Sometimes | -0.010 |
dinosaurs | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
sometimes | +0.007 |
maybe | +0.006 |
Sometimes | +0.006 |
then | +0.005 |
dinosaurs | +0.005 |
Neg logit contributions | |
ria | -0.008 |
ING | -0.008 |
groom | -0.008 |
ume | -0.008 |
slight | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
copy | +0.048 |
ater | +0.048 |
groom | +0.046 |
ING | +0.045 |
iver | +0.045 |
Neg logit contributions | |
Sometimes | -0.024 |
sometimes | -0.022 |
maybe | -0.021 |
then | -0.017 |
Tim | -0.017 |
Token | saw |
Token ID | 2497 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
ING | +0.018 |
ria | +0.018 |
ume | +0.017 |
groom | +0.017 |
tap | +0.016 |
Neg logit contributions | |
sometimes | -0.014 |
maybe | -0.012 |
then | -0.012 |
Sometimes | -0.012 |
dinosaurs | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ria | +0.021 |
ING | +0.021 |
groom | +0.020 |
tap | +0.020 |
ume | +0.020 |
Neg logit contributions | |
sometimes | -0.014 |
Sometimes | -0.012 |
maybe | -0.012 |
dinosaurs | -0.011 |
then | -0.011 |
Token | gentle |
Token ID | 10296 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
ume | +0.004 |
ING | +0.004 |
ria | +0.004 |
oxy | +0.004 |
estone | +0.004 |
Neg logit contributions | |
sometimes | -0.003 |
dinosaurs | -0.003 |
then | -0.003 |
maybe | -0.003 |
Sometimes | -0.003 |
Token | glow |
Token ID | 19634 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
ING | +0.083 |
ria | +0.082 |
ume | +0.080 |
oxy | +0.080 |
ady | +0.075 |
Neg logit contributions | |
sometimes | -0.096 |
then | -0.085 |
maybe | -0.080 |
Sometimes | -0.080 |
dinosaurs | -0.079 |
Token | coming |
Token ID | 2406 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ria | +0.015 |
ING | +0.015 |
oxy | +0.014 |
ume | +0.014 |
iya | +0.014 |
Neg logit contributions | |
sometimes | -0.011 |
then | -0.009 |
maybe | -0.009 |
dinosaurs | -0.009 |
Sometimes | -0.009 |
Token | from |
Token ID | 422 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
ING | +0.030 |
ria | +0.029 |
groom | +0.028 |
ume | +0.028 |
ater | +0.028 |
Neg logit contributions | |
sometimes | -0.017 |
maybe | -0.013 |
then | -0.013 |
Sometimes | -0.013 |
under | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
rob | +0.014 |
sometimes | +0.013 |
dinosaurs | +0.013 |
maybe | +0.013 |
Sometimes | +0.013 |
Neg logit contributions | |
tap | -0.013 |
pet | -0.013 |
lamb | -0.012 |
groom | -0.012 |
poppy | -0.012 |
Token | small |
Token ID | 1402 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ria | +0.018 |
ING | +0.018 |
ume | +0.017 |
oxy | +0.017 |
oing | +0.017 |
Neg logit contributions | |
sometimes | -0.019 |
Sometimes | -0.016 |
dinosaurs | -0.016 |
then | -0.016 |
maybe | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ria | +0.011 |
ING | +0.010 |
Care | +0.010 |
ady | +0.009 |
Her | +0.009 |
Neg logit contributions | |
sometimes | -0.014 |
dinosaurs | -0.014 |
narrative | -0.013 |
cast | -0.013 |
rob | -0.013 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
sometimes | +0.003 |
Sometimes | +0.003 |
maybe | +0.003 |
then | +0.003 |
dinosaurs | +0.003 |
Neg logit contributions | |
ING | -0.003 |
ria | -0.003 |
groom | -0.003 |
ume | -0.003 |
iya | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
ING | +0.015 |
ria | +0.014 |
tap | +0.014 |
elcome | +0.014 |
ume | +0.013 |
Neg logit contributions | |
sometimes | -0.014 |
Sometimes | -0.013 |
maybe | -0.012 |
rob | -0.012 |
dinosaurs | -0.012 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
ING | +0.019 |
ria | +0.019 |
groom | +0.018 |
ume | +0.018 |
tap | +0.018 |
Neg logit contributions | |
sometimes | -0.021 |
Sometimes | -0.019 |
maybe | -0.019 |
dinosaurs | -0.018 |
then | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
spoken | +0.011 |
pet | +0.011 |
tap | +0.011 |
human | +0.011 |
neighbour | +0.011 |
Neg logit contributions | |
sometimes | -0.017 |
narrative | -0.017 |
rob | -0.017 |
cast | -0.017 |
Sometimes | -0.017 |
Token | peaceful |
Token ID | 12309 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
ady | +0.011 |
ume | +0.010 |
ria | +0.010 |
ING | +0.010 |
estone | +0.010 |
Neg logit contributions | |
sometimes | -0.008 |
maybe | -0.008 |
dinosaurs | -0.008 |
then | -0.007 |
Sometimes | -0.007 |
Token | pond |
Token ID | 16723 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ume | +0.081 |
ady | +0.079 |
ING | +0.078 |
ria | +0.077 |
Care | +0.077 |
Neg logit contributions | |
sometimes | -0.093 |
then | -0.084 |
dinosaurs | -0.081 |
Sometimes | -0.079 |
maybe | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ria | +0.057 |
ING | +0.055 |
groom | +0.054 |
ume | +0.053 |
iya | +0.053 |
Neg logit contributions | |
sometimes | -0.037 |
then | -0.030 |
Sometimes | -0.030 |
maybe | -0.029 |
under | -0.028 |
Token | he |
Token ID | 339 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
ria | +0.005 |
ING | +0.005 |
groom | +0.004 |
tap | +0.004 |
slight | +0.004 |
Neg logit contributions | |
sometimes | -0.004 |
Sometimes | -0.004 |
maybe | -0.004 |
rob | -0.004 |
dinosaurs | -0.004 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
sometimes | +0.001 |
maybe | +0.001 |
Sometimes | +0.001 |
then | +0.001 |
dinosaurs | +0.001 |
Neg logit contributions | |
ING | -0.002 |
ria | -0.002 |
ume | -0.001 |
groom | -0.001 |
tap | -0.001 |
Token | this |
Token ID | 428 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
ria | +0.003 |
ING | +0.003 |
groom | +0.003 |
tap | +0.003 |
ume | +0.003 |
Neg logit contributions | |
sometimes | -0.004 |
Sometimes | -0.003 |
maybe | -0.003 |
dinosaurs | -0.003 |
rob | -0.003 |
Token | looking |
Token ID | 2045 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
ING | +0.010 |
ria | +0.010 |
ume | +0.009 |
groom | +0.009 |
tap | +0.009 |
Neg logit contributions | |
sometimes | -0.008 |
Sometimes | -0.007 |
maybe | -0.007 |
dinosaurs | -0.007 |
then | -0.007 |
Token | around |
Token ID | 1088 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ING | +0.009 |
ria | +0.009 |
groom | +0.009 |
ume | +0.009 |
tap | +0.008 |
Neg logit contributions | |
sometimes | -0.006 |
Sometimes | -0.005 |
maybe | -0.005 |
then | -0.005 |
dinosaurs | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
sometimes | +0.003 |
Sometimes | +0.003 |
rob | +0.003 |
maybe | +0.003 |
dinosaurs | +0.003 |
Neg logit contributions | |
ria | -0.004 |
ING | -0.004 |
tap | -0.004 |
groom | -0.004 |
copy | -0.004 |
Token | enjoying |
Token ID | 13226 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ria | +0.019 |
tap | +0.018 |
ING | +0.018 |
groom | +0.018 |
slight | +0.018 |
Neg logit contributions | |
sometimes | -0.019 |
Sometimes | -0.018 |
dinosaurs | -0.018 |
rob | -0.018 |
maybe | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ria | +0.037 |
ING | +0.037 |
groom | +0.035 |
tap | +0.035 |
ume | +0.035 |
Neg logit contributions | |
sometimes | -0.025 |
Sometimes | -0.023 |
maybe | -0.022 |
dinosaurs | -0.021 |
then | -0.020 |
Token | peaceful |
Token ID | 12309 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
ria | +0.033 |
ING | +0.033 |
ume | +0.032 |
groom | +0.031 |
oxy | +0.030 |
Neg logit contributions | |
sometimes | -0.040 |
Sometimes | -0.036 |
maybe | -0.035 |
then | -0.034 |
dinosaurs | -0.034 |
Token | view |
Token ID | 1570 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
ria | +0.090 |
ING | +0.088 |
ume | +0.086 |
oxy | +0.085 |
ady | +0.084 |
Neg logit contributions | |
sometimes | -0.092 |
Sometimes | -0.079 |
then | -0.078 |
maybe | -0.077 |
dinosaurs | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
sometimes | +0.008 |
maybe | +0.007 |
Sometimes | +0.007 |
then | +0.007 |
dinosaurs | +0.007 |
Neg logit contributions | |
ING | -0.010 |
ria | -0.010 |
groom | -0.010 |
ume | -0.009 |
elcome | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ria | +0.000 |
ING | +0.000 |
ume | +0.000 |
tap | +0.000 |
slight | +0.000 |
Neg logit contributions | |
sometimes | -0.000 |
maybe | -0.000 |
Sometimes | -0.000 |
dinosaurs | -0.000 |
then | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
groom | +0.009 |
ING | +0.008 |
ria | +0.008 |
ater | +0.008 |
copy | +0.008 |
Neg logit contributions | |
sometimes | -0.004 |
Sometimes | -0.004 |
maybe | -0.004 |
then | -0.003 |
cast | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
ria | +0.008 |
ING | +0.008 |
Care | +0.008 |
elcome | +0.008 |
ady | +0.007 |
Neg logit contributions | |
sometimes | -0.008 |
dinosaurs | -0.007 |
Sometimes | -0.007 |
maybe | -0.007 |
rob | -0.006 |
Token | at |
Token ID | 379 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
sometimes | +0.018 |
Sometimes | +0.016 |
maybe | +0.016 |
dinosaurs | +0.015 |
rob | +0.015 |
Neg logit contributions | |
ING | -0.021 |
ria | -0.021 |
tap | -0.020 |
groom | -0.020 |
slight | -0.020 |
Token | him |
Token ID | 683 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
pet | +0.008 |
hand | +0.008 |
ING | +0.008 |
tap | +0.007 |
human | +0.007 |
Neg logit contributions | |
narrative | -0.007 |
sometimes | -0.007 |
rob | -0.007 |
besides | -0.007 |
maybe | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
ria | +0.012 |
ING | +0.012 |
ume | +0.012 |
groom | +0.012 |
mare | +0.012 |
Neg logit contributions | |
sometimes | -0.006 |
then | -0.005 |
maybe | -0.005 |
Sometimes | -0.005 |
dinosaurs | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
sometimes | +0.009 |
then | +0.009 |
maybe | +0.008 |
Sometimes | +0.007 |
he | +0.007 |
Neg logit contributions | |
ING | -0.019 |
ume | -0.018 |
ria | -0.018 |
ater | -0.018 |
estone | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
ING | +0.008 |
ria | +0.008 |
slight | +0.008 |
groom | +0.008 |
tap | +0.008 |
Neg logit contributions | |
sometimes | -0.009 |
Sometimes | -0.008 |
dinosaurs | -0.008 |
maybe | -0.008 |
rob | -0.008 |
Token | gentle |
Token ID | 10296 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
oxy | +0.001 |
ING | +0.001 |
cess | +0.001 |
ume | +0.001 |
ater | +0.001 |
Neg logit contributions | |
he | -0.000 |
hard | -0.000 |
maybe | -0.000 |
everywhere | -0.000 |
then | -0.000 |
Token | gesture |
Token ID | 18342 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
ING | +0.081 |
oxy | +0.081 |
ria | +0.079 |
ume | +0.078 |
ich | +0.075 |
Neg logit contributions | |
sometimes | -0.083 |
for | -0.081 |
then | -0.079 |
he | -0.077 |
maybe | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
sometimes | +0.000 |
then | +0.000 |
maybe | +0.000 |
for | +0.000 |
he | +0.000 |
Neg logit contributions | |
ING | -0.001 |
ria | -0.001 |
slight | -0.001 |
oxy | -0.001 |
iver | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
sometimes | +0.004 |
maybe | +0.003 |
Sometimes | +0.003 |
then | +0.003 |
dinosaurs | +0.003 |
Neg logit contributions | |
ING | -0.011 |
ria | -0.011 |
ume | -0.010 |
groom | -0.010 |
ater | -0.010 |
Token | pushed |
Token ID | 7121 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
sometimes | +0.013 |
maybe | +0.011 |
then | +0.011 |
Sometimes | +0.011 |
dinosaurs | +0.010 |
Neg logit contributions | |
ING | -0.016 |
ria | -0.016 |
ume | -0.015 |
estone | -0.015 |
ater | -0.015 |
Token | him |
Token ID | 683 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
sometimes | +0.010 |
Sometimes | +0.009 |
rob | +0.009 |
maybe | +0.009 |
dinosaurs | +0.008 |
Neg logit contributions | |
ING | -0.015 |
ria | -0.015 |
tap | -0.015 |
pet | -0.015 |
copy | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ING | +0.020 |
ume | +0.018 |
ria | +0.018 |
estone | +0.017 |
ater | +0.017 |
Neg logit contributions | |
sometimes | -0.012 |
then | -0.011 |
maybe | -0.010 |
now | -0.009 |
Sometimes | -0.009 |
Token | blowing |
Token ID | 19280 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
ING | +0.045 |
ume | +0.042 |
ria | +0.041 |
ive | +0.039 |
itter | +0.038 |
Neg logit contributions | |
sometimes | -0.032 |
then | -0.029 |
cast | -0.026 |
maybe | -0.026 |
Sometimes | -0.025 |
Token | until |
Token ID | 1566 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
ria | +0.020 |
ING | +0.020 |
tap | +0.019 |
ume | +0.018 |
groom | +0.018 |
Neg logit contributions | |
sometimes | -0.014 |
Sometimes | -0.013 |
maybe | -0.012 |
dinosaurs | -0.012 |
then | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
sometimes | +0.001 |
maybe | +0.001 |
Sometimes | +0.001 |
then | +0.001 |
dinosaurs | +0.001 |
Neg logit contributions | |
ING | -0.001 |
ria | -0.001 |
ume | -0.001 |
groom | -0.001 |
tap | -0.001 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
sometimes | +0.022 |
Sometimes | +0.020 |
maybe | +0.020 |
dinosaurs | +0.019 |
then | +0.019 |
Neg logit contributions | |
ria | -0.020 |
ING | -0.020 |
groom | -0.019 |
ume | -0.019 |
elcome | -0.018 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
sometimes | +0.027 |
maybe | +0.022 |
Sometimes | +0.022 |
then | +0.022 |
dinosaurs | +0.020 |
Neg logit contributions | |
ING | -0.037 |
ria | -0.037 |
groom | -0.036 |
iya | -0.035 |
ume | -0.035 |
Token | ay |
Token ID | 323 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
sometimes | +0.136 |
dinosaurs | +0.129 |
maybe | +0.123 |
rob | +0.120 |
eighty | +0.120 |
Neg logit contributions | |
itter | -0.065 |
ria | -0.063 |
ING | -0.062 |
ume | -0.061 |
ower | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
sometimes | +0.025 |
maybe | +0.021 |
then | +0.021 |
Sometimes | +0.020 |
dinosaurs | +0.018 |
Neg logit contributions | |
ING | -0.035 |
ria | -0.034 |
groom | -0.033 |
ady | -0.033 |
ram | -0.033 |
Token | so |
Token ID | 523 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
sometimes | +0.030 |
then | +0.026 |
maybe | +0.024 |
under | +0.024 |
everywhere | +0.024 |
Neg logit contributions | |
ING | -0.040 |
ria | -0.038 |
oing | -0.036 |
oxy | -0.036 |
ram | -0.036 |
Token | dry |
Token ID | 5894 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
ING | +0.006 |
ria | +0.006 |
ram | +0.005 |
oxy | +0.005 |
ume | +0.005 |
Neg logit contributions | |
sometimes | -0.005 |
maybe | -0.005 |
then | -0.005 |
Sometimes | -0.005 |
now | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ria | +0.008 |
ING | +0.008 |
tap | +0.008 |
ume | +0.008 |
groom | +0.008 |
Neg logit contributions | |
sometimes | -0.009 |
Sometimes | -0.009 |
maybe | -0.008 |
dinosaurs | -0.008 |
rob | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
sometimes | +0.005 |
Sometimes | +0.005 |
rob | +0.005 |
maybe | +0.005 |
dinosaurs | +0.005 |
Neg logit contributions | |
ING | -0.004 |
ria | -0.004 |
tap | -0.004 |
ume | -0.004 |
copy | -0.004 |
Token | I |
Token ID | 314 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
ING | +0.009 |
ria | +0.009 |
tap | +0.009 |
ume | +0.009 |
slight | +0.009 |
Neg logit contributions | |
sometimes | -0.009 |
cast | -0.008 |
rob | -0.008 |
dinosaurs | -0.008 |
maybe | -0.007 |
Token | have |
Token ID | 423 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
copy | +0.001 |
tap | +0.001 |
ING | +0.001 |
ria | +0.001 |
pet | +0.001 |
Neg logit contributions | |
rob | -0.001 |
sometimes | -0.001 |
dinosaurs | -0.001 |
Sometimes | -0.001 |
cast | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
sometimes | +0.005 |
Sometimes | +0.005 |
maybe | +0.005 |
dinosaurs | +0.004 |
then | +0.004 |
Neg logit contributions | |
ria | -0.007 |
ING | -0.007 |
groom | -0.007 |
ume | -0.007 |
tap | -0.007 |
Token | screw |
Token ID | 9580 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Sometimes | +0.016 |
maybe | +0.015 |
sometimes | +0.015 |
dinosaurs | +0.014 |
for | +0.014 |
Neg logit contributions | |
ING | -0.017 |
oxy | -0.017 |
ani | -0.016 |
iya | -0.016 |
ume | -0.016 |
Token | driver |
Token ID | 26230 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
Sometimes | +0.043 |
sometimes | +0.042 |
narrative | +0.040 |
maybe | +0.040 |
cast | +0.039 |
Neg logit contributions | |
ume | -0.056 |
ater | -0.056 |
tap | -0.056 |
ING | -0.055 |
op | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Sometimes | +0.113 |
maybe | +0.113 |
rob | +0.112 |
narrative | +0.110 |
