Token | Spot |
Token ID | 32565 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ems | +0.022 |
ophone | +0.020 |
ppy | +0.020 |
oke | +0.019 |
ets | +0.019 |
Neg logit contributions | |
it | -0.012 |
sudden | -0.012 |
excitement | -0.011 |
the | -0.011 |
a | -0.011 |
Token | grow |
Token ID | 1663 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ems | +0.046 |
ppy | +0.044 |
arl | +0.043 |
ophone | +0.042 |
wy | +0.040 |
Neg logit contributions | |
it | -0.039 |
excitement | -0.038 |
delight | -0.037 |
an | -0.037 |
the | -0.036 |
Token | ls |
Token ID | 7278 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
ems | +0.145 |
ppy | +0.138 |
ophone | +0.131 |
arl | +0.129 |
wy | +0.124 |
Neg logit contributions | |
it | -0.102 |
excitement | -0.102 |
delight | -0.096 |
an | -0.095 |
Mill | -0.093 |
Token | and |
Token ID | 290 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ems | +0.074 |
ppy | +0.072 |
ophone | +0.068 |
arl | +0.068 |
oke | +0.066 |
Neg logit contributions | |
excitement | -0.032 |
Mill | -0.031 |
it | -0.030 |
delight | -0.030 |
sudden | -0.029 |
Token | sn |
Token ID | 3013 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
ems | +0.032 |
ppy | +0.031 |
ophone | +0.030 |
arl | +0.029 |
oke | +0.029 |
Neg logit contributions | |
excitement | -0.021 |
it | -0.021 |
delight | -0.020 |
an | -0.019 |
the | -0.019 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
it | +0.099 |
top | +0.091 |
the | +0.090 |
a | +0.087 |
her | +0.086 |
Neg logit contributions | |
ems | -0.075 |
ppy | -0.068 |
ophone | -0.062 |
oke | -0.061 |
wy | -0.056 |
Token | s |
Token ID | 82 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ems | +1.057 |
ppy | +1.016 |
ophone | +1.008 |
wy | +0.940 |
oke | +0.912 |
Neg logit contributions | |
it | -0.461 |
excitement | -0.432 |
delight | -0.399 |
the | -0.397 |
top | -0.391 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
ems | +0.028 |
ppy | +0.027 |
ophone | +0.026 |
arl | +0.025 |
oke | +0.024 |
Neg logit contributions | |
excitement | -0.016 |
it | -0.016 |
Mill | -0.015 |
delight | -0.015 |
sudden | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
ems | +0.002 |
ppy | +0.002 |
arl | +0.002 |
ophone | +0.002 |
oke | +0.002 |
Neg logit contributions | |
excitement | -0.001 |
Mill | -0.001 |
it | -0.001 |
delight | -0.001 |
sudden | -0.001 |
Token | tries |
Token ID | 8404 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ems | +0.049 |
ppy | +0.047 |
arl | +0.047 |
ophone | +0.044 |
oke | +0.043 |
Neg logit contributions | |
it | -0.039 |
excitement | -0.037 |
an | -0.037 |
the | -0.037 |
a | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Mill | +0.001 |
excitement | +0.001 |
delight | +0.001 |
Frankie | +0.001 |
sudden | +0.001 |
Neg logit contributions | |
ems | -0.002 |
ppy | -0.002 |
arl | -0.002 |
ophone | -0.002 |
oke | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Frankie | +0.044 |
excitement | +0.043 |
delight | +0.043 |
Mill | +0.042 |
Its | +0.039 |
Neg logit contributions | |
ems | -0.094 |
ppy | -0.091 |
ophone | -0.088 |
arl | -0.085 |
oke | -0.085 |
Token | grow |
Token ID | 1663 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
excitement | +0.024 |
it | +0.023 |
sudden | +0.023 |
Mill | +0.023 |
delight | +0.023 |
Neg logit contributions | |
ems | -0.037 |
ppy | -0.036 |
ophone | -0.033 |
arl | -0.033 |
wy | -0.031 |
Token | l |
Token ID | 75 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
ems | +0.142 |
ppy | +0.136 |
ophone | +0.129 |
arl | +0.128 |
oke | +0.125 |
Neg logit contributions | |
excitement | -0.083 |
Mill | -0.079 |
it | -0.079 |
delight | -0.079 |
sudden | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
excitement | +0.015 |
it | +0.015 |
Mill | +0.014 |
delight | +0.014 |
an | +0.014 |
Neg logit contributions | |
ems | -0.042 |
ppy | -0.040 |
ophone | -0.039 |
arl | -0.039 |
wy | -0.037 |
Token | sn |
Token ID | 3013 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
ems | +0.016 |
ppy | +0.016 |
arl | +0.015 |
ophone | +0.015 |
oke | +0.015 |
Neg logit contributions | |
excitement | -0.008 |
it | -0.008 |
Mill | -0.008 |
delight | -0.008 |
an | -0.007 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
it | +0.117 |
Mill | +0.116 |
sudden | +0.111 |
excitement | +0.110 |
Frankie | +0.109 |
Neg logit contributions | |
ems | -0.078 |
ppy | -0.069 |
ophone | -0.066 |
oke | -0.060 |
wy | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ems | +0.921 |
ppy | +0.876 |
ophone | +0.839 |
arl | +0.827 |
oke | +0.801 |
Neg logit contributions | |
excitement | -0.569 |
it | -0.555 |
Mill | -0.542 |
delight | -0.537 |
sudden | -0.521 |
Token | try |
Token ID | 1949 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
sudden | +0.020 |
excitement | +0.020 |
Frankie | +0.019 |
Mill | +0.019 |
delight | +0.018 |