cast | +0.105 |
Neg logit contributions | |
ater | -0.069 |
ING | -0.065 |
ume | -0.064 |
copy | -0.062 |
tap | -0.062 |
Token | It |
Token ID | 632 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
ING | +0.009 |
ria | +0.009 |
ume | +0.008 |
tap | +0.008 |
Care | +0.008 |
Neg logit contributions | |
sometimes | -0.008 |
cast | -0.008 |
rob | -0.008 |
dinosaurs | -0.007 |
maybe | -0.007 |
Token | is |
Token ID | 318 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
sometimes | +0.007 |
Sometimes | +0.006 |
maybe | +0.006 |
dinosaurs | +0.006 |
rob | +0.006 |
Neg logit contributions | |
ING | -0.008 |
ria | -0.007 |
tap | -0.007 |
ume | -0.007 |
copy | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
sometimes | +0.032 |
rob | +0.031 |
Sometimes | +0.030 |
maybe | +0.029 |
cast | +0.029 |
Neg logit contributions | |
ria | -0.033 |
tap | -0.033 |
ING | -0.033 |
groom | -0.032 |
copy | -0.032 |
Token | reliable |
Token ID | 9314 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
sometimes | +0.030 |
maybe | +0.028 |
Sometimes | +0.028 |
dinosaurs | +0.027 |
then | +0.027 |
Neg logit contributions | |
ING | -0.027 |
ria | -0.027 |
ume | -0.026 |
iya | -0.025 |
ady | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
ING | +0.012 |
ria | +0.012 |
groom | +0.011 |
ume | +0.011 |
tap | +0.011 |
Neg logit contributions | |
sometimes | -0.007 |
Sometimes | -0.006 |
maybe | -0.006 |
dinosaurs | -0.006 |
then | -0.006 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
sometimes | +0.008 |
maybe | +0.007 |
Sometimes | +0.007 |
then | +0.007 |
dinosaurs | +0.007 |
Neg logit contributions | |
ING | -0.010 |
ria | -0.010 |
ume | -0.010 |
slight | -0.009 |
groom | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
pet | +0.002 |
ria | +0.002 |
groom | +0.002 |
copy | +0.002 |
hand | +0.002 |
Neg logit contributions | |
sometimes | -0.002 |
cast | -0.002 |
rob | -0.002 |
narrative | -0.002 |
Sometimes | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
sometimes | +0.005 |
maybe | +0.004 |
then | +0.004 |
Sometimes | +0.003 |
Tim | +0.003 |
Neg logit contributions | |
ING | -0.016 |
ria | -0.015 |
ower | -0.015 |
elcome | -0.015 |
iya | -0.015 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
sometimes | +0.014 |
Sometimes | +0.013 |
maybe | +0.013 |
then | +0.012 |
dinosaurs | +0.012 |
Neg logit contributions | |
ria | -0.021 |
ING | -0.021 |
iya | -0.021 |
groom | -0.020 |
ume | -0.020 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
sometimes | +0.028 |
maybe | +0.024 |
Sometimes | +0.024 |
then | +0.023 |
dinosaurs | +0.022 |
Neg logit contributions | |
ING | -0.046 |
ria | -0.046 |
groom | -0.045 |
iya | -0.045 |
ume | -0.043 |
Token | ay |
Token ID | 323 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
sometimes | +0.136 |
dinosaurs | +0.125 |
maybe | +0.123 |
Sometimes | +0.120 |
rob | +0.119 |
Neg logit contributions | |
itter | -0.061 |
ria | -0.060 |
ING | -0.059 |
op | -0.058 |
ume | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
sometimes | +0.054 |
Sometimes | +0.048 |
maybe | +0.048 |
dinosaurs | +0.045 |
then | +0.045 |
Neg logit contributions | |
ING | -0.058 |
ria | -0.058 |
groom | -0.054 |
ume | -0.054 |
tap | -0.054 |
Token | She |
Token ID | 1375 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
sometimes | +0.013 |
Sometimes | +0.011 |
maybe | +0.011 |
dinosaurs | +0.010 |
then | +0.010 |
Neg logit contributions | |
ria | -0.021 |
ING | -0.021 |
groom | -0.020 |
ume | -0.020 |
tap | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
sometimes | +0.004 |
Sometimes | +0.003 |
maybe | +0.003 |
dinosaurs | +0.003 |
rob | +0.003 |
Neg logit contributions | |
ria | -0.004 |
groom | -0.004 |
ING | -0.004 |
tap | -0.004 |
elcome | -0.004 |
Token | very |
Token ID | 845 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
sometimes | +0.013 |
maybe | +0.011 |
Sometimes | +0.011 |
then | +0.011 |
dinosaurs | +0.010 |
Neg logit contributions | |
ING | -0.024 |
ria | -0.023 |
ume | -0.022 |
ater | -0.022 |
tap | -0.022 |
Token | pa |
Token ID | 8957 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
sometimes | +0.035 |
Sometimes | +0.032 |
maybe | +0.032 |
then | +0.029 |
dinosaurs | +0.029 |
Neg logit contributions | |
ria | -0.048 |
ING | -0.048 |
ady | -0.045 |
tap | -0.045 |
elcome | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
sometimes | +0.002 |
maybe | +0.002 |
then | +0.002 |
Sometimes | +0.002 |
dinosaurs | +0.002 |
Neg logit contributions | |
ING | -0.003 |
ria | -0.003 |
ume | -0.003 |
estone | -0.003 |
groom | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
ria | +0.013 |
ING | +0.013 |
groom | +0.012 |
ume | +0.012 |
tap | +0.012 |
Neg logit contributions | |
sometimes | -0.011 |
Sometimes | -0.010 |
maybe | -0.010 |
dinosaurs | -0.010 |
then | -0.009 |
Token | expensive |
Token ID | 5789 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
sometimes | +0.013 |
Sometimes | +0.012 |
maybe | +0.012 |
rob | +0.012 |
then | +0.011 |
Neg logit contributions | |
tap | -0.009 |
ria | -0.009 |
ING | -0.009 |
slight | -0.009 |
groom | -0.008 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
sometimes | +0.028 |
maybe | +0.025 |
Sometimes | +0.025 |
dinosaurs | +0.024 |
then | +0.023 |
Neg logit contributions | |
ING | -0.033 |
ria | -0.032 |
ume | -0.031 |
groom | -0.031 |
iya | -0.030 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
sometimes | +0.029 |
Sometimes | +0.026 |
maybe | +0.026 |
dinosaurs | +0.024 |
then | +0.024 |
Neg logit contributions | |
ING | -0.034 |
ria | -0.034 |
groom | -0.032 |
ume | -0.032 |
slight | -0.031 |
Token | ay |
Token ID | 323 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
sometimes | +0.143 |
dinosaurs | +0.132 |
maybe | +0.131 |
then | +0.126 |
Sometimes | +0.126 |
Neg logit contributions | |
itter | -0.055 |
ower | -0.050 |
op | -0.048 |
ria | -0.048 |
ume | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
sometimes | +0.038 |
Sometimes | +0.033 |
maybe | +0.033 |
dinosaurs | +0.031 |
then | +0.030 |
Neg logit contributions | |
ria | -0.056 |
ING | -0.056 |
groom | -0.053 |
ume | -0.052 |
tap | -0.052 |
Token | At |
Token ID | 1629 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ING | +0.014 |
ria | +0.014 |
groom | +0.013 |
ume | +0.013 |
tap | +0.013 |
Neg logit contributions | |
sometimes | -0.009 |
Sometimes | -0.008 |
maybe | -0.008 |
dinosaurs | -0.008 |
then | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
besides | +0.033 |
dinosaurs | +0.033 |
Did | +0.032 |
narrative | +0.032 |
maybe | +0.032 |
Neg logit contributions | |
ria | -0.019 |
step | -0.018 |
tap | -0.017 |
massage | -0.017 |
hand | -0.016 |
Token | end |
Token ID | 886 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
sometimes | +0.009 |
Sometimes | +0.008 |
maybe | +0.008 |
dinosaurs | +0.007 |
then | +0.007 |
Neg logit contributions | |
ING | -0.013 |
ria | -0.013 |
ume | -0.012 |
groom | -0.012 |
slight | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
sometimes | +0.031 |
Sometimes | +0.028 |
maybe | +0.027 |
dinosaurs | +0.026 |
then | +0.025 |
Neg logit contributions | |
ria | -0.042 |
ING | -0.042 |
ume | -0.040 |
tap | -0.040 |
groom | -0.040 |
Token | Ben |
Token ID | 3932 |
Feature activation | -9.56e-03 |
Pos logit contributions | |
ria | +0.019 |
ING | +0.019 |
tap | +0.019 |
groom | +0.018 |
ume | +0.018 |
Neg logit contributions | |
sometimes | -0.016 |
Sometimes | -0.014 |
maybe | -0.013 |
dinosaurs | -0.013 |
rob | -0.013 |
Token | gets |
Token ID | 3011 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
sometimes | +0.000 |
Sometimes | +0.000 |
maybe | +0.000 |
dinosaurs | +0.000 |
then | +0.000 |
Neg logit contributions | |
ria | -0.000 |
ING | -0.000 |
groom | -0.000 |
ume | -0.000 |
tap | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ING | +0.044 |
ria | +0.043 |
ume | +0.040 |
groom | +0.040 |
iya | +0.040 |
Neg logit contributions | |
sometimes | -0.026 |
maybe | -0.022 |
Sometimes | -0.022 |
then | -0.021 |
dinosaurs | -0.020 |
Token | screw |
Token ID | 9580 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
maybe | +0.007 |
Sometimes | +0.007 |
sometimes | +0.007 |
for | +0.006 |
then | +0.006 |
Neg logit contributions | |
iya | -0.010 |
oxy | -0.010 |
ING | -0.010 |
ani | -0.010 |
iver | -0.010 |
Token | driver |
Token ID | 26230 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
sometimes | +0.044 |
Sometimes | +0.042 |
maybe | +0.040 |
dinosaurs | +0.037 |
rob | +0.037 |
Neg logit contributions | |
ING | -0.065 |
tap | -0.065 |
ria | -0.064 |
ume | -0.064 |
ater | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
sometimes | +0.106 |
Sometimes | +0.105 |
maybe | +0.104 |
dinosaurs | +0.097 |
rob | +0.097 |
Neg logit contributions | |
ING | -0.080 |
ria | -0.078 |
tap | -0.077 |
ume | -0.076 |
ater | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
ria | +0.029 |
ING | +0.029 |
ater | +0.028 |
ume | +0.028 |
groom | +0.027 |
Neg logit contributions | |
sometimes | -0.013 |
Sometimes | -0.013 |
maybe | -0.011 |
then | -0.010 |
dinosaurs | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
ria | +0.018 |
ING | +0.018 |
Care | +0.017 |
tap | +0.016 |
ume | +0.016 |
Neg logit contributions | |
sometimes | -0.019 |
dinosaurs | -0.017 |
maybe | -0.017 |
then | -0.017 |
rob | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
spoken | +0.005 |
rys | +0.005 |
moth | +0.005 |
slight | +0.005 |
guardian | +0.005 |
Neg logit contributions | |
sometimes | -0.007 |
Sometimes | -0.006 |
then | -0.006 |
maybe | -0.005 |
he | -0.005 |
Token | Look |
Token ID | 8567 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
ria | +0.027 |
ING | +0.027 |
ume | +0.025 |
itter | +0.025 |
slight | +0.025 |
Neg logit contributions | |
sometimes | -0.028 |
Sometimes | -0.024 |
then | -0.024 |
maybe | -0.024 |
dinosaurs | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
rob | +0.004 |
Sometimes | +0.004 |
cast | +0.004 |
sometimes | +0.004 |
narrative | +0.003 |
Neg logit contributions | |
tap | -0.004 |
pet | -0.004 |
ING | -0.004 |
groom | -0.003 |
hand | -0.003 |
Token | hammer |
Token ID | 15554 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
sometimes | +0.032 |
maybe | +0.029 |
Sometimes | +0.029 |
dinosaurs | +0.029 |
then | +0.028 |
Neg logit contributions | |
ria | -0.030 |
ING | -0.030 |
ume | -0.028 |
ater | -0.027 |
oxy | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
sometimes | +0.037 |
Sometimes | +0.033 |
maybe | +0.033 |
dinosaurs | +0.031 |
then | +0.030 |
Neg logit contributions | |
ING | -0.044 |
ria | -0.044 |
ume | -0.042 |
groom | -0.042 |
tap | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
rob | +0.005 |
Sometimes | +0.004 |
sometimes | +0.004 |
cast | +0.004 |
narrative | +0.004 |
Neg logit contributions | |
tap | -0.005 |
ING | -0.005 |
pet | -0.004 |
ume | -0.004 |
groom | -0.004 |
Token | screw |
Token ID | 9580 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
sometimes | +0.032 |
maybe | +0.029 |
dinosaurs | +0.029 |
Sometimes | +0.028 |
then | +0.028 |
Neg logit contributions | |
ria | -0.030 |
ING | -0.029 |
iya | -0.028 |
ume | -0.028 |
oxy | -0.028 |
Token | driver |
Token ID | 26230 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
sometimes | +0.042 |
Sometimes | +0.039 |
maybe | +0.038 |
dinosaurs | +0.035 |
cast | +0.034 |
Neg logit contributions | |
ING | -0.068 |
ria | -0.067 |
tap | -0.066 |
ume | -0.066 |
ater | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
sometimes | +0.096 |
Sometimes | +0.093 |
maybe | +0.091 |
dinosaurs | +0.085 |
rob | +0.083 |
Neg logit contributions | |
ING | -0.091 |
ria | -0.089 |
ume | -0.087 |
tap | -0.087 |
groom | -0.084 |
Token | a |
Token ID | 257 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
rob | +0.004 |
Sometimes | +0.004 |
sometimes | +0.004 |
cast | +0.004 |
dinosaurs | +0.004 |
Neg logit contributions | |
tap | -0.004 |
ING | -0.004 |
pet | -0.004 |
ume | -0.004 |
groom | -0.004 |
Token | box |
Token ID | 3091 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
sometimes | +0.034 |
maybe | +0.031 |
Sometimes | +0.031 |
dinosaurs | +0.030 |
then | +0.030 |
Neg logit contributions | |
ria | -0.032 |
ING | -0.031 |
iya | -0.029 |
ume | -0.029 |
oxy | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
sometimes | +0.030 |
Sometimes | +0.028 |
maybe | +0.028 |
dinosaurs | +0.026 |
rob | +0.026 |
Neg logit contributions | |
ING | -0.032 |
ria | -0.032 |
tap | -0.031 |
ume | -0.031 |
groom | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
rob | +0.006 |
sometimes | +0.006 |
Sometimes | +0.006 |
cast | +0.005 |
dinosaurs | +0.005 |
Neg logit contributions | |
tap | -0.006 |
ING | -0.006 |
pet | -0.006 |
ume | -0.006 |
groom | -0.006 |
Token | cleaned |
Token ID | 20750 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Sometimes | +0.013 |
rob | +0.013 |
dinosaurs | +0.013 |
sometimes | +0.012 |
maybe | +0.012 |
Neg logit contributions | |
ria | -0.008 |
tap | -0.007 |
pet | -0.007 |
groom | -0.007 |
ft | -0.007 |
Token | up |
Token ID | 510 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
sometimes | +0.012 |
eighty | +0.011 |
rob | +0.011 |
maybe | +0.011 |
dinosaurs | +0.011 |
Neg logit contributions | |
ria | -0.012 |
tap | -0.012 |
ING | -0.012 |
copy | -0.011 |
pet | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ria | +0.002 |
tap | +0.002 |
ING | +0.002 |
ume | +0.002 |
pet | +0.002 |
Neg logit contributions | |
sometimes | -0.002 |
Sometimes | -0.002 |
rob | -0.002 |
maybe | -0.002 |
dinosaurs | -0.002 |
Token | broken |
Token ID | 5445 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
rob | +0.048 |
sometimes | +0.048 |
maybe | +0.047 |
eighty | +0.045 |
cast | +0.044 |
Neg logit contributions | |
tap | -0.026 |
hand | -0.023 |
ING | -0.023 |
pet | -0.022 |
hose | -0.022 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
sometimes | +0.057 |
maybe | +0.053 |
Sometimes | +0.052 |
dinosaurs | +0.050 |
rob | +0.049 |
Neg logit contributions | |
ING | -0.040 |
ria | -0.040 |
tap | -0.039 |
ume | -0.037 |
ater | -0.037 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
sometimes | +0.045 |
dinosaurs | +0.043 |
maybe | +0.043 |
rob | +0.043 |
Sometimes | +0.043 |
Neg logit contributions | |
ING | -0.031 |
ria | -0.030 |
tap | -0.030 |
ower | -0.030 |
itter | -0.028 |
Token | ay |
Token ID | 323 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
sometimes | +0.139 |
dinosaurs | +0.130 |
eighty | +0.128 |
maybe | +0.125 |
then | +0.123 |
Neg logit contributions | |
itter | -0.057 |
ower | -0.051 |
op | -0.051 |
ria | -0.050 |
ING | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
eighty | +0.044 |
Sometimes | +0.044 |
sometimes | +0.043 |
dinosaurs | +0.042 |
narrative | +0.042 |
Neg logit contributions | |
ria | -0.041 |
ING | -0.039 |
itter | -0.037 |
op | -0.037 |
ower | -0.037 |
Token | Lily |
Token ID | 20037 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
rob | +0.017 |
Sometimes | +0.017 |
dinosaurs | +0.017 |
cast | +0.016 |
eighty | +0.015 |
Neg logit contributions | |
tap | -0.012 |
groom | -0.012 |
pet | -0.012 |
ria | -0.011 |
copy | -0.011 |
Token | learned |
Token ID | 4499 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
sometimes | +0.016 |
Sometimes | +0.015 |
maybe | +0.014 |
dinosaurs | +0.014 |
rob | +0.013 |
Neg logit contributions | |
ria | -0.016 |
ING | -0.016 |
tap | -0.015 |
groom | -0.015 |
ume | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
ria | +0.010 |
ING | +0.010 |
tap | +0.009 |
ume | +0.009 |
groom | +0.009 |
Neg logit contributions | |
sometimes | -0.007 |
dinosaurs | -0.006 |
maybe | -0.006 |
Sometimes | -0.006 |
rob | -0.006 |
Token | throw |
Token ID | 3714 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
sometimes | +0.005 |
rob | +0.005 |
Sometimes | +0.005 |
dinosaurs | +0.005 |
maybe | +0.005 |
Neg logit contributions | |
tap | -0.006 |
ria | -0.006 |
groom | -0.006 |
ING | -0.006 |
copy | -0.006 |
Token | away |
Token ID | 1497 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ria | +0.010 |
ING | +0.010 |
elcome | +0.009 |
groom | +0.009 |
ume | +0.009 |
Neg logit contributions | |
sometimes | -0.008 |
maybe | -0.007 |
Sometimes | -0.007 |
then | -0.007 |
dinosaurs | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
ING | +0.049 |
ria | +0.048 |
elcome | +0.047 |
ady | +0.047 |
iya | +0.046 |
Neg logit contributions | |
sometimes | -0.029 |
maybe | -0.024 |
then | -0.022 |
Sometimes | -0.022 |
dinosaurs | -0.020 |
Token | dirty |
Token ID | 11841 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
sometimes | +0.018 |
Sometimes | +0.016 |
maybe | +0.016 |
dinosaurs | +0.015 |
then | +0.015 |
Neg logit contributions | |
ria | -0.016 |
ING | -0.016 |
groom | -0.015 |
ume | -0.015 |
elcome | -0.014 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ria | +0.021 |
iya | +0.020 |
ING | +0.020 |
ume | +0.020 |
groom | +0.020 |
Neg logit contributions | |
sometimes | -0.013 |
dinosaurs | -0.011 |
Sometimes | -0.010 |
under | -0.010 |
maybe | -0.010 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
sometimes | +0.022 |
Sometimes | +0.019 |
maybe | +0.019 |
then | +0.018 |
dinosaurs | +0.018 |
Neg logit contributions | |
ria | -0.026 |
ING | -0.026 |
groom | -0.025 |
slight | -0.024 |
ume | -0.024 |
Token | ay |
Token ID | 323 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
sometimes | +0.124 |
maybe | +0.114 |
dinosaurs | +0.113 |
Sometimes | +0.109 |
then | +0.108 |
Neg logit contributions | |
ria | -0.068 |
ING | -0.067 |
itter | -0.066 |
ume | -0.065 |
ower | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
sometimes | +0.035 |
maybe | +0.031 |
Sometimes | +0.030 |
then | +0.029 |
dinosaurs | +0.029 |
Neg logit contributions | |
ING | -0.042 |
ria | -0.042 |
groom | -0.040 |
slight | -0.040 |
tap | -0.040 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
rob | +0.009 |
dinosaurs | +0.008 |
sometimes | +0.008 |
eighty | +0.007 |
cast | +0.007 |
Neg logit contributions | |
ria | -0.009 |
ING | -0.009 |
Her | -0.008 |
Care | -0.008 |
pet | -0.008 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
sometimes | +0.013 |
maybe | +0.012 |
dinosaurs | +0.012 |
cast | +0.012 |
then | +0.012 |
Neg logit contributions | |
ING | -0.007 |
Care | -0.006 |
ria | -0.006 |
pet | -0.006 |
hand | -0.006 |
Token | upon |
Token ID | 2402 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
rob | +0.082 |
bones | +0.072 |
sometimes | +0.071 |
dinosaurs | +0.071 |
eighty | +0.069 |
Neg logit contributions | |
ria | -0.039 |
hand | -0.035 |
opsy | -0.034 |
aa | -0.034 |
a | -0.033 |
Token | not |
Token ID | 407 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
sometimes | +0.001 |
then | +0.000 |
maybe | +0.000 |
now | +0.000 |
Tim | +0.000 |
Neg logit contributions | |
oing | -0.001 |
ria | -0.001 |
estone | -0.001 |
ING | -0.001 |
ume | -0.001 |
Token | played |
Token ID | 2826 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
sometimes | +0.003 |
then | +0.003 |
Tim | +0.003 |
maybe | +0.003 |
dinosaurs | +0.002 |
Neg logit contributions | |
ria | -0.005 |
ING | -0.005 |
iya | -0.005 |
Girl | -0.004 |
moth | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ria | +0.001 |
ING | +0.001 |
groom | +0.001 |
ume | +0.001 |
tap | +0.001 |
Neg logit contributions | |
sometimes | -0.001 |
Sometimes | -0.001 |
maybe | -0.001 |
dinosaurs | -0.001 |
then | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
sometimes | +0.004 |
Sometimes | +0.003 |
maybe | +0.003 |
dinosaurs | +0.003 |
then | +0.003 |
Neg logit contributions | |
ria | -0.006 |
ING | -0.006 |
ume | -0.005 |
elcome | -0.005 |
groom | -0.005 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
sometimes | +0.033 |
maybe | +0.031 |
Sometimes | +0.030 |
rob | +0.030 |
then | +0.030 |
Neg logit contributions | |
tap | -0.019 |
ING | -0.018 |
ria | -0.018 |
slight | -0.017 |
pet | -0.017 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
sometimes | +0.039 |
maybe | +0.037 |
Sometimes | +0.037 |
dinosaurs | +0.035 |
rob | +0.035 |
Neg logit contributions | |
ING | -0.032 |
ria | -0.031 |
tap | -0.031 |
ume | -0.029 |
ower | -0.029 |
Token | ay |
Token ID | 323 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
sometimes | +0.130 |
maybe | +0.121 |
dinosaurs | +0.118 |
then | +0.117 |
eighty | +0.115 |
Neg logit contributions | |
itter | -0.061 |
ING | -0.058 |
ria | -0.057 |
ower | -0.056 |
op | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
sometimes | +0.058 |
maybe | +0.054 |
Sometimes | +0.054 |
dinosaurs | +0.051 |
cast | +0.050 |
Neg logit contributions | |
ING | -0.051 |
ria | -0.051 |
ume | -0.048 |
tap | -0.047 |
elcome | -0.046 |
Token | They |
Token ID | 1119 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
ING | +0.020 |
ria | +0.020 |
ume | +0.019 |
tap | +0.019 |
groom | +0.018 |
Neg logit contributions | |
sometimes | -0.012 |
maybe | -0.011 |
Sometimes | -0.011 |
dinosaurs | -0.010 |
then | -0.010 |
Token | wished |
Token ID | 16555 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
pet | +0.001 |
groom | +0.001 |
tap | +0.001 |
ING | +0.001 |
spoken | +0.001 |
Neg logit contributions | |
Sometimes | -0.001 |
dinosaurs | -0.001 |
rob | -0.001 |
cast | -0.001 |
maybe | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
rob | +0.037 |
eighty | +0.031 |
cast | +0.029 |
camps | +0.028 |
ousel | +0.027 |
Neg logit contributions | |
tap | -0.032 |
ria | -0.030 |
rhythm | -0.028 |
human | -0.028 |
wife | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
rob | +0.015 |
Sometimes | +0.015 |
cast | +0.015 |
maybe | +0.015 |
sometimes | +0.014 |
Neg logit contributions | |
pet | -0.015 |
groom | -0.014 |
tap | -0.014 |
hand | -0.014 |
spoken | -0.014 |
Token | hammer |
Token ID | 15554 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
sometimes | +0.018 |
Sometimes | +0.016 |
maybe | +0.016 |
then | +0.016 |
rob | +0.016 |
Neg logit contributions | |
ria | -0.013 |
ING | -0.013 |
tap | -0.012 |
groom | -0.012 |
slight | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
sometimes | +0.035 |
maybe | +0.034 |
Sometimes | +0.034 |
rob | +0.031 |
dinosaurs | +0.031 |
Neg logit contributions | |
ING | -0.043 |
ria | -0.042 |
tap | -0.042 |
ume | -0.042 |
ater | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
sometimes | +0.004 |
Sometimes | +0.004 |
rob | +0.004 |
cast | +0.004 |
maybe | +0.003 |
Neg logit contributions | |
tap | -0.004 |
ING | -0.004 |
pet | -0.004 |
copy | -0.004 |
groom | -0.004 |
Token | screw |
Token ID | 9580 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
sometimes | +0.021 |
maybe | +0.019 |
Sometimes | +0.019 |
dinosaurs | +0.018 |
then | +0.018 |
Neg logit contributions | |
ING | -0.019 |
ria | -0.019 |
ume | -0.018 |
groom | -0.017 |
iya | -0.017 |
Token | driver |
Token ID | 26230 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
sometimes | +0.044 |
Sometimes | +0.044 |
maybe | +0.041 |
rob | +0.038 |
narrative | +0.038 |
Neg logit contributions | |
tap | -0.062 |
ING | -0.060 |
ume | -0.059 |
ria | -0.058 |
ater | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
Sometimes | +0.094 |
sometimes | +0.093 |
maybe | +0.092 |
cast | +0.085 |
narrative | +0.085 |
Neg logit contributions | |
ING | -0.086 |
ume | -0.084 |
tap | -0.084 |
ria | -0.084 |
ater | -0.080 |
Token | a |
Token ID | 257 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
rob | +0.008 |
cast | +0.008 |
Sometimes | +0.008 |
sometimes | +0.008 |
narrative | +0.008 |
Neg logit contributions | |
tap | -0.008 |
ING | -0.008 |
ume | -0.008 |
pet | -0.008 |
ady | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
sometimes | +0.028 |
maybe | +0.026 |
Sometimes | +0.026 |
dinosaurs | +0.024 |
then | +0.024 |
Neg logit contributions | |
ria | -0.026 |
ING | -0.026 |
ume | -0.024 |
groom | -0.024 |
iya | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Sometimes | +0.048 |
sometimes | +0.046 |
maybe | +0.045 |
rob | +0.044 |
cast | +0.042 |
Neg logit contributions | |
ING | -0.045 |
ater | -0.044 |
tap | -0.044 |
ume | -0.044 |
ady | -0.043 |
Token | some |
Token ID | 617 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
rob | +0.003 |
cast | +0.003 |
Sometimes | +0.003 |
narrative | +0.003 |
sometimes | +0.003 |
Neg logit contributions | |
tap | -0.003 |
groom | -0.003 |
ume | -0.003 |
copy | -0.003 |
ria | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
ING | +0.032 |
ria | +0.029 |
ume | +0.029 |
ady | +0.029 |
iver | +0.028 |
Neg logit contributions | |
sometimes | -0.016 |
dinosaurs | -0.013 |
Sometimes | -0.013 |
puzzles | -0.013 |
maybe | -0.013 |
Token | work |
Token ID | 670 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
sometimes | +0.011 |
then | +0.010 |
maybe | +0.010 |
Sometimes | +0.010 |
dinosaurs | +0.009 |
Neg logit contributions | |
ING | -0.011 |
ria | -0.011 |
ume | -0.011 |
iya | -0.010 |
oxy | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Sometimes | +0.033 |
sometimes | +0.032 |
rob | +0.032 |
maybe | +0.031 |
dinosaurs | +0.030 |
Neg logit contributions | |
ria | -0.017 |
tap | -0.017 |
copy | -0.017 |
rhythm | -0.015 |
ater | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ria | +0.003 |
ING | +0.003 |
groom | +0.003 |
tap | +0.003 |
ume | +0.003 |
Neg logit contributions | |
sometimes | -0.003 |
Sometimes | -0.002 |
maybe | -0.002 |
dinosaurs | -0.002 |
then | -0.002 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
sometimes | +0.012 |
maybe | +0.010 |
Sometimes | +0.010 |
dinosaurs | +0.010 |
then | +0.010 |
Neg logit contributions | |
ING | -0.011 |
ria | -0.011 |
ume | -0.010 |
groom | -0.010 |
Care | -0.010 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
sometimes | +0.035 |
Sometimes | +0.031 |
maybe | +0.031 |
dinosaurs | +0.029 |
then | +0.029 |
Neg logit contributions | |
ria | -0.040 |
ING | -0.040 |
groom | -0.038 |
ume | -0.037 |
tap | -0.037 |
Token | ay |
Token ID | 323 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
sometimes | +0.140 |
then | +0.128 |
maybe | +0.128 |
dinosaurs | +0.128 |
eighty | +0.125 |
Neg logit contributions | |
itter | -0.055 |
ria | -0.048 |
ING | -0.047 |
op | -0.045 |
ume | -0.045 |
Token | right |
Token ID | 826 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
sometimes | +0.047 |
Sometimes | +0.043 |
maybe | +0.043 |
dinosaurs | +0.041 |
then | +0.040 |
Neg logit contributions | |
ria | -0.043 |
ING | -0.042 |
ume | -0.039 |
tap | -0.039 |
elcome | -0.039 |
Token | away |
Token ID | 1497 |
Feature activation | -2.90e-03 |
Pos logit contributions | |
sometimes | +0.036 |
maybe | +0.035 |
Sometimes | +0.035 |
dinosaurs | +0.034 |
rob | +0.034 |
Neg logit contributions | |
ING | -0.015 |
ria | -0.014 |
ater | -0.013 |
copy | -0.013 |
tap | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
sometimes | +0.000 |
maybe | +0.000 |
Sometimes | +0.000 |
then | +0.000 |
dinosaurs | +0.000 |
Neg logit contributions | |
ria | -0.000 |
ING | -0.000 |
groom | -0.000 |
elcome | -0.000 |
slight | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ING | +0.012 |
ria | +0.012 |
ater | +0.012 |
moth | +0.011 |
groom | +0.011 |
Neg logit contributions | |
Sometimes | -0.007 |
sometimes | -0.007 |
maybe | -0.006 |
then | -0.006 |
dinosaurs | -0.005 |
Token | Did |
Token ID | 11633 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
sometimes | +0.026 |
Sometimes | +0.024 |
maybe | +0.024 |
dinosaurs | +0.023 |
then | +0.022 |
Neg logit contributions | |
ING | -0.020 |
ria | -0.020 |
groom | -0.019 |
tap | -0.018 |
ume | -0.018 |
Token | you |
Token ID | 345 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
rob | +0.050 |
cast | +0.046 |
Sometimes | +0.045 |
camps | +0.045 |
sometimes | +0.045 |
Neg logit contributions | |
ING | -0.029 |
ria | -0.028 |
tap | -0.027 |
elcome | -0.026 |
copy | -0.025 |
Token | destroy |
Token ID | 4117 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
ING | +0.004 |
ria | +0.004 |
tap | +0.004 |
groom | +0.004 |
ume | +0.004 |
Neg logit contributions | |
sometimes | -0.007 |
Sometimes | -0.006 |
maybe | -0.006 |
dinosaurs | -0.006 |
then | -0.006 |
Token | my |
Token ID | 616 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
sometimes | +0.016 |
Sometimes | +0.015 |
maybe | +0.015 |
dinosaurs | +0.014 |
then | +0.014 |
Neg logit contributions | |
ria | -0.018 |
ING | -0.018 |
groom | -0.017 |
ume | -0.017 |
tap | -0.017 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
sometimes | +0.048 |
rob | +0.044 |
maybe | +0.044 |
Sometimes | +0.043 |
eighty | +0.043 |
Neg logit contributions | |
tap | -0.027 |
ING | -0.027 |
pet | -0.026 |
ria | -0.026 |
hand | -0.025 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
sometimes | +0.035 |
maybe | +0.033 |
Sometimes | +0.032 |
dinosaurs | +0.031 |
then | +0.030 |
Neg logit contributions | |
ING | -0.032 |
ria | -0.032 |
tap | -0.030 |
ume | -0.029 |
elcome | -0.029 |
Token | ay |
Token ID | 323 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
sometimes | +0.132 |
maybe | +0.122 |
dinosaurs | +0.120 |
then | +0.117 |
eighty | +0.116 |
Neg logit contributions | |
itter | -0.061 |
ING | -0.057 |
ria | -0.054 |
ower | -0.054 |
ume | -0.052 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
sometimes | +0.056 |
maybe | +0.054 |
Sometimes | +0.053 |
dinosaurs | +0.051 |
cast | +0.049 |
Neg logit contributions | |
ING | -0.062 |
ria | -0.061 |
elcome | -0.057 |
ume | -0.057 |
itter | -0.057 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
sometimes | +0.006 |
dinosaurs | +0.005 |
rob | +0.005 |
Sometimes | +0.005 |
cast | +0.005 |
Neg logit contributions | |
ria | -0.011 |
ING | -0.011 |
tap | -0.010 |
elcome | -0.010 |
Her | -0.010 |
Token | felt |
Token ID | 2936 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
ume | +0.000 |
ING | +0.000 |
groom | +0.000 |
rys | +0.000 |
ria | +0.000 |
Neg logit contributions | |
sometimes | -0.000 |
then | -0.000 |
maybe | -0.000 |
Sometimes | -0.000 |
Tim | -0.000 |
Token | bad |
Token ID | 2089 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
tap | +0.009 |
ING | +0.009 |
slight | +0.009 |
pet | +0.009 |
Care | +0.009 |
Neg logit contributions | |
sometimes | -0.011 |
rob | -0.011 |
dinosaurs | -0.011 |
cast | -0.011 |
Sometimes | -0.011 |
Token | throw |
Token ID | 3714 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ria | +0.010 |
ING | +0.010 |
ume | +0.009 |
oing | +0.009 |
groom | +0.009 |
Neg logit contributions | |
sometimes | -0.015 |
maybe | -0.014 |
Sometimes | -0.014 |
then | -0.013 |
dinosaurs | -0.013 |
Token | away |
Token ID | 1497 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ING | +0.005 |
ria | +0.005 |
tap | +0.005 |
ume | +0.004 |
slight | +0.004 |
Neg logit contributions | |
sometimes | -0.005 |
Sometimes | -0.004 |
maybe | -0.004 |
dinosaurs | -0.004 |
rob | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ria | +0.047 |
ING | +0.047 |
groom | +0.046 |
iya | +0.044 |
oxy | +0.044 |
Neg logit contributions | |
sometimes | -0.025 |
maybe | -0.021 |
then | -0.020 |
Sometimes | -0.020 |
dinosaurs | -0.017 |
Token | broken |
Token ID | 5445 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
sometimes | +0.032 |
Sometimes | +0.030 |
maybe | +0.030 |
rob | +0.029 |
cast | +0.028 |
Neg logit contributions | |
tap | -0.018 |
ING | -0.018 |
ria | -0.018 |
slight | -0.017 |
pet | -0.017 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
sometimes | +0.030 |
Sometimes | +0.027 |
maybe | +0.027 |
dinosaurs | +0.026 |
then | +0.026 |
Neg logit contributions | |
ria | -0.028 |
ING | -0.028 |
groom | -0.026 |
ume | -0.026 |
iya | -0.026 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
sometimes | +0.032 |
Sometimes | +0.030 |
maybe | +0.030 |
dinosaurs | +0.029 |
rob | +0.028 |
Neg logit contributions | |
ING | -0.029 |
ria | -0.029 |
tap | -0.027 |
ume | -0.027 |
ower | -0.026 |
Token | ay |
Token ID | 323 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
sometimes | +0.131 |
dinosaurs | +0.121 |
maybe | +0.119 |
eighty | +0.116 |
rob | +0.114 |
Neg logit contributions | |
itter | -0.061 |
ria | -0.057 |
ING | -0.056 |
ower | -0.055 |
op | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
sometimes | +0.039 |
Sometimes | +0.037 |
maybe | +0.036 |
dinosaurs | +0.035 |
cast | +0.033 |
Neg logit contributions | |
ria | -0.044 |
ING | -0.043 |
ume | -0.041 |
elcome | -0.040 |
tap | -0.040 |
Token | soon |
Token ID | 2582 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
sometimes | +0.005 |
Sometimes | +0.005 |
maybe | +0.004 |
dinosaurs | +0.004 |
rob | +0.004 |
Neg logit contributions | |
ria | -0.008 |
ING | -0.008 |
tap | -0.008 |
groom | -0.008 |
ume | -0.007 |
Token | forgotten |
Token ID | 11564 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
sometimes | +0.005 |
maybe | +0.004 |
Sometimes | +0.004 |
dinosaurs | +0.004 |
then | +0.004 |
Neg logit contributions | |
ING | -0.009 |
ria | -0.009 |
groom | -0.009 |
ume | -0.009 |
tap | -0.009 |
Token | about |
Token ID | 546 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
ING | +0.012 |
ria | +0.012 |
groom | +0.012 |
oxy | +0.011 |
ater | +0.011 |
Neg logit contributions | |
sometimes | -0.008 |
maybe | -0.007 |
Sometimes | -0.006 |
then | -0.006 |
dinosaurs | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
sometimes | +0.001 |
then | +0.001 |
maybe | +0.001 |
dinosaurs | +0.001 |
Sometimes | +0.001 |
Neg logit contributions | |
ria | -0.001 |
ING | -0.001 |
groom | -0.001 |
iya | -0.001 |
slight | -0.001 |
Token | accidentally |
Token ID | 14716 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
sometimes | +0.037 |
maybe | +0.034 |
Sometimes | +0.033 |
then | +0.032 |
dinosaurs | +0.032 |
Neg logit contributions | |
ING | -0.041 |
ria | -0.041 |
ume | -0.038 |
ater | -0.037 |
groom | -0.037 |
Token | dropped |
Token ID | 5710 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
sometimes | +0.011 |
then | +0.011 |
under | +0.010 |
Tim | +0.010 |
maybe | +0.010 |
Neg logit contributions | |
ria | -0.022 |
Girl | -0.022 |
estone | -0.021 |
ING | -0.021 |
iya | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
sometimes | +0.005 |
Sometimes | +0.004 |
maybe | +0.004 |
dinosaurs | +0.004 |
then | +0.004 |
Neg logit contributions | |
ria | -0.010 |
ING | -0.010 |
groom | -0.009 |
ume | -0.009 |
iya | -0.009 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
sometimes | +0.018 |
then | +0.018 |
under | +0.017 |
for | +0.017 |
maybe | +0.017 |
Neg logit contributions | |
ria | -0.013 |
Care | -0.012 |
ING | -0.012 |
Girl | -0.012 |
elcome | -0.012 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
sometimes | +0.020 |
then | +0.017 |
under | +0.016 |
Sometimes | +0.016 |
maybe | +0.016 |
Neg logit contributions | |
ria | -0.035 |
iya | -0.033 |
groom | -0.033 |
ING | -0.033 |
elcome | -0.032 |
Token | ay |
Token ID | 323 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
sometimes | +0.119 |
maybe | +0.110 |
dinosaurs | +0.107 |
Sometimes | +0.106 |
then | +0.104 |
Neg logit contributions | |
ING | -0.071 |
ria | -0.068 |
ume | -0.067 |
itter | -0.064 |
ower | -0.062 |
Token | on |
Token ID | 319 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
sometimes | +0.052 |
Sometimes | +0.047 |
maybe | +0.047 |
dinosaurs | +0.044 |
then | +0.044 |
Neg logit contributions | |
ria | -0.052 |
ING | -0.052 |
groom | -0.049 |
ume | -0.049 |
tap | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
sometimes | +0.023 |
Sometimes | +0.021 |
maybe | +0.021 |
dinosaurs | +0.019 |
then | +0.019 |
Neg logit contributions | |
ING | -0.037 |
ria | -0.037 |
groom | -0.035 |
ume | -0.035 |
tap | -0.034 |
Token | ground |
Token ID | 2323 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
sometimes | +0.019 |
dinosaurs | +0.017 |
then | +0.017 |
Sometimes | +0.016 |
maybe | +0.016 |
Neg logit contributions | |
ria | -0.025 |
ING | -0.023 |
elcome | -0.023 |
ume | -0.023 |
oing | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
sometimes | +0.013 |
Sometimes | +0.011 |
then | +0.011 |
maybe | +0.010 |
under | +0.010 |
Neg logit contributions | |
ria | -0.018 |
groom | -0.017 |
ING | -0.017 |
iya | -0.017 |
elcome | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ria | +0.012 |
ING | +0.012 |
groom | +0.011 |
ume | +0.011 |
tap | +0.011 |
Neg logit contributions | |
sometimes | -0.008 |
Sometimes | -0.007 |
maybe | -0.007 |
dinosaurs | -0.006 |
then | -0.006 |
Token | hammer |
Token ID | 15554 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
maybe | +0.031 |
sometimes | +0.030 |
Sometimes | +0.029 |
everywhere | +0.029 |
puzzles | +0.028 |
Neg logit contributions | |
ING | -0.042 |
ani | -0.041 |
oxy | -0.040 |
iya | -0.040 |
ume | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
sometimes | +0.039 |
Sometimes | +0.035 |
maybe | +0.035 |
dinosaurs | +0.033 |
then | +0.033 |
Neg logit contributions | |
ria | -0.042 |
ING | -0.042 |
groom | -0.039 |
ume | -0.039 |
tap | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
sometimes | +0.009 |
Sometimes | +0.008 |
maybe | +0.008 |
rob | +0.007 |
dinosaurs | +0.007 |
Neg logit contributions | |
ria | -0.009 |
tap | -0.009 |
ING | -0.009 |
groom | -0.009 |
elcome | -0.009 |
Token | screw |
Token ID | 9580 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
maybe | +0.027 |
sometimes | +0.027 |
then | +0.026 |
Sometimes | +0.025 |
puzzles | +0.025 |
Neg logit contributions | |
ING | -0.034 |
iya | -0.033 |
ria | -0.033 |
ani | -0.032 |
oxy | -0.032 |
Token | driver |
Token ID | 26230 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
sometimes | +0.039 |
Sometimes | +0.035 |
maybe | +0.033 |
dinosaurs | +0.032 |
rob | +0.030 |
Neg logit contributions | |
ria | -0.077 |
ING | -0.077 |
tap | -0.075 |
ume | -0.075 |
groom | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
sometimes | +0.098 |
Sometimes | +0.092 |
maybe | +0.091 |
dinosaurs | +0.087 |
rob | +0.084 |
Neg logit contributions | |
ria | -0.086 |
ING | -0.086 |
ume | -0.081 |
tap | -0.081 |
groom | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
ING | +0.013 |
groom | +0.013 |
ria | +0.013 |
ater | +0.013 |
ume | +0.012 |
Neg logit contributions | |
sometimes | -0.009 |
Sometimes | -0.009 |
maybe | -0.009 |
then | -0.008 |
dinosaurs | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
ING | +0.022 |
groom | +0.022 |
ria | +0.022 |
slight | +0.021 |
ume | +0.021 |
Neg logit contributions | |
sometimes | -0.012 |
Sometimes | -0.011 |
maybe | -0.010 |
then | -0.009 |
besides | -0.008 |
Token | M |
Token ID | 44 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
groom | +0.009 |
ING | +0.009 |
ram | +0.009 |
guardian | +0.009 |
spoken | +0.009 |
Neg logit contributions | |
sometimes | -0.013 |
then | -0.011 |
Sometimes | -0.011 |
maybe | -0.011 |
besides | -0.010 |
Token | olly |
Token ID | 5098 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ING | +0.003 |
groom | +0.003 |
ria | +0.003 |
tap | +0.003 |
slight | +0.003 |
Neg logit contributions | |
sometimes | -0.003 |
Sometimes | -0.003 |
maybe | -0.003 |
then | -0.003 |
dinosaurs | -0.002 |
Token | I |
Token ID | 314 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
sometimes | +0.034 |
maybe | +0.030 |
Sometimes | +0.029 |
then | +0.028 |
dinosaurs | +0.026 |
Neg logit contributions | |
ING | -0.043 |
ria | -0.043 |
ater | -0.042 |
ady | -0.042 |
ume | -0.041 |
Token | keep |
Token ID | 1394 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
Care | +0.018 |
ING | +0.017 |
oxy | +0.017 |
oing | +0.017 |
iya | +0.017 |
Neg logit contributions | |
sometimes | -0.019 |
then | -0.017 |
maybe | -0.015 |
now | -0.015 |
Sometimes | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
ING | +0.010 |
ria | +0.010 |
ume | +0.009 |
slight | +0.009 |
estone | +0.009 |
Neg logit contributions | |
sometimes | -0.007 |
maybe | -0.006 |
Sometimes | -0.006 |
dinosaurs | -0.006 |
then | -0.006 |
Token | talking |
Token ID | 3375 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
sometimes | +0.013 |
Sometimes | +0.012 |
maybe | +0.012 |
dinosaurs | +0.011 |
then | +0.011 |
Neg logit contributions | |
ria | -0.015 |
ING | -0.015 |
groom | -0.014 |
ume | -0.014 |
iya | -0.014 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
iya | +0.012 |
ria | +0.012 |
ING | +0.012 |
groom | +0.011 |
opsy | +0.011 |
Neg logit contributions | |
sometimes | -0.011 |
maybe | -0.010 |
Sometimes | -0.009 |
then | -0.009 |
dinosaurs | -0.009 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
sometimes | +0.027 |
Sometimes | +0.024 |
maybe | +0.024 |
dinosaurs | +0.023 |
then | +0.023 |
Neg logit contributions | |
ria | -0.030 |
ING | -0.030 |
groom | -0.028 |
ume | -0.028 |
tap | -0.028 |
Token | ay |
Token ID | 323 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
sometimes | +0.124 |
dinosaurs | +0.114 |
maybe | +0.112 |
Sometimes | +0.110 |
then | +0.109 |
Neg logit contributions | |
itter | -0.063 |
ria | -0.062 |
ING | -0.061 |
ume | -0.059 |
ower | -0.057 |
Token | ? |
Token ID | 30 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
sometimes | +0.046 |
Sometimes | +0.043 |
maybe | +0.042 |
dinosaurs | +0.040 |
then | +0.038 |
Neg logit contributions | |
ria | -0.057 |
ING | -0.057 |
ume | -0.053 |
groom | -0.053 |
elcome | -0.053 |
Token | â |
Token ID | 22940 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
sometimes | +0.014 |
Sometimes | +0.013 |
maybe | +0.013 |
then | +0.012 |
dinosaurs | +0.011 |
Neg logit contributions | |
ING | -0.023 |
ria | -0.023 |
groom | -0.022 |
ater | -0.022 |
ram | -0.022 |
Token | € |
Token ID | 26391 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
groom | +0.006 |
ING | +0.006 |
ria | +0.006 |
ume | +0.005 |
slight | +0.005 |
Neg logit contributions | |
sometimes | -0.007 |
Sometimes | -0.006 |
maybe | -0.006 |
then | -0.006 |
rob | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
ING | +0.016 |
ria | +0.016 |
groom | +0.015 |
ume | +0.015 |
copy | +0.015 |
Neg logit contributions | |
sometimes | -0.013 |
maybe | -0.012 |
Sometimes | -0.011 |
then | -0.011 |
dinosaurs | -0.010 |
Token | happy |
Token ID | 3772 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
ria | +0.001 |
ING | +0.001 |
groom | +0.001 |
tap | +0.001 |
slight | +0.001 |
Neg logit contributions | |
sometimes | -0.001 |
Sometimes | -0.001 |
maybe | -0.001 |
dinosaurs | -0.001 |
rob | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ria | +0.022 |
ING | +0.022 |
groom | +0.021 |
ume | +0.021 |
tap | +0.021 |
Neg logit contributions | |
sometimes | -0.018 |
Sometimes | -0.017 |
maybe | -0.016 |
dinosaurs | -0.016 |
then | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ria | +0.008 |
tap | +0.007 |
ING | +0.007 |
groom | +0.007 |
slight | +0.007 |
Neg logit contributions | |
sometimes | -0.010 |
Sometimes | -0.009 |
rob | -0.009 |
dinosaurs | -0.009 |
maybe | -0.009 |
Token | warm |
Token ID | 5814 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
sometimes | +0.011 |
Sometimes | +0.010 |
maybe | +0.010 |
dinosaurs | +0.010 |
then | +0.010 |
Neg logit contributions | |
ING | -0.009 |
ria | -0.009 |
groom | -0.008 |
ume | -0.008 |
tap | -0.008 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ING | +0.001 |
ria | +0.001 |
groom | +0.001 |
ume | +0.001 |
ater | +0.001 |
Neg logit contributions | |
sometimes | -0.002 |
Sometimes | -0.001 |
maybe | -0.001 |
then | -0.001 |
dinosaurs | -0.001 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
sometimes | +0.029 |
Sometimes | +0.025 |
maybe | +0.025 |
then | +0.024 |
dinosaurs | +0.023 |
Neg logit contributions | |
ING | -0.037 |
ria | -0.036 |
groom | -0.035 |
ume | -0.034 |
iya | -0.034 |
Token | ay |
Token ID | 323 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
sometimes | +0.129 |
dinosaurs | +0.121 |
maybe | +0.118 |
Sometimes | +0.115 |
then | +0.112 |
Neg logit contributions | |
itter | -0.059 |
ria | -0.057 |
ower | -0.055 |
ING | -0.054 |
op | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
sometimes | +0.037 |
maybe | +0.032 |
Sometimes | +0.032 |
then | +0.031 |
dinosaurs | +0.031 |
Neg logit contributions | |
ING | -0.038 |
ria | -0.038 |
groom | -0.036 |
ume | -0.036 |
tap | -0.036 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ria | +0.007 |
ING | +0.007 |
groom | +0.006 |
ume | +0.006 |
tap | +0.006 |
Neg logit contributions | |
sometimes | -0.005 |
Sometimes | -0.004 |
maybe | -0.004 |
dinosaurs | -0.004 |
then | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
sometimes | +0.009 |
maybe | +0.008 |
Sometimes | +0.008 |
dinosaurs | +0.008 |
then | +0.008 |
Neg logit contributions | |
ING | -0.007 |
ria | -0.007 |
Care | -0.007 |
tap | -0.007 |
ady | -0.006 |
Token | upon |
Token ID | 2402 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
rob | +0.062 |
sometimes | +0.058 |
dinosaurs | +0.056 |
bones | +0.055 |
eighty | +0.055 |
Neg logit contributions | |
ria | -0.041 |
hand | -0.036 |
opsy | -0.035 |
aa | -0.035 |
op | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ING | +0.010 |
ria | +0.010 |
groom | +0.009 |
ume | +0.009 |
slight | +0.009 |
Neg logit contributions | |
sometimes | -0.005 |
maybe | -0.004 |
Sometimes | -0.004 |
dinosaurs | -0.004 |
then | -0.004 |
Token | heating |
Token ID | 16930 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
ria | +0.006 |
ING | +0.006 |
tap | +0.005 |
groom | +0.005 |
ume | +0.005 |
Neg logit contributions | |
sometimes | -0.004 |
Sometimes | -0.003 |
maybe | -0.003 |
dinosaurs | -0.003 |
then | -0.003 |
Token | up |
Token ID | 510 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
ING | +0.026 |
ria | +0.026 |
groom | +0.024 |
ume | +0.024 |
slight | +0.024 |
Neg logit contributions | |
sometimes | -0.016 |
Sometimes | -0.014 |
maybe | -0.014 |
then | -0.013 |
dinosaurs | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
ING | +0.007 |
ria | +0.007 |
groom | +0.007 |
ume | +0.007 |
slight | +0.006 |
Neg logit contributions | |
sometimes | -0.005 |
maybe | -0.004 |
Sometimes | -0.004 |
then | -0.004 |
dinosaurs | -0.004 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
sometimes | +0.017 |
maybe | +0.015 |
Sometimes | +0.015 |
rob | +0.015 |
dinosaurs | +0.015 |
Neg logit contributions | |
ING | -0.012 |
ria | -0.012 |
tap | -0.012 |
slight | -0.011 |
groom | -0.011 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
sometimes | +0.023 |
Sometimes | +0.020 |
maybe | +0.020 |
then | +0.019 |
dinosaurs | +0.019 |
Neg logit contributions | |
ria | -0.028 |
ING | -0.027 |
groom | -0.026 |
ume | -0.026 |
slight | -0.026 |
Token | ay |
Token ID | 323 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
sometimes | +0.128 |
dinosaurs | +0.119 |
maybe | +0.117 |
eighty | +0.115 |
then | +0.114 |
Neg logit contributions | |
itter | -0.058 |
ria | -0.054 |
ING | -0.054 |
ume | -0.053 |
op | -0.052 |
Token | would |
Token ID | 561 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
sometimes | +0.035 |
Sometimes | +0.032 |
maybe | +0.032 |
dinosaurs | +0.030 |
then | +0.029 |
Neg logit contributions | |
ria | -0.043 |
ING | -0.043 |
ume | -0.041 |
groom | -0.040 |
tap | -0.040 |
Token | make |
Token ID | 787 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
sometimes | +0.046 |
maybe | +0.041 |
Sometimes | +0.041 |
then | +0.040 |
dinosaurs | +0.039 |
Neg logit contributions | |
ria | -0.027 |
ING | -0.027 |
ume | -0.024 |
groom | -0.024 |
elcome | -0.024 |
Token | things |
Token ID | 1243 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ING | +0.027 |
ria | +0.027 |
ater | +0.026 |
groom | +0.026 |
oing | +0.025 |
Neg logit contributions | |
sometimes | -0.017 |
maybe | -0.015 |
Sometimes | -0.014 |
then | -0.014 |
dinosaurs | -0.013 |
Token | really |
Token ID | 1107 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ria | +0.025 |
ING | +0.025 |
iya | +0.023 |
oxy | +0.023 |
ady | +0.023 |
Neg logit contributions | |
sometimes | -0.025 |
maybe | -0.023 |
then | -0.021 |
Sometimes | -0.020 |
cast | -0.019 |
Token | not |
Token ID | 407 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ria | +0.001 |
ING | +0.001 |
oing | +0.001 |
slight | +0.001 |
ume | +0.001 |
Neg logit contributions | |
sometimes | -0.000 |
maybe | -0.000 |
Sometimes | -0.000 |
then | -0.000 |
dinosaurs | -0.000 |
Token | play |
Token ID | 711 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
ria | +0.015 |
iya | +0.015 |
groom | +0.014 |
ady | +0.014 |
elcome | +0.014 |
Neg logit contributions | |
sometimes | -0.016 |
Tim | -0.013 |
then | -0.012 |
Sometimes | -0.012 |
now | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
sometimes | +0.002 |
Sometimes | +0.001 |
maybe | +0.001 |
dinosaurs | +0.001 |
then | +0.001 |
Neg logit contributions | |
ING | -0.002 |
ria | -0.002 |
tap | -0.002 |
ume | -0.002 |
groom | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
sometimes | +0.008 |
Sometimes | +0.007 |
maybe | +0.007 |
dinosaurs | +0.007 |
then | +0.007 |
Neg logit contributions | |
ria | -0.011 |
ING | -0.010 |
oing | -0.010 |
estone | -0.010 |
slight | -0.010 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
sometimes | +0.009 |
Sometimes | +0.008 |
maybe | +0.008 |
dinosaurs | +0.007 |
then | +0.007 |
Neg logit contributions | |
ria | -0.007 |
ING | -0.007 |
groom | -0.007 |
ume | -0.007 |
tap | -0.007 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
sometimes | +0.032 |
maybe | +0.031 |
Sometimes | +0.030 |
rob | +0.028 |
dinosaurs | +0.028 |
Neg logit contributions | |
ING | -0.026 |
tap | -0.024 |
ria | -0.023 |
ower | -0.023 |
ater | -0.023 |
Token | ay |
Token ID | 323 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
sometimes | +0.129 |
maybe | +0.121 |
dinosaurs | +0.116 |
eighty | +0.116 |
then | +0.115 |
Neg logit contributions | |
itter | -0.057 |
ING | -0.056 |
ower | -0.052 |
op | -0.052 |
ria | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
sometimes | +0.073 |
maybe | +0.072 |
Sometimes | +0.071 |
eighty | +0.067 |
narrative | +0.066 |
Neg logit contributions | |
ING | -0.050 |
ria | -0.046 |
itter | -0.043 |
ower | -0.043 |
elcome | -0.043 |
Token | It |
Token ID | 632 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
ria | +0.020 |
ING | +0.020 |
groom | +0.019 |
slight | +0.019 |
copy | +0.018 |
Neg logit contributions | |
sometimes | -0.013 |
Sometimes | -0.012 |
maybe | -0.012 |
then | -0.011 |
dinosaurs | -0.010 |
Token | is |
Token ID | 318 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
sometimes | +0.002 |
Sometimes | +0.001 |
maybe | +0.001 |
dinosaurs | +0.001 |
then | +0.001 |
Neg logit contributions | |
ING | -0.002 |
ria | -0.002 |
tap | -0.002 |
ume | -0.002 |
groom | -0.002 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
sometimes | +0.016 |
Sometimes | +0.015 |
maybe | +0.014 |
dinosaurs | +0.014 |
then | +0.013 |
Neg logit contributions | |
ING | -0.021 |
ria | -0.021 |
groom | -0.020 |
ume | -0.020 |
tap | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
rob | +0.006 |
narrative | +0.005 |
sometimes | +0.005 |
cast | +0.005 |
bones | +0.004 |
Neg logit contributions | |
tap | -0.006 |
ria | -0.006 |
elcome | -0.006 |
ume | -0.006 |
groom | -0.006 |
Token | throw |
Token ID | 3714 |
Feature activation | +8.33e-03 |
Pos logit contributions | |
sometimes | +0.003 |
then | +0.003 |
Tim | +0.003 |
maybe | +0.003 |
now | +0.002 |
Neg logit contributions | |
oing | -0.005 |
ossom | -0.004 |
estone | -0.004 |
ady | -0.004 |
ria | -0.004 |
Token | away |
Token ID | 1497 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ria | +0.000 |
ING | +0.000 |
groom | +0.000 |
ume | +0.000 |
elcome | +0.000 |
Neg logit contributions | |
sometimes | -0.000 |
Sometimes | -0.000 |
maybe | -0.000 |
then | -0.000 |
dinosaurs | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
ING | +0.045 |
ady | +0.044 |
oing | +0.044 |
iya | +0.043 |
elcome | +0.043 |
Neg logit contributions | |
sometimes | -0.017 |
then | -0.013 |
maybe | -0.012 |
Tim | -0.011 |
under | -0.011 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
sometimes | +0.014 |
maybe | +0.012 |
Sometimes | +0.012 |
dinosaurs | +0.012 |
under | +0.012 |
Neg logit contributions | |
ria | -0.015 |
ING | -0.014 |
iya | -0.014 |
groom | -0.014 |
ume | -0.013 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
sometimes | +0.027 |
Sometimes | +0.024 |
maybe | +0.024 |
dinosaurs | +0.023 |
then | +0.023 |
Neg logit contributions | |
ria | -0.032 |
ING | -0.032 |
groom | -0.030 |
ume | -0.030 |
slight | -0.030 |
Token | ay |
Token ID | 323 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
sometimes | +0.121 |
maybe | +0.111 |
dinosaurs | +0.111 |
then | +0.107 |
Sometimes | +0.106 |
Neg logit contributions | |
itter | -0.062 |
ria | -0.061 |
ING | -0.060 |
ume | -0.060 |
op | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
sometimes | +0.044 |
Sometimes | +0.042 |
maybe | +0.040 |
dinosaurs | +0.040 |
cast | +0.039 |
Neg logit contributions | |
ria | -0.046 |
ING | -0.045 |
ume | -0.044 |
tap | -0.043 |
elcome | -0.041 |
Token | stop |
Token ID | 2245 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
sometimes | +0.007 |
maybe | +0.007 |
Sometimes | +0.007 |
then | +0.006 |
dinosaurs | +0.006 |
Neg logit contributions | |
ING | -0.008 |
ria | -0.008 |
ume | -0.008 |
ady | -0.007 |
ater | -0.007 |
Token | smoking |
Token ID | 9216 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
ING | +0.016 |
ria | +0.016 |
ume | +0.015 |
ady | +0.015 |
slight | +0.015 |
Neg logit contributions | |
sometimes | -0.013 |
maybe | -0.011 |
then | -0.011 |
Sometimes | -0.011 |
dinosaurs | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
ria | +0.001 |
ING | +0.001 |
groom | +0.001 |
ume | +0.001 |
slight | +0.001 |
Neg logit contributions | |
sometimes | -0.001 |
Sometimes | -0.001 |
maybe | -0.001 |
then | -0.001 |
dinosaurs | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ria | +0.012 |
ING | +0.012 |
ume | +0.012 |
ady | +0.011 |
elcome | +0.011 |
Neg logit contributions | |
sometimes | -0.009 |
maybe | -0.008 |
Sometimes | -0.008 |
then | -0.008 |
dinosaurs | -0.007 |
Token | hole |
Token ID | 7604 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ria | +0.035 |
ING | +0.033 |
ume | +0.032 |
elcome | +0.031 |
oing | +0.031 |
Neg logit contributions | |
sometimes | -0.048 |
maybe | -0.044 |
Sometimes | -0.043 |
then | -0.043 |
dinosaurs | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ING | +0.004 |
ria | +0.004 |
tap | +0.004 |
ater | +0.004 |
ume | +0.004 |
Neg logit contributions | |
rob | -0.004 |
sometimes | -0.004 |
Sometimes | -0.004 |
maybe | -0.003 |
dinosaurs | -0.003 |
Token | hears |
Token ID | 23180 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
tap | +0.004 |
ING | +0.004 |
ria | +0.004 |
groom | +0.004 |
copy | +0.004 |
Neg logit contributions | |
sometimes | -0.004 |
Sometimes | -0.004 |
rob | -0.004 |
dinosaurs | -0.004 |
maybe | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
ING | +0.041 |
ria | +0.041 |
tap | +0.040 |
ume | +0.039 |
groom | +0.039 |
Neg logit contributions | |
sometimes | -0.031 |
rob | -0.028 |
Sometimes | -0.027 |
maybe | -0.026 |
dinosaurs | -0.026 |
Token | soft |
Token ID | 2705 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ady | +0.016 |
ume | +0.016 |
ria | +0.015 |
ING | +0.015 |
iya | +0.015 |
Neg logit contributions | |
sometimes | -0.018 |
maybe | -0.017 |
Sometimes | -0.016 |
dinosaurs | -0.016 |
then | -0.016 |
Token | sound |
Token ID | 2128 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ume | +0.063 |
ady | +0.060 |
ING | +0.057 |
groom | +0.056 |
ria | +0.056 |
Neg logit contributions | |
sometimes | -0.067 |
then | -0.060 |
for | -0.058 |
Sometimes | -0.058 |
maybe | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ria | +0.044 |
ING | +0.042 |
iya | +0.042 |
groom | +0.041 |
opsy | +0.041 |
Neg logit contributions | |
sometimes | -0.029 |
maybe | -0.024 |
then | -0.023 |
under | -0.022 |
for | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
ater | +0.006 |
ING | +0.006 |
ria | +0.006 |
ady | +0.006 |
groom | +0.006 |
Neg logit contributions | |
Sometimes | -0.004 |
sometimes | -0.003 |
maybe | -0.003 |
then | -0.003 |
Tim | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
ING | +0.020 |
ria | +0.020 |
tap | +0.019 |
Care | +0.019 |
elcome | +0.019 |
Neg logit contributions | |
sometimes | -0.020 |
dinosaurs | -0.018 |
maybe | -0.017 |
Sometimes | -0.017 |
rob | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
groom | +0.007 |
iya | +0.007 |
burn | +0.007 |
contract | +0.006 |
spoken | +0.006 |
Neg logit contributions | |
sometimes | -0.009 |
then | -0.008 |
maybe | -0.007 |
Sometimes | -0.007 |
besides | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ING | +0.010 |
ria | +0.009 |
groom | +0.009 |
ume | +0.009 |
slight | +0.009 |
Neg logit contributions | |
sometimes | -0.006 |
Sometimes | -0.005 |
maybe | -0.005 |
then | -0.005 |
dinosaurs | -0.005 |
Token | " |
Token ID | 1 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
sometimes | +0.000 |
Sometimes | +0.000 |
then | +0.000 |
maybe | +0.000 |
From | +0.000 |
Neg logit contributions | |
groom | -0.000 |
ING | -0.000 |
scent | -0.000 |
ower | -0.000 |
burn | -0.000 |
Token | Listen |
Token ID | 23061 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
ING | +0.008 |
ria | +0.008 |
ower | +0.008 |
itter | +0.008 |
ume | +0.008 |
Neg logit contributions | |
sometimes | -0.007 |
then | -0.006 |
maybe | -0.006 |
Sometimes | -0.006 |
rob | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +9.12e-02 |
Pos logit contributions | |
sometimes | +0.011 |
Sometimes | +0.010 |
maybe | +0.010 |
then | +0.009 |
dinosaurs | +0.009 |
Neg logit contributions | |
ria | -0.015 |
ING | -0.015 |
groom | -0.014 |
ume | -0.014 |
tap | -0.014 |
Token | little |
Token ID | 1310 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
ria | +0.002 |
ING | +0.002 |
ady | +0.002 |
ume | +0.002 |
estone | +0.002 |
Neg logit contributions | |
sometimes | -0.002 |
maybe | -0.002 |
Sometimes | -0.002 |
then | -0.002 |
dinosaurs | -0.002 |
Token | chicken |
Token ID | 9015 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
sometimes | +0.007 |
Sometimes | +0.006 |
then | +0.006 |
maybe | +0.006 |
dinosaurs | +0.006 |
Neg logit contributions | |
ria | -0.004 |
ING | -0.004 |
ume | -0.004 |
ady | -0.004 |
elcome | -0.004 |
Token | ," |
Token ID | 553 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
ria | +0.088 |
ING | +0.087 |
Care | +0.084 |
groom | +0.084 |
ume | +0.082 |
Neg logit contributions | |
sometimes | -0.057 |
maybe | -0.048 |
then | -0.046 |
Sometimes | -0.045 |
dinosaurs | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ria | +0.001 |
ING | +0.001 |
groom | +0.001 |
tap | +0.001 |
ume | +0.001 |
Neg logit contributions | |
sometimes | -0.000 |
Sometimes | -0.000 |
maybe | -0.000 |
dinosaurs | -0.000 |
cast | -0.000 |
Token | owl |
Token ID | 39610 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ria | +0.002 |
ING | +0.002 |
ume | +0.002 |
estone | +0.002 |
elcome | +0.002 |
Neg logit contributions | |
sometimes | -0.004 |
then | -0.004 |
maybe | -0.004 |
dinosaurs | -0.004 |
Sometimes | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
sometimes | +0.004 |
then | +0.003 |
maybe | +0.003 |
Sometimes | +0.003 |
dinosaurs | +0.003 |
Neg logit contributions | |
ING | -0.007 |
ria | -0.006 |
ume | -0.006 |
groom | -0.006 |
slight | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
ING | +0.008 |
ria | +0.008 |
groom | +0.008 |
ady | +0.008 |
ume | +0.008 |
Neg logit contributions | |
sometimes | -0.006 |
maybe | -0.005 |
then | -0.005 |
Sometimes | -0.005 |
under | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
sometimes | +0.000 |
Sometimes | +0.000 |
maybe | +0.000 |
dinosaurs | +0.000 |
rob | +0.000 |
Neg logit contributions | |
ria | -0.000 |
ING | -0.000 |
tap | -0.000 |
ume | -0.000 |
groom | -0.000 |
Token | looked |
Token ID | 3114 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
sometimes | +0.004 |
Sometimes | +0.004 |
maybe | +0.003 |
dinosaurs | +0.003 |
rob | +0.003 |
Neg logit contributions | |
ria | -0.004 |
ING | -0.004 |
groom | -0.004 |
tap | -0.004 |
pet | -0.004 |
Token | out |
Token ID | 503 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
sometimes | +0.014 |
Sometimes | +0.013 |
rob | +0.013 |
maybe | +0.012 |
dinosaurs | +0.012 |
Neg logit contributions | |
ria | -0.015 |
ING | -0.015 |
tap | -0.014 |
groom | -0.014 |
slight | -0.014 |
Token | at |
Token ID | 379 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
ria | +0.050 |
ING | +0.050 |
groom | +0.048 |
ume | +0.048 |
tap | +0.047 |
Neg logit contributions | |
sometimes | -0.034 |
Sometimes | -0.030 |
maybe | -0.030 |
dinosaurs | -0.028 |
then | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
hand | +0.010 |
tap | +0.010 |
pet | +0.010 |
groom | +0.010 |
poppy | +0.009 |
Neg logit contributions | |
rob | -0.012 |
sometimes | -0.012 |
eighty | -0.011 |
cast | -0.011 |
besides | -0.011 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
ria | +0.034 |
ING | +0.034 |
groom | +0.032 |
ume | +0.032 |
tap | +0.031 |
Neg logit contributions | |
sometimes | -0.038 |
Sometimes | -0.034 |
maybe | -0.034 |
dinosaurs | -0.032 |
then | -0.032 |
Token | scenery |
Token ID | 31068 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
ria | +0.071 |
ING | +0.069 |
ume | +0.069 |
oxy | +0.068 |
ady | +0.068 |
Neg logit contributions | |
sometimes | -0.066 |
Sometimes | -0.058 |
maybe | -0.057 |
then | -0.056 |
cast | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
ria | +0.005 |
ING | +0.005 |
groom | +0.005 |
ume | +0.005 |
slight | +0.005 |
Neg logit contributions | |
sometimes | -0.005 |
maybe | -0.005 |
Sometimes | -0.005 |
then | -0.004 |
dinosaurs | -0.004 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
sometimes | +0.010 |
dinosaurs | +0.008 |
maybe | +0.008 |
rob | +0.008 |
Sometimes | +0.008 |
Neg logit contributions | |
ria | -0.013 |
ING | -0.013 |
ume | -0.012 |
Care | -0.012 |
tap | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ria | +0.002 |
ING | +0.002 |
groom | +0.002 |
ume | +0.002 |
tap | +0.002 |
Neg logit contributions | |
sometimes | -0.001 |
Sometimes | -0.001 |
maybe | -0.001 |
dinosaurs | -0.001 |
then | -0.001 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ria | +0.005 |
ING | +0.005 |
groom | +0.005 |
ume | +0.005 |
tap | +0.005 |
Neg logit contributions | |
sometimes | -0.003 |
Sometimes | -0.002 |
maybe | -0.002 |
dinosaurs | -0.002 |
rob | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
ING | +0.006 |
groom | +0.006 |
ria | +0.006 |
ume | +0.006 |
tap | +0.006 |
Neg logit contributions | |
sometimes | -0.006 |
Sometimes | -0.005 |
then | -0.005 |
maybe | -0.005 |
besides | -0.005 |
Token | I |
Token ID | 40 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
ING | +0.020 |
ria | +0.019 |
ume | +0.019 |
tap | +0.019 |
ram | +0.019 |
Neg logit contributions | |
sometimes | -0.019 |
then | -0.016 |
Sometimes | -0.016 |
maybe | -0.016 |
rob | -0.015 |
Token | 'm |
Token ID | 1101 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ING | +0.017 |
ria | +0.017 |
elcome | +0.015 |
groom | +0.015 |
ume | +0.015 |
Neg logit contributions | |
sometimes | -0.019 |
maybe | -0.017 |
Sometimes | -0.017 |
then | -0.016 |
cast | -0.015 |
Token | making |
Token ID | 1642 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
ING | +0.009 |
ria | +0.009 |
estone | +0.008 |
ater | +0.008 |
ume | +0.008 |
Neg logit contributions | |
sometimes | -0.005 |
maybe | -0.004 |
then | -0.004 |
Sometimes | -0.004 |
dinosaurs | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ria | +0.023 |
ING | +0.023 |
groom | +0.022 |
ume | +0.022 |
tap | +0.022 |
Neg logit contributions | |
sometimes | -0.018 |
Sometimes | -0.017 |
maybe | -0.016 |
dinosaurs | -0.015 |
then | -0.015 |
Token | peaceful |
Token ID | 12309 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
ume | +0.005 |
ING | +0.005 |
ria | +0.005 |
ady | +0.005 |
oxy | +0.005 |
Neg logit contributions | |
sometimes | -0.005 |
maybe | -0.005 |
dinosaurs | -0.005 |
then | -0.005 |
Sometimes | -0.005 |
Token | place |
Token ID | 1295 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
ING | +0.060 |
ria | +0.059 |
ume | +0.058 |
ady | +0.055 |
Care | +0.055 |
Neg logit contributions | |
sometimes | -0.102 |
Sometimes | -0.092 |
maybe | -0.091 |
then | -0.091 |
dinosaurs | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
ria | +0.013 |
ING | +0.013 |
tap | +0.013 |
ume | +0.012 |
groom | +0.012 |
Neg logit contributions | |
sometimes | -0.009 |
Sometimes | -0.009 |
maybe | -0.008 |
rob | -0.008 |
dinosaurs | -0.008 |
Token | I |
Token ID | 314 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ria | +0.006 |
ING | +0.006 |
ume | +0.005 |
groom | +0.005 |
tap | +0.005 |
Neg logit contributions | |
sometimes | -0.005 |
Sometimes | -0.004 |
maybe | -0.004 |
dinosaurs | -0.004 |
then | -0.004 |
Token | 'm |
Token ID | 1101 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
ING | +0.022 |
ria | +0.022 |
ume | +0.020 |
groom | +0.020 |
elcome | +0.020 |
Neg logit contributions | |
sometimes | -0.025 |
maybe | -0.022 |
Sometimes | -0.022 |
then | -0.021 |
dinosaurs | -0.020 |
Token | making |
Token ID | 1642 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ING | +0.015 |
ria | +0.014 |
estone | +0.014 |
ater | +0.014 |
Care | +0.014 |
Neg logit contributions | |
sometimes | -0.009 |
maybe | -0.008 |
then | -0.008 |
Sometimes | -0.007 |
dinosaurs | -0.007 |
Token | friends |
Token ID | 2460 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
hand | +0.002 |
pet | +0.002 |
groom | +0.001 |
finger | +0.001 |
ria | +0.001 |
Neg logit contributions | |
rob | -0.004 |
sometimes | -0.004 |
Sometimes | -0.004 |
maybe | -0.004 |
cast | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
ria | +0.012 |
ING | +0.012 |
ume | +0.011 |
groom | +0.011 |
tap | +0.011 |
Neg logit contributions | |
sometimes | -0.008 |
maybe | -0.007 |
Sometimes | -0.007 |
dinosaurs | -0.006 |
then | -0.006 |
Token | amazed |
Token ID | 24562 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
sometimes | +0.009 |
maybe | +0.008 |
then | +0.007 |
Sometimes | +0.007 |
dinosaurs | +0.007 |
Neg logit contributions | |
ING | -0.014 |
ria | -0.014 |
ume | -0.013 |
ater | -0.013 |
estone | -0.013 |
Token | by |
Token ID | 416 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Sometimes | +0.024 |
sometimes | +0.023 |
maybe | +0.023 |
rob | +0.023 |
eighty | +0.022 |
Neg logit contributions | |
ING | -0.025 |
ria | -0.024 |
ater | -0.023 |
copy | -0.023 |
groom | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ria | +0.029 |
ING | +0.028 |
groom | +0.028 |
tap | +0.028 |
elcome | +0.027 |
Neg logit contributions | |
sometimes | -0.020 |
Sometimes | -0.018 |
maybe | -0.018 |
rob | -0.017 |
cast | -0.016 |
Token | unique |
Token ID | 3748 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
ING | +0.033 |
ria | +0.033 |
tap | +0.031 |
groom | +0.031 |
slight | +0.030 |
Neg logit contributions | |
sometimes | -0.057 |
Sometimes | -0.054 |
maybe | -0.053 |
dinosaurs | -0.050 |
then | -0.050 |
Token | shell |
Token ID | 7582 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ria | +0.047 |
ING | +0.046 |
ume | +0.044 |
slight | +0.041 |
Care | +0.041 |
Neg logit contributions | |
sometimes | -0.092 |
maybe | -0.083 |
Sometimes | -0.083 |
dinosaurs | -0.082 |
then | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
ria | +0.027 |
ING | +0.027 |
tap | +0.026 |
ume | +0.026 |
groom | +0.026 |
Neg logit contributions | |
sometimes | -0.018 |
Sometimes | -0.017 |
maybe | -0.016 |
dinosaurs | -0.015 |
rob | -0.015 |
Token | they |
Token ID | 484 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
sometimes | +0.000 |
Sometimes | +0.000 |
rob | +0.000 |
dinosaurs | +0.000 |
narrative | +0.000 |
Neg logit contributions | |
groom | -0.001 |
ria | -0.001 |
tap | -0.001 |
pet | -0.001 |
elcome | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Sometimes | +0.000 |
sometimes | +0.000 |
maybe | +0.000 |
rob | +0.000 |
dinosaurs | +0.000 |
Neg logit contributions | |
groom | -0.001 |
ria | -0.001 |
pet | -0.001 |
copy | -0.001 |
tap | -0.001 |
Token | wanted |
Token ID | 2227 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
sometimes | +0.006 |
maybe | +0.005 |
Sometimes | +0.005 |
then | +0.005 |
dinosaurs | +0.005 |
Neg logit contributions | |
ING | -0.008 |
ria | -0.008 |
ume | -0.008 |
groom | -0.008 |
slight | -0.008 |
Token | ed |
Token ID | 276 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ING | +0.027 |
ria | +0.027 |
groom | +0.026 |
ume | +0.025 |
tap | +0.025 |
Neg logit contributions | |
sometimes | -0.026 |
maybe | -0.023 |
Sometimes | -0.023 |
then | -0.022 |
dinosaurs | -0.021 |
Token | it |
Token ID | 340 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ING | +0.012 |
ria | +0.012 |
ume | +0.012 |
estone | +0.011 |
mare | +0.011 |
Neg logit contributions | |
sometimes | -0.008 |
maybe | -0.007 |
Sometimes | -0.007 |
then | -0.007 |
dinosaurs | -0.006 |
Token | up |
Token ID | 510 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
sometimes | +0.002 |
under | +0.001 |
then | +0.001 |
cast | +0.001 |
maybe | +0.001 |
Neg logit contributions | |
ria | -0.003 |
ING | -0.003 |
groom | -0.003 |
ram | -0.003 |
iya | -0.003 |
Token | full |
Token ID | 1336 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
sometimes | +0.016 |
maybe | +0.014 |
Sometimes | +0.014 |
then | +0.014 |
dinosaurs | +0.013 |
Neg logit contributions | |
ING | -0.021 |
ria | -0.021 |
groom | -0.020 |
ume | -0.020 |
tap | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ria | +0.002 |
ING | +0.002 |
groom | +0.002 |
ram | +0.002 |
iya | +0.002 |
Neg logit contributions | |
sometimes | -0.001 |
then | -0.001 |
maybe | -0.001 |
Sometimes | -0.001 |
for | -0.001 |
Token | water |
Token ID | 1660 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ING | +0.007 |
ria | +0.007 |
ume | +0.007 |
estone | +0.006 |
elcome | +0.006 |
Neg logit contributions | |
sometimes | -0.009 |
maybe | -0.008 |
Sometimes | -0.008 |
then | -0.008 |
dinosaurs | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
ria | +0.031 |
ING | +0.031 |
oxy | +0.029 |
slight | +0.029 |
Care | +0.029 |
Neg logit contributions | |
sometimes | -0.021 |
then | -0.018 |
maybe | -0.017 |
cast | -0.017 |
Sometimes | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ING | +0.000 |
ater | +0.000 |
groom | +0.000 |
ria | +0.000 |
copy | +0.000 |
Neg logit contributions | |
Sometimes | -0.000 |
sometimes | -0.000 |
maybe | -0.000 |
then | -0.000 |
Tim | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
ING | +0.004 |
ria | +0.004 |
ume | +0.004 |
groom | +0.004 |
estone | +0.004 |
Neg logit contributions | |
sometimes | -0.004 |
maybe | -0.003 |
then | -0.003 |
Sometimes | -0.003 |
dinosaurs | -0.003 |
Token | so |
Token ID | 523 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
sometimes | +0.006 |
then | +0.005 |
maybe | +0.005 |
Sometimes | +0.004 |
dinosaurs | +0.004 |
Neg logit contributions | |
ING | -0.016 |
ria | -0.015 |
estone | -0.014 |
ater | -0.014 |
ume | -0.014 |
Token | glad |
Token ID | 9675 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
ING | +0.034 |
ria | +0.033 |
estone | +0.031 |
ram | +0.031 |
mare | +0.031 |
Neg logit contributions | |
sometimes | -0.019 |
maybe | -0.017 |
then | -0.017 |
Sometimes | -0.015 |
now | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
ING | +0.006 |
pet | +0.006 |
Care | +0.006 |
Her | +0.006 |
oxy | +0.006 |
Neg logit contributions | |
cast | -0.010 |
rob | -0.009 |
sometimes | -0.009 |
Sometimes | -0.009 |
narrative | -0.009 |
Token | time |
Token ID | 640 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ING | +0.016 |
ria | +0.015 |
ady | +0.014 |
slight | +0.014 |
oxy | +0.014 |
Neg logit contributions | |
sometimes | -0.020 |
maybe | -0.019 |
Sometimes | -0.018 |
dinosaurs | -0.018 |
rob | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ING | +0.002 |
elcome | +0.002 |
ria | +0.002 |
tap | +0.002 |
itter | +0.002 |
Neg logit contributions | |
sometimes | -0.003 |
rob | -0.003 |
dinosaurs | -0.003 |
bones | -0.003 |
Sometimes | -0.003 |
Token | there |
Token ID | 612 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
rob | +0.008 |
dinosaurs | +0.007 |
cast | +0.007 |
sometimes | +0.007 |
narrative | +0.007 |
Neg logit contributions | |
a | -0.006 |
hold | -0.006 |
hand | -0.006 |
ady | -0.006 |
ING | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ING | +0.010 |
ria | +0.010 |
tap | +0.010 |
elcome | +0.010 |
pet | +0.009 |
Neg logit contributions | |
sometimes | -0.013 |
dinosaurs | -0.012 |
rob | -0.012 |
cast | -0.012 |
Sometimes | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
pet | +0.022 |
ady | +0.021 |
oxy | +0.020 |
ING | +0.019 |
Her | +0.019 |
Neg logit contributions | |
cast | -0.038 |
sometimes | -0.036 |
lights | -0.036 |
rob | -0.036 |
Sometimes | -0.036 |
Token | little |
Token ID | 1310 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ume | +0.011 |
ING | +0.010 |
ria | +0.010 |
ady | +0.010 |
estone | +0.010 |
Neg logit contributions | |
sometimes | -0.015 |
maybe | -0.014 |
then | -0.014 |
dinosaurs | -0.014 |
Sometimes | -0.013 |
Token | girl |
Token ID | 2576 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
ING | +0.006 |
ria | +0.006 |
ume | +0.006 |
elcome | +0.006 |
spoken | +0.006 |
Neg logit contributions | |
sometimes | -0.008 |
dinosaurs | -0.007 |
Sometimes | -0.007 |
maybe | -0.007 |
then | -0.007 |
Token | named |
Token ID | 3706 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
ING | +0.022 |
ria | +0.022 |
ume | +0.021 |
slight | +0.021 |
groom | +0.021 |
Neg logit contributions | |
sometimes | -0.012 |
Sometimes | -0.010 |
maybe | -0.010 |
then | -0.010 |
dinosaurs | -0.009 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
sometimes | +0.007 |
Sometimes | +0.006 |
maybe | +0.006 |
dinosaurs | +0.005 |
then | +0.005 |
Neg logit contributions | |
ria | -0.021 |
ING | -0.021 |
ume | -0.020 |
groom | -0.020 |
tap | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
sometimes | +0.016 |
Sometimes | +0.014 |
maybe | +0.014 |
dinosaurs | +0.014 |
then | +0.013 |
Neg logit contributions | |
ria | -0.015 |
ING | -0.015 |
groom | -0.014 |
ume | -0.014 |
tap | -0.014 |
Token | sunny |
Token ID | 27737 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
groom | +0.017 |
ume | +0.017 |
ING | +0.016 |
elcome | +0.016 |
ria | +0.016 |
Neg logit contributions | |
sometimes | -0.006 |
then | -0.004 |
Sometimes | -0.004 |
maybe | -0.004 |
under | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
ING | +0.073 |
ria | +0.073 |
groom | +0.072 |
ume | +0.072 |
slight | +0.070 |
Neg logit contributions | |
sometimes | -0.029 |
Sometimes | -0.023 |
then | -0.021 |
maybe | -0.020 |
dinosaurs | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
groom | +0.033 |
ria | +0.032 |
ater | +0.032 |
slight | +0.031 |
ING | +0.031 |
Neg logit contributions | |
sometimes | -0.014 |
then | -0.010 |
maybe | -0.010 |
Sometimes | -0.010 |
under | -0.009 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ria | +0.014 |
ING | +0.014 |
ume | +0.013 |
ater | +0.013 |
groom | +0.013 |
Neg logit contributions | |
sometimes | -0.012 |
maybe | -0.010 |
Sometimes | -0.010 |
then | -0.010 |
dinosaurs | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
ria | +0.037 |
ING | +0.037 |
ume | +0.035 |
groom | +0.035 |
slight | +0.034 |
Neg logit contributions | |
sometimes | -0.029 |
maybe | -0.025 |
Sometimes | -0.025 |
then | -0.024 |
dinosaurs | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
ING | +0.025 |
ume | +0.025 |
ria | +0.024 |
ater | +0.024 |
ady | +0.024 |
Neg logit contributions | |
sometimes | -0.021 |
maybe | -0.018 |
Sometimes | -0.018 |
then | -0.017 |
dinosaurs | -0.017 |
Token | friends |
Token ID | 2460 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
ria | +0.015 |
ING | +0.015 |
ume | +0.015 |
oing | +0.014 |
ater | +0.014 |
Neg logit contributions | |
sometimes | -0.014 |
dinosaurs | -0.013 |
maybe | -0.012 |
Sometimes | -0.012 |
under | -0.012 |
Token | were |
Token ID | 547 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ria | +0.024 |
ING | +0.023 |
oing | +0.023 |
slight | +0.023 |
estone | +0.022 |
Neg logit contributions | |
sometimes | -0.015 |
then | -0.012 |
maybe | -0.012 |
Sometimes | -0.012 |
dinosaurs | -0.011 |
Token | playing |
Token ID | 2712 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
sometimes | +0.007 |
Sometimes | +0.006 |
maybe | +0.006 |
then | +0.006 |
dinosaurs | +0.006 |
Neg logit contributions | |
ria | -0.014 |
ING | -0.014 |
slight | -0.013 |
ater | -0.013 |
Care | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
sometimes | +0.001 |
Sometimes | +0.001 |
maybe | +0.001 |
dinosaurs | +0.001 |
then | +0.001 |
Neg logit contributions | |
ING | -0.001 |
ria | -0.001 |
tap | -0.001 |
groom | -0.001 |
copy | -0.001 |
Token | game |
Token ID | 983 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ume | +0.001 |
ria | +0.001 |
ING | +0.001 |
ady | +0.001 |
groom | +0.001 |
Neg logit contributions | |
sometimes | -0.001 |
Sometimes | -0.001 |
maybe | -0.001 |
dinosaurs | -0.001 |
then | -0.001 |
Token | sour |
Token ID | 11348 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ria | +0.005 |
ING | +0.005 |
groom | +0.004 |
ume | +0.004 |
tap | +0.004 |
Neg logit contributions | |
sometimes | -0.006 |
Sometimes | -0.005 |
maybe | -0.005 |
dinosaurs | -0.005 |
then | -0.005 |
Token | le |
Token ID | 443 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ria | +0.052 |
ING | +0.050 |
ady | +0.049 |
oxy | +0.049 |
ume | +0.049 |
Neg logit contributions | |
sometimes | -0.033 |
dinosaurs | -0.032 |
for | -0.032 |
books | -0.030 |
puzzles | -0.030 |
Token | mons |
Token ID | 11567 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
slight | +0.039 |
copy | +0.039 |
groom | +0.039 |
Care | +0.039 |
rhythm | +0.039 |
Neg logit contributions | |
cast | -0.033 |
sometimes | -0.033 |
dinosaurs | -0.032 |
rob | -0.031 |
for | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
ING | +0.042 |
ria | +0.042 |
groom | +0.041 |
slight | +0.040 |
ram | +0.040 |
Neg logit contributions | |
sometimes | -0.023 |
then | -0.019 |
maybe | -0.019 |
Sometimes | -0.017 |
cast | -0.017 |
Token | headed |
Token ID | 9153 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
sometimes | +0.011 |
maybe | +0.010 |
Sometimes | +0.010 |
then | +0.009 |
dinosaurs | +0.009 |
Neg logit contributions | |
ING | -0.013 |
ria | -0.013 |
ume | -0.012 |
groom | -0.012 |
slight | -0.012 |
Token | back |
Token ID | 736 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
ING | +0.005 |
ria | +0.005 |
slight | +0.005 |
oxy | +0.005 |
ume | +0.005 |
Neg logit contributions | |
sometimes | -0.006 |
then | -0.005 |
Sometimes | -0.005 |
maybe | -0.005 |
dinosaurs | -0.005 |
Token | home |
Token ID | 1363 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
ING | +0.023 |
ria | +0.022 |
ume | +0.022 |
oxy | +0.022 |
slight | +0.022 |
Neg logit contributions | |
sometimes | -0.020 |
Sometimes | -0.018 |
then | -0.017 |
maybe | -0.017 |
under | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ING | +0.028 |
Care | +0.026 |
ria | +0.026 |
slight | +0.026 |
OU | +0.026 |
Neg logit contributions | |
sometimes | -0.017 |
then | -0.015 |
maybe | -0.015 |
for | -0.014 |
under | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ING | +0.003 |
ria | +0.003 |
groom | +0.003 |
ater | +0.003 |
tap | +0.003 |
Neg logit contributions | |
sometimes | -0.002 |
Sometimes | -0.002 |
maybe | -0.002 |
then | -0.001 |
dinosaurs | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ria | +0.014 |
ING | +0.013 |
elcome | +0.013 |
ady | +0.013 |
Care | +0.013 |
Neg logit contributions | |
sometimes | -0.011 |
Sometimes | -0.010 |
maybe | -0.010 |
dinosaurs | -0.010 |
rob | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
ING | +0.007 |
tap | +0.006 |
ria | +0.006 |
ater | +0.006 |
slight | +0.006 |
Neg logit contributions | |
sometimes | -0.008 |
then | -0.007 |
Sometimes | -0.007 |
maybe | -0.007 |
dinosaurs | -0.006 |
Token | toy |
Token ID | 13373 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
sometimes | +0.023 |
maybe | +0.022 |
Sometimes | +0.021 |
rob | +0.020 |
eighty | +0.020 |
Neg logit contributions | |
tap | -0.019 |
ING | -0.019 |
pet | -0.019 |
human | -0.018 |
ria | -0.018 |
Token | cars |
Token ID | 5006 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
sometimes | +0.029 |
Sometimes | +0.027 |
maybe | +0.027 |
eighty | +0.025 |
then | +0.025 |
Neg logit contributions | |
ING | -0.031 |
tap | -0.030 |
ria | -0.030 |
pet | -0.029 |
groom | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Sometimes | +0.028 |
maybe | +0.027 |
sometimes | +0.026 |
rob | +0.026 |
dinosaurs | +0.025 |
Neg logit contributions | |
ING | -0.015 |
tap | -0.015 |
ater | -0.014 |
pet | -0.014 |
ume | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
ING | +0.010 |
ria | +0.010 |
tap | +0.010 |
Care | +0.010 |
pet | +0.009 |
Neg logit contributions | |
sometimes | -0.009 |
rob | -0.008 |
dinosaurs | -0.008 |
eighty | -0.008 |
then | -0.007 |
Token | did |
Token ID | 750 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Sometimes | +0.010 |
rob | +0.008 |
sometimes | +0.008 |
maybe | +0.008 |
dinosaurs | +0.008 |
Neg logit contributions | |
pet | -0.010 |
groom | -0.009 |
tap | -0.009 |
copy | -0.009 |
ING | -0.009 |
Token | not |
Token ID | 407 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
rob | +0.012 |
sometimes | +0.011 |
Sometimes | +0.011 |
dinosaurs | +0.011 |
maybe | +0.010 |
Neg logit contributions | |
ING | -0.010 |
copy | -0.010 |
tap | -0.010 |
ria | -0.010 |
pet | -0.009 |
Token | steal |
Token ID | 8711 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ria | +0.008 |
elcome | +0.008 |
ING | +0.007 |
ower | +0.007 |
Care | +0.007 |
Neg logit contributions | |
sometimes | -0.007 |
maybe | -0.005 |
then | -0.005 |
dinosaurs | -0.005 |
Sometimes | -0.005 |
Token | anything |
Token ID | 1997 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ING | +0.006 |
ria | +0.006 |
tap | +0.006 |
groom | +0.006 |
ume | +0.006 |
Neg logit contributions | |
sometimes | -0.005 |
Sometimes | -0.005 |
maybe | -0.005 |
rob | -0.005 |
dinosaurs | -0.005 |
Token | again |
Token ID | 757 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ING | +0.000 |
ria | +0.000 |
tap | +0.000 |
ume | +0.000 |
groom | +0.000 |
Neg logit contributions | |
sometimes | -0.000 |
Sometimes | -0.000 |
maybe | -0.000 |
dinosaurs | -0.000 |
then | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
sometimes | +0.024 |
maybe | +0.021 |
Sometimes | +0.021 |
then | +0.020 |
dinosaurs | +0.020 |
Neg logit contributions | |
ria | -0.025 |
ING | -0.024 |
groom | -0.023 |
ume | -0.023 |
slight | -0.023 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
ING | +0.012 |
ria | +0.011 |
tap | +0.011 |
Care | +0.011 |
ume | +0.011 |
Neg logit contributions | |
sometimes | -0.011 |
rob | -0.010 |
eighty | -0.010 |
cast | -0.010 |
dinosaurs | -0.010 |
Token | as |
Token ID | 355 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
sometimes | +0.014 |
Sometimes | +0.012 |
maybe | +0.012 |
then | +0.012 |
dinosaurs | +0.012 |
Neg logit contributions | |
ria | -0.016 |
ING | -0.016 |
slight | -0.015 |
ume | -0.015 |
groom | -0.015 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ria | +0.018 |
ING | +0.018 |
groom | +0.017 |
ume | +0.016 |
tap | +0.016 |
Neg logit contributions | |
sometimes | -0.016 |
Sometimes | -0.014 |
maybe | -0.014 |
then | -0.013 |
dinosaurs | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
sometimes | +0.006 |
maybe | +0.005 |
Sometimes | +0.005 |
dinosaurs | +0.005 |
then | +0.005 |
Neg logit contributions | |
ria | -0.006 |
ING | -0.006 |
slight | -0.006 |
groom | -0.006 |
ume | -0.006 |
Token | You |
Token ID | 921 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
ria | +0.009 |
ING | +0.009 |
groom | +0.009 |
slight | +0.009 |
ume | +0.009 |
Neg logit contributions | |
sometimes | -0.006 |
Sometimes | -0.005 |
maybe | -0.005 |
dinosaurs | -0.005 |
then | -0.005 |
Token | are |
Token ID | 389 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
sometimes | +0.006 |
maybe | +0.005 |
Sometimes | +0.005 |
then | +0.005 |
dinosaurs | +0.005 |
Neg logit contributions | |
ria | -0.011 |
ING | -0.010 |
elcome | -0.010 |
slight | -0.010 |
iya | -0.010 |
Token | my |
Token ID | 616 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
sometimes | +0.004 |
dinosaurs | +0.004 |
maybe | +0.004 |
then | +0.003 |
Sometimes | +0.003 |
Neg logit contributions | |
ria | -0.005 |
ING | -0.005 |
oing | -0.005 |
estone | -0.005 |
ower | -0.005 |
Token | friend |
Token ID | 1545 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
sometimes | +0.004 |
Sometimes | +0.004 |
maybe | +0.004 |
dinosaurs | +0.004 |
then | +0.003 |
Neg logit contributions | |
ria | -0.002 |
ING | -0.002 |
ume | -0.002 |
groom | -0.002 |
slight | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
sometimes | +0.000 |
Sometimes | +0.000 |
maybe | +0.000 |
dinosaurs | +0.000 |
then | +0.000 |
Neg logit contributions | |
ING | -0.000 |
ria | -0.000 |
groom | -0.000 |
ume | -0.000 |
tap | -0.000 |
Token | Can |
Token ID | 1680 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
ria | +0.013 |
ING | +0.012 |
groom | +0.012 |
slight | +0.012 |
tap | +0.012 |
Neg logit contributions | |
sometimes | -0.008 |
Sometimes | -0.007 |
maybe | -0.007 |
dinosaurs | -0.007 |
then | -0.007 |
Token | we |
Token ID | 356 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
cast | +0.025 |
rob | +0.024 |
dinosaurs | +0.022 |
bones | +0.022 |
camps | +0.022 |
Neg logit contributions | |
Her | -0.013 |
ING | -0.013 |
ria | -0.013 |
tap | -0.012 |
Girl | -0.011 |
Token | play |
Token ID | 711 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
ria | +0.029 |
ady | +0.029 |
ING | +0.029 |
slight | +0.028 |
oing | +0.028 |
Neg logit contributions | |
sometimes | -0.029 |
then | -0.025 |
Sometimes | -0.024 |
maybe | -0.024 |
now | -0.022 |
Token | ran |
Token ID | 4966 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
sometimes | +0.010 |
Sometimes | +0.010 |
rob | +0.009 |
dinosaurs | +0.009 |
narrative | +0.009 |
Neg logit contributions | |
ria | -0.010 |
groom | -0.010 |
ING | -0.010 |
tap | -0.010 |
pet | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
sometimes | +0.011 |
Sometimes | +0.010 |
maybe | +0.010 |
dinosaurs | +0.010 |
then | +0.010 |
Neg logit contributions | |
ria | -0.012 |
ING | -0.012 |
groom | -0.011 |
tap | -0.011 |
ume | -0.011 |
Token | catch |
Token ID | 4929 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
sometimes | +0.002 |
Sometimes | +0.001 |
maybe | +0.001 |
dinosaurs | +0.001 |
rob | +0.001 |
Neg logit contributions | |
ING | -0.002 |
ria | -0.002 |
tap | -0.002 |
copy | -0.002 |
groom | -0.002 |
Token | him |
Token ID | 683 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ING | +0.019 |
ria | +0.019 |
tap | +0.019 |
copy | +0.018 |
Care | +0.018 |
Neg logit contributions | |
sometimes | -0.012 |
Sometimes | -0.011 |
maybe | -0.010 |
rob | -0.010 |
narrative | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
sometimes | +0.031 |
Sometimes | +0.028 |
maybe | +0.028 |
dinosaurs | +0.027 |
then | +0.026 |
Neg logit contributions | |
ria | -0.029 |
ING | -0.029 |
groom | -0.027 |
ume | -0.027 |
tap | -0.027 |
Token | But |
Token ID | 887 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ria | +0.002 |
ING | +0.002 |
groom | +0.002 |
ume | +0.002 |
slight | +0.002 |
Neg logit contributions | |
sometimes | -0.002 |
Sometimes | -0.001 |
maybe | -0.001 |
then | -0.001 |
dinosaurs | -0.001 |
Token | Ben |
Token ID | 3932 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
rob | +0.005 |
Sometimes | +0.005 |
sometimes | +0.005 |
cast | +0.005 |
dinosaurs | +0.005 |
Neg logit contributions | |
ria | -0.007 |
ING | -0.007 |
tap | -0.007 |
elcome | -0.007 |
snail | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
sometimes | +0.008 |
maybe | +0.007 |
then | +0.007 |
Sometimes | +0.006 |
dinosaurs | +0.006 |
Neg logit contributions | |
ria | -0.013 |
ING | -0.013 |
ume | -0.013 |
groom | -0.013 |
slight | -0.012 |
Token | too |
Token ID | 1165 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
sometimes | +0.024 |
maybe | +0.021 |
Sometimes | +0.020 |
then | +0.020 |
dinosaurs | +0.019 |
Neg logit contributions | |
ria | -0.036 |
ING | -0.036 |
ume | -0.034 |
groom | -0.034 |
elcome | -0.033 |
Token | fast |
Token ID | 3049 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
groom | +0.034 |
ria | +0.033 |
elcome | +0.033 |
ING | +0.033 |
ume | +0.033 |
Neg logit contributions | |
sometimes | -0.021 |
maybe | -0.017 |
Sometimes | -0.017 |
then | -0.016 |
now | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
sometimes | +0.028 |
Sometimes | +0.028 |
maybe | +0.027 |
rob | +0.026 |
narrative | +0.025 |
Neg logit contributions | |
ING | -0.028 |
ria | -0.027 |
tap | -0.026 |
ume | -0.026 |
ater | -0.025 |
Token | my |
Token ID | 1820 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
sometimes | +0.020 |
Sometimes | +0.017 |
maybe | +0.017 |
dinosaurs | +0.016 |
then | +0.016 |
Neg logit contributions | |
ria | -0.032 |
ING | -0.032 |
groom | -0.031 |
ume | -0.031 |
tap | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
sometimes | +0.002 |
then | +0.002 |
maybe | +0.002 |
now | +0.002 |
dinosaurs | +0.002 |
Neg logit contributions | |
ING | -0.005 |
ume | -0.004 |
estone | -0.004 |
ria | -0.004 |
Care | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
sometimes | +0.010 |
then | +0.008 |
maybe | +0.008 |
Sometimes | +0.007 |
now | +0.007 |
Neg logit contributions | |
ING | -0.017 |
ria | -0.016 |
estone | -0.016 |
ater | -0.016 |
ume | -0.016 |
Token | too |
Token ID | 1165 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ria | +0.019 |
ING | +0.018 |
groom | +0.018 |
tap | +0.018 |
elcome | +0.017 |
Neg logit contributions | |
sometimes | -0.014 |
Sometimes | -0.014 |
rob | -0.013 |
maybe | -0.013 |
dinosaurs | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ria | +0.006 |
ING | +0.006 |
groom | +0.006 |
Care | +0.006 |
ume | +0.006 |
Neg logit contributions | |
sometimes | -0.004 |
then | -0.004 |
maybe | -0.004 |
dinosaurs | -0.003 |
Sometimes | -0.003 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
sometimes | +0.024 |
rob | +0.021 |
narrative | +0.021 |
dinosaurs | +0.021 |
maybe | +0.020 |
Neg logit contributions | |
ria | -0.026 |
ING | -0.024 |
elcome | -0.024 |
Care | -0.023 |
tap | -0.023 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
sometimes | +0.016 |
maybe | +0.015 |
dinosaurs | +0.015 |
then | +0.014 |
cast | +0.014 |
Neg logit contributions | |
ING | -0.010 |
ria | -0.009 |
Care | -0.009 |
pet | -0.009 |
ady | -0.008 |
Token | upon |
Token ID | 2402 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
rob | +0.081 |
sometimes | +0.074 |
bones | +0.072 |
dinosaurs | +0.071 |
eighty | +0.069 |
Neg logit contributions | |
ria | -0.043 |
hand | -0.039 |
aa | -0.038 |
a | -0.038 |
opsy | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ING | +0.012 |
Care | +0.011 |
pet | +0.011 |
ria | +0.011 |
Her | +0.011 |
Neg logit contributions | |
sometimes | -0.013 |
Sometimes | -0.012 |
cast | -0.012 |
rob | -0.012 |
maybe | -0.012 |
Token | time |
Token ID | 640 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ING | +0.022 |
ria | +0.021 |
ady | +0.019 |
oxy | +0.019 |
ater | +0.019 |
Neg logit contributions | |
sometimes | -0.030 |
maybe | -0.028 |
Sometimes | -0.027 |
dinosaurs | -0.027 |
rob | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
ING | +0.008 |
elcome | +0.007 |
ria | +0.007 |
ume | +0.006 |
unk | +0.006 |
Neg logit contributions | |
sometimes | -0.011 |
rob | -0.011 |
bones | -0.010 |
dinosaurs | -0.010 |
cast | -0.010 |
Token | is |
Token ID | 318 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
sometimes | +0.026 |
maybe | +0.024 |
Sometimes | +0.023 |
dinosaurs | +0.022 |
then | +0.022 |
Neg logit contributions | |
ING | -0.030 |
ria | -0.029 |
tap | -0.028 |
ume | -0.027 |
copy | -0.027 |
Token | sad |
Token ID | 6507 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
sometimes | +0.023 |
maybe | +0.020 |
then | +0.019 |
Sometimes | +0.019 |
under | +0.018 |
Neg logit contributions | |
ria | -0.035 |
ING | -0.035 |
iya | -0.033 |
estone | -0.033 |
ume | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
sometimes | +0.010 |
Sometimes | +0.009 |
maybe | +0.009 |
dinosaurs | +0.009 |
rob | +0.009 |
Neg logit contributions | |
ING | -0.008 |
ria | -0.008 |
tap | -0.008 |
ume | -0.008 |
groom | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
ria | +0.012 |
groom | +0.012 |
ater | +0.011 |
elcome | +0.011 |
ING | +0.011 |
Neg logit contributions | |
Sometimes | -0.006 |
sometimes | -0.006 |
maybe | -0.005 |
then | -0.004 |
besides | -0.004 |
Token | loves |
Token ID | 10408 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
sometimes | +0.018 |
rob | +0.016 |
dinosaurs | +0.016 |
maybe | +0.016 |
Sometimes | +0.016 |
Neg logit contributions | |
tap | -0.016 |
pet | -0.016 |
ING | -0.015 |
copy | -0.014 |
ram | -0.014 |
Token | Sara |
Token ID | 24799 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
sometimes | +0.037 |
Sometimes | +0.034 |
rob | +0.033 |
maybe | +0.033 |
then | +0.032 |
Neg logit contributions | |
groom | -0.042 |
ria | -0.042 |
tap | -0.042 |
ING | -0.041 |
iya | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
sometimes | +0.016 |
Sometimes | +0.015 |
maybe | +0.015 |
dinosaurs | +0.014 |
rob | +0.014 |
Neg logit contributions | |
ING | -0.016 |
ria | -0.016 |
tap | -0.015 |
ume | -0.015 |
groom | -0.015 |
Token | Ben |
Token ID | 3932 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
tap | +0.017 |
groom | +0.016 |
ING | +0.016 |
pet | +0.016 |
ria | +0.016 |
Neg logit contributions | |
sometimes | -0.016 |
rob | -0.015 |
Sometimes | -0.014 |
maybe | -0.014 |
dinosaurs | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
sometimes | +0.002 |
maybe | +0.002 |
Sometimes | +0.002 |
then | +0.002 |
dinosaurs | +0.002 |
Neg logit contributions | |
ria | -0.002 |
ING | -0.002 |
groom | -0.002 |
ume | -0.002 |
slight | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
ria | +0.011 |
ING | +0.011 |
groom | +0.010 |
elcome | +0.010 |
ater | +0.010 |
Neg logit contributions | |
sometimes | -0.006 |
Sometimes | -0.006 |
maybe | -0.006 |
then | -0.005 |
dinosaurs | -0.005 |
Token | wants |
Token ID | 3382 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
sometimes | +0.018 |
rob | +0.016 |
maybe | +0.016 |
dinosaurs | +0.016 |
Sometimes | +0.016 |
Neg logit contributions | |
pet | -0.016 |
tap | -0.016 |
ING | -0.015 |
copy | -0.014 |
groom | -0.014 |
Token | draw |
Token ID | 3197 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
ria | +0.035 |
ING | +0.034 |
ume | +0.033 |
Care | +0.033 |
ady | +0.032 |
Neg logit contributions | |
sometimes | -0.027 |
maybe | -0.024 |
Sometimes | -0.022 |
then | -0.022 |
dinosaurs | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Sometimes | +0.025 |
eighty | +0.025 |
sometimes | +0.024 |
eday | +0.024 |
maybe | +0.023 |
Neg logit contributions | |
tap | -0.011 |
ING | -0.011 |
rhythm | -0.010 |
pet | -0.010 |
Her | -0.009 |
Token | cr |
Token ID | 1067 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
sometimes | +0.003 |
maybe | +0.003 |
Sometimes | +0.003 |
rob | +0.003 |
then | +0.003 |
Neg logit contributions | |
ING | -0.003 |
tap | -0.003 |
groom | -0.003 |
ria | -0.003 |
copy | -0.003 |
Token | ay |
Token ID | 323 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
sometimes | +0.002 |
maybe | +0.002 |
Sometimes | +0.002 |
then | +0.002 |
dinosaurs | +0.002 |
Neg logit contributions | |
ING | -0.002 |
ria | -0.002 |
ume | -0.002 |
tap | -0.002 |
groom | -0.002 |
Token | ons |
Token ID | 684 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
sometimes | +0.002 |
Sometimes | +0.002 |
maybe | +0.002 |
then | +0.002 |
dinosaurs | +0.002 |
Neg logit contributions | |
ria | -0.003 |
ING | -0.003 |
ume | -0.003 |
tap | -0.003 |
groom | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Sometimes | +0.002 |
maybe | +0.002 |
sometimes | +0.002 |
rob | +0.002 |
cast | +0.002 |
Neg logit contributions | |
ING | -0.001 |
ria | -0.001 |
ume | -0.001 |
tap | -0.001 |
groom | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
sometimes | +0.002 |
rob | +0.002 |
maybe | +0.002 |
dinosaurs | +0.002 |
then | +0.002 |
Neg logit contributions | |
ria | -0.004 |
ING | -0.004 |
tap | -0.004 |
ume | -0.004 |
pet | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
groom | +0.003 |
pet | +0.003 |
copy | +0.003 |
tap | +0.003 |
ria | +0.003 |
Neg logit contributions | |
rob | -0.004 |
Sometimes | -0.003 |
cast | -0.003 |
maybe | -0.003 |
dinosaurs | -0.003 |
Token | many |
Token ID | 867 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
rob | +0.005 |
cast | +0.005 |
maybe | +0.005 |
sometimes | +0.004 |
Sometimes | +0.004 |
Neg logit contributions | |
groom | -0.006 |
pet | -0.006 |
hand | -0.005 |
ume | -0.005 |
tap | -0.005 |
Token | colors |
Token ID | 7577 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
sometimes | +0.042 |
Sometimes | +0.042 |
rob | +0.041 |
maybe | +0.041 |
eighty | +0.040 |
Neg logit contributions | |
pet | -0.024 |
tap | -0.024 |
ady | -0.023 |
copy | -0.023 |
ater | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
rob | +0.009 |
Sometimes | +0.009 |
maybe | +0.009 |
sometimes | +0.009 |
narrative | +0.009 |
Neg logit contributions | |
tap | -0.008 |
ume | -0.008 |
ria | -0.008 |
ING | -0.007 |
copy | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
sometimes | +0.009 |
maybe | +0.007 |
Sometimes | +0.007 |
dinosaurs | +0.007 |
then | +0.007 |
Neg logit contributions | |
ria | -0.012 |
ING | -0.012 |
slight | -0.011 |
groom | -0.011 |
ume | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
sometimes | +0.007 |
Sometimes | +0.006 |
maybe | +0.006 |
dinosaurs | +0.005 |
then | +0.005 |
Neg logit contributions | |
ria | -0.020 |
ING | -0.020 |
groom | -0.019 |
tap | -0.019 |
ume | -0.019 |
Token | bin |
Token ID | 9874 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
sometimes | +0.018 |
Sometimes | +0.017 |
maybe | +0.017 |
rob | +0.016 |
then | +0.016 |
Neg logit contributions | |
ING | -0.012 |
ria | -0.012 |
tap | -0.012 |
groom | -0.011 |
slight | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
ria | +0.005 |
ING | +0.005 |
tap | +0.005 |
ume | +0.005 |
groom | +0.005 |
Neg logit contributions | |
sometimes | -0.004 |
Sometimes | -0.004 |
maybe | -0.004 |
dinosaurs | -0.004 |
rob | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
sometimes | +0.010 |
rob | +0.009 |
dinosaurs | +0.009 |
cast | +0.009 |
maybe | +0.009 |
Neg logit contributions | |
ING | -0.011 |
ria | -0.011 |
Care | -0.010 |
tap | -0.010 |
elcome | -0.010 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
sometimes | +0.009 |
maybe | +0.008 |
then | +0.008 |
Sometimes | +0.008 |
dinosaurs | +0.008 |
Neg logit contributions | |
ING | -0.007 |
ria | -0.007 |
Care | -0.007 |
tap | -0.007 |
ady | -0.006 |
Token | upon |
Token ID | 2402 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
rob | +0.075 |
sometimes | +0.067 |
dinosaurs | +0.066 |
eighty | +0.064 |
bones | +0.064 |
Neg logit contributions | |
ria | -0.044 |
hand | -0.041 |
a | -0.040 |
aa | -0.040 |
opsy | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ING | +0.012 |
Care | +0.012 |
pet | +0.012 |
Her | +0.011 |
copy | +0.011 |
Neg logit contributions | |
sometimes | -0.014 |
cast | -0.014 |
Sometimes | -0.014 |
rob | -0.014 |
dinosaurs | -0.013 |
Token | time |
Token ID | 640 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ING | +0.022 |
ria | +0.021 |
ady | +0.020 |
ater | +0.019 |
slight | +0.019 |
Neg logit contributions | |
sometimes | -0.029 |
maybe | -0.027 |
Sometimes | -0.026 |
dinosaurs | -0.026 |
rob | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
ING | +0.003 |
ria | +0.003 |
elcome | +0.003 |
tap | +0.003 |
ower | +0.003 |
Neg logit contributions | |
sometimes | -0.003 |
rob | -0.003 |
dinosaurs | -0.003 |
Sometimes | -0.003 |
maybe | -0.003 |
Token | there |
Token ID | 612 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
rob | +0.008 |
dinosaurs | +0.007 |
cast | +0.007 |
unic | +0.006 |
rides | +0.006 |
Neg logit contributions | |
a | -0.005 |
hand | -0.005 |
tap | -0.005 |
hold | -0.004 |
ING | -0.004 |
Token | happily |
Token ID | 18177 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
sometimes | +0.008 |
Sometimes | +0.007 |
maybe | +0.007 |
dinosaurs | +0.007 |
then | +0.006 |
Neg logit contributions | |
ria | -0.009 |
ING | -0.009 |
groom | -0.008 |
tap | -0.008 |
ume | -0.008 |
Token | ever |
Token ID | 1683 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
sometimes | +0.016 |
maybe | +0.012 |
then | +0.012 |
Sometimes | +0.012 |
dinosaurs | +0.012 |
Neg logit contributions | |
ING | -0.037 |
ria | -0.037 |
slight | -0.035 |
groom | -0.035 |
tap | -0.035 |
Token | after |
Token ID | 706 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
sometimes | +0.038 |
Sometimes | +0.033 |
maybe | +0.033 |
dinosaurs | +0.031 |
then | +0.031 |
Neg logit contributions | |
ria | -0.049 |
ING | -0.049 |
groom | -0.046 |
ume | -0.046 |
tap | -0.045 |
Token | ! |
Token ID | 0 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Sometimes | +0.024 |
sometimes | +0.023 |
maybe | +0.023 |
eighty | +0.022 |
rob | +0.022 |
Neg logit contributions | |
ING | -0.011 |
ria | -0.011 |
tap | -0.010 |
pet | -0.010 |
elcome | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
sometimes | +0.009 |
maybe | +0.008 |
cast | +0.008 |
dinosaurs | +0.008 |
Sometimes | +0.008 |
Neg logit contributions | |
ria | -0.008 |
ING | -0.008 |
Care | -0.008 |
ady | -0.008 |
ume | -0.008 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
sometimes | +0.008 |
maybe | +0.008 |
Sometimes | +0.008 |
then | +0.007 |
dinosaurs | +0.007 |
Neg logit contributions | |
ING | -0.007 |
ria | -0.007 |
Care | -0.007 |
tap | -0.007 |
ume | -0.007 |
Token | there |
Token ID | 612 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
rob | +0.074 |
dinosaurs | +0.066 |
sometimes | +0.066 |
bones | +0.064 |
eighty | +0.063 |
Neg logit contributions | |
ria | -0.033 |
hand | -0.030 |
a | -0.029 |
opsy | -0.028 |
aa | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
sometimes | +0.010 |
dinosaurs | +0.010 |
rob | +0.010 |
Sometimes | +0.010 |
narrative | +0.009 |
Neg logit contributions | |
ria | -0.010 |
ING | -0.010 |
tap | -0.009 |
elcome | -0.009 |
pet | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
pet | +0.034 |
ady | +0.031 |
lamb | +0.028 |
Her | +0.028 |
Care | +0.028 |
Neg logit contributions | |
cast | -0.066 |
rob | -0.062 |
lights | -0.059 |
narrative | -0.059 |
bones | -0.057 |
Token | young |
Token ID | 1862 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ume | +0.013 |
ING | +0.012 |
ria | +0.012 |
ady | +0.012 |
estone | +0.012 |
Neg logit contributions | |
sometimes | -0.018 |
maybe | -0.017 |
Sometimes | -0.017 |
then | -0.017 |
dinosaurs | -0.016 |
Token | boy |
Token ID | 2933 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ING | +0.004 |
ria | +0.004 |
ume | +0.004 |
Care | +0.004 |
slight | +0.004 |
Neg logit contributions | |
sometimes | -0.005 |
dinosaurs | -0.005 |
maybe | -0.005 |
Sometimes | -0.005 |
then | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
sometimes | +0.003 |
Sometimes | +0.003 |
maybe | +0.003 |
dinosaurs | +0.003 |
then | +0.003 |
Neg logit contributions | |
ria | -0.004 |
ING | -0.004 |
groom | -0.004 |
slight | -0.004 |
tap | -0.004 |
Token | shiny |
Token ID | 22441 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
ING | +0.001 |
ria | +0.001 |
ume | +0.001 |
groom | +0.000 |
tap | +0.000 |
Neg logit contributions | |
sometimes | -0.001 |
Sometimes | -0.001 |
maybe | -0.001 |
dinosaurs | -0.001 |
then | -0.001 |
Token | sword |
Token ID | 8429 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
sometimes | +0.021 |
Sometimes | +0.019 |
maybe | +0.019 |
rob | +0.017 |
dinosaurs | +0.017 |
Neg logit contributions | |
ING | -0.021 |
tap | -0.020 |
ria | -0.020 |
groom | -0.020 |
ater | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
Sometimes | +0.020 |
sometimes | +0.018 |
maybe | +0.018 |
rob | +0.017 |
narrative | +0.017 |
Neg logit contributions | |
ING | -0.025 |
tap | -0.024 |
pet | -0.024 |
ater | -0.024 |
ume | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
sometimes | +0.001 |
Sometimes | +0.001 |
dinosaurs | +0.001 |
maybe | +0.001 |
rob | +0.001 |
Neg logit contributions | |
ria | -0.003 |
ING | -0.003 |
tap | -0.003 |
groom | -0.003 |
slight | -0.003 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Sometimes | +0.022 |
sometimes | +0.021 |
narrative | +0.019 |
maybe | +0.019 |
rob | +0.018 |
Neg logit contributions | |
pet | -0.020 |
ria | -0.020 |
ater | -0.020 |
groom | -0.020 |
copy | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
narrative | +0.070 |
Sometimes | +0.067 |
rob | +0.067 |
sometimes | +0.066 |
maybe | +0.066 |
Neg logit contributions | |
pet | -0.036 |
tap | -0.034 |
rhythm | -0.032 |
human | -0.032 |
ria | -0.032 |
Token | show |
Token ID | 905 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
sometimes | +0.005 |
Sometimes | +0.005 |
dinosaurs | +0.005 |
maybe | +0.005 |
narrative | +0.005 |
Neg logit contributions | |
tap | -0.003 |
copy | -0.003 |
ING | -0.003 |
pet | -0.003 |
groom | -0.003 |
Token | off |
Token ID | 572 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ria | +0.013 |
ING | +0.013 |
ume | +0.012 |
slight | +0.012 |
groom | +0.012 |
Neg logit contributions | |
sometimes | -0.008 |
maybe | -0.007 |
Sometimes | -0.007 |
dinosaurs | -0.007 |
then | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
ING | +0.038 |
ria | +0.038 |
ume | +0.035 |
groom | +0.035 |
tap | +0.035 |
Neg logit contributions | |
sometimes | -0.027 |
Sometimes | -0.023 |
maybe | -0.023 |
dinosaurs | -0.022 |
then | -0.021 |
Token | his |
Token ID | 465 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
sometimes | +0.001 |
Sometimes | +0.001 |
rob | +0.001 |
maybe | +0.001 |
eighty | +0.001 |
Neg logit contributions | |
ria | -0.002 |
ING | -0.002 |
tap | -0.002 |
groom | -0.002 |
copy | -0.002 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
sometimes | +0.022 |
Sometimes | +0.019 |
maybe | +0.019 |
dinosaurs | +0.017 |
then | +0.017 |
Neg logit contributions | |
ria | -0.045 |
ING | -0.045 |
groom | -0.043 |
ume | -0.043 |
tap | -0.042 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ING | +0.009 |
ume | +0.009 |
ria | +0.008 |
estone | +0.008 |
rys | +0.008 |
Neg logit contributions | |
sometimes | -0.005 |
then | -0.004 |
maybe | -0.004 |
Sometimes | -0.004 |
dinosaurs | -0.004 |
Token | how |
Token ID | 703 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
sometimes | +0.039 |
Sometimes | +0.035 |
maybe | +0.035 |
dinosaurs | +0.033 |
then | +0.033 |
Neg logit contributions | |
ria | -0.044 |
ING | -0.043 |
groom | -0.041 |
tap | -0.041 |
ume | -0.041 |
Token | soft |
Token ID | 2705 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
ria | +0.012 |
ING | +0.012 |
groom | +0.011 |
ume | +0.011 |
tap | +0.011 |
Neg logit contributions | |
sometimes | -0.011 |
Sometimes | -0.010 |
maybe | -0.010 |
dinosaurs | -0.009 |
then | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ria | +0.002 |
ING | +0.002 |
ume | +0.002 |
groom | +0.002 |
tap | +0.002 |
Neg logit contributions | |
sometimes | -0.001 |
Sometimes | -0.001 |
maybe | -0.001 |
dinosaurs | -0.001 |
then | -0.001 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ING | +0.010 |
ria | +0.010 |
ume | +0.010 |
groom | +0.010 |
ady | +0.010 |
Neg logit contributions | |
sometimes | -0.007 |
maybe | -0.006 |
Sometimes | -0.006 |
then | -0.005 |
dinosaurs | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
sometimes | +0.045 |
for | +0.034 |
maybe | +0.034 |
then | +0.033 |
under | +0.033 |
Neg logit contributions | |
ria | -0.078 |
ING | -0.076 |
oxy | -0.075 |
iya | -0.075 |
groom | -0.074 |
Token | wrapped |
Token ID | 12908 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
sometimes | +0.002 |
Sometimes | +0.002 |
maybe | +0.002 |
dinosaurs | +0.002 |
rob | +0.002 |
Neg logit contributions | |
ria | -0.002 |
ING | -0.002 |
groom | -0.002 |
tap | -0.002 |
slight | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
Sometimes | +0.010 |
sometimes | +0.010 |
dinosaurs | +0.010 |
rob | +0.010 |
maybe | +0.010 |
Neg logit contributions | |
ria | -0.010 |
ING | -0.010 |
tap | -0.010 |
pet | -0.010 |
ater | -0.009 |
Token | around |
Token ID | 1088 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
rob | +0.015 |
dinosaurs | +0.014 |
sometimes | +0.014 |
Sometimes | +0.014 |
maybe | +0.013 |
Neg logit contributions | |
ria | -0.021 |
ING | -0.021 |
copy | -0.020 |
ft | -0.020 |
pet | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
sometimes | +0.028 |
Sometimes | +0.027 |
maybe | +0.026 |
rob | +0.026 |
dinosaurs | +0.026 |
Neg logit contributions | |
ria | -0.019 |
ING | -0.019 |
tap | -0.018 |
groom | -0.017 |
copy | -0.017 |
Token | join |
Token ID | 4654 |
Feature activation | -4.31e-03 |
Pos logit contributions | |
ria | +0.014 |
oing | +0.014 |
oxy | +0.013 |
mber | +0.013 |
ady | +0.013 |
Neg logit contributions | |
sometimes | -0.011 |
then | -0.009 |
Sometimes | -0.009 |
maybe | -0.008 |
Tim | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
sometimes | +0.000 |
Sometimes | +0.000 |
then | +0.000 |
maybe | +0.000 |
dinosaurs | +0.000 |
Neg logit contributions | |
ria | -0.000 |
slight | -0.000 |
ING | -0.000 |
estone | -0.000 |
ower | -0.000 |
Token | water |
Token ID | 1660 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
ria | +0.004 |
ING | +0.003 |
oxy | +0.003 |
ady | +0.003 |
ume | +0.003 |
Neg logit contributions | |
sometimes | -0.004 |
Sometimes | -0.003 |
maybe | -0.003 |
dinosaurs | -0.003 |
then | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ria | +0.016 |
ING | +0.016 |
slight | +0.015 |
Care | +0.015 |
ady | +0.015 |
Neg logit contributions | |
sometimes | -0.013 |
Sometimes | -0.011 |
maybe | -0.011 |
then | -0.011 |
dinosaurs | -0.011 |
Token | It |
Token ID | 632 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
sometimes | +0.005 |
Sometimes | +0.004 |
maybe | +0.004 |
then | +0.004 |
dinosaurs | +0.004 |
Neg logit contributions | |
ria | -0.007 |
ING | -0.007 |
groom | -0.006 |
ume | -0.006 |
slight | -0.006 |
Token | looks |
Token ID | 3073 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
sometimes | +0.004 |
Sometimes | +0.003 |
maybe | +0.003 |
then | +0.003 |
dinosaurs | +0.002 |
Neg logit contributions | |
ria | -0.008 |
iya | -0.007 |
ING | -0.007 |
oxy | -0.007 |
ady | -0.007 |
Token | fun |
Token ID | 1257 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
sometimes | +0.049 |
rob | +0.045 |
Sometimes | +0.045 |
dinosaurs | +0.044 |
maybe | +0.043 |
Neg logit contributions | |
ING | -0.053 |
tap | -0.052 |
ria | -0.051 |
slight | -0.050 |
groom | -0.050 |
Token | ." |
Token ID | 526 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
sometimes | +0.021 |
Sometimes | +0.021 |
maybe | +0.020 |
dinosaurs | +0.019 |
rob | +0.019 |
Neg logit contributions | |
ING | -0.016 |
ria | -0.016 |
tap | -0.015 |
groom | -0.015 |
ater | -0.014 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
ria | +0.036 |
slight | +0.036 |
elcome | +0.036 |
ater | +0.035 |
guardian | +0.035 |
Neg logit contributions | |
sometimes | -0.015 |
Sometimes | -0.014 |
maybe | -0.013 |
then | -0.012 |
Tim | -0.010 |
Token | says |
Token ID | 1139 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ria | +0.008 |
ING | +0.008 |
ume | +0.007 |
slight | +0.007 |
groom | +0.007 |
Neg logit contributions | |
sometimes | -0.004 |
maybe | -0.004 |
Sometimes | -0.004 |
then | -0.004 |
dinosaurs | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ria | +0.022 |
ING | +0.021 |
ady | +0.021 |
groom | +0.021 |
iya | +0.021 |
Neg logit contributions | |
sometimes | -0.012 |
maybe | -0.011 |
Sometimes | -0.010 |
then | -0.010 |
dinosaurs | -0.009 |