Neg logit contributions | |
ems | -0.052 |
ppy | -0.050 |
arl | -0.048 |
ophone | -0.046 |
ets | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
excitement | +0.082 |
delight | +0.077 |
sudden | +0.076 |
Frankie | +0.072 |
Mill | +0.072 |
Neg logit contributions | |
ems | -0.209 |
ppy | -0.198 |
ophone | -0.192 |
arl | -0.186 |
oke | -0.182 |
Token | scare |
Token ID | 19437 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
ems | +0.009 |
ppy | +0.009 |
ophone | +0.008 |
arl | +0.008 |
oke | +0.008 |
Neg logit contributions | |
excitement | -0.004 |
it | -0.004 |
Mill | -0.004 |
delight | -0.004 |
sudden | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ems | +0.001 |
ppy | +0.001 |
ophone | +0.001 |
arl | +0.001 |
ets | +0.001 |
Neg logit contributions | |
excitement | -0.000 |
Mill | -0.000 |
sudden | -0.000 |
delight | -0.000 |
Frankie | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
excitement | +0.009 |
Mill | +0.009 |
delight | +0.009 |
sudden | +0.009 |
Frankie | +0.009 |
Neg logit contributions | |
ems | -0.019 |
ppy | -0.019 |
arl | -0.018 |
ophone | -0.018 |
oke | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
ems | +0.044 |
ppy | +0.042 |
arl | +0.041 |
ophone | +0.041 |
oke | +0.040 |
Neg logit contributions | |
excitement | -0.015 |
delight | -0.014 |
Mill | -0.014 |
it | -0.013 |
sudden | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ems | +0.049 |
ppy | +0.047 |
arl | +0.046 |
ophone | +0.045 |
oke | +0.045 |
Neg logit contributions | |
excitement | -0.016 |
Mill | -0.015 |
delight | -0.015 |
it | -0.014 |
Frankie | -0.014 |
Token | Rex |
Token ID | 47389 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ems | +0.038 |
ppy | +0.036 |
ophone | +0.036 |
arl | +0.034 |
wy | +0.034 |
Neg logit contributions | |
it | -0.021 |
excitement | -0.019 |
sudden | -0.019 |
an | -0.019 |
the | -0.019 |
Token | sn |
Token ID | 3013 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
ems | +0.189 |
ppy | +0.182 |
arl | +0.177 |
ophone | +0.173 |
wy | +0.166 |
Neg logit contributions | |
it | -0.155 |
excitement | -0.148 |
an | -0.146 |
the | -0.144 |
a | -0.143 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
it | +0.091 |
the | +0.082 |
its | +0.080 |
top | +0.079 |
her | +0.079 |
Neg logit contributions | |
ems | -0.088 |
ppy | -0.083 |
ophone | -0.076 |
wy | -0.072 |
oke | -0.070 |
Token | s |
Token ID | 82 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ems | +1.136 |
ppy | +1.126 |
ophone | +1.100 |
wy | +1.040 |
ets | +0.981 |
Neg logit contributions | |
it | -0.397 |
top | -0.334 |
the | -0.328 |
excitement | -0.325 |
new | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ems | +0.028 |
ppy | +0.026 |
ophone | +0.025 |
arl | +0.024 |
oke | +0.024 |
Neg logit contributions | |
it | -0.016 |
excitement | -0.016 |
an | -0.015 |
delight | -0.015 |
Mill | -0.014 |
Token | He |
Token ID | 679 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
ems | +0.020 |
ppy | +0.020 |
ophone | +0.019 |
wy | +0.019 |
pp | +0.019 |
Neg logit contributions | |
it | -0.005 |
excitement | -0.004 |
an | -0.004 |
Its | -0.004 |
a | -0.004 |
Token | does |
Token ID | 857 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ems | +0.065 |
ppy | +0.065 |
arl | +0.062 |
ophone | +0.060 |
wy | +0.057 |
Neg logit contributions | |
it | -0.050 |
the | -0.047 |
an | -0.046 |
excitement | -0.046 |
a | -0.046 |
Token | not |
Token ID | 407 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
ems | +0.020 |
ppy | +0.020 |
ophone | +0.019 |
arl | +0.018 |
oke | +0.018 |
Neg logit contributions | |
it | -0.008 |
excitement | -0.008 |
an | -0.007 |
delight | -0.007 |
a | -0.007 |
Token | disappointment |
Token ID | 18641 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
arl | +0.006 |
ems | +0.006 |
ppy | +0.006 |
ets | +0.005 |
wy | +0.005 |
Neg logit contributions | |
Mill | -0.002 |
sudden | -0.002 |
Frankie | -0.002 |
Its | -0.002 |
Mill | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -5.19e-03 |
Pos logit contributions | |
excitement | +0.065 |
it | +0.062 |
Mill | +0.060 |
delight | +0.060 |
sudden | +0.057 |
Neg logit contributions | |
ems | -0.185 |
ppy | -0.178 |
ophone | -0.171 |
arl | -0.170 |
oke | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
excitement | +0.000 |
sudden | +0.000 |
it | +0.000 |
delight | +0.000 |
sight | +0.000 |
Neg logit contributions | |
ems | -0.001 |
ppy | -0.001 |
arl | -0.001 |
oke | -0.001 |
ophone | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
excitement | +0.012 |
delight | +0.011 |
Mill | +0.011 |
sight | +0.011 |
it | +0.010 |
Neg logit contributions | |
ems | -0.028 |
ppy | -0.028 |
arl | -0.027 |
ophone | -0.026 |
oke | -0.026 |
Token | M |
Token ID | 44 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
excitement | +0.013 |
it | +0.012 |
Mill | +0.012 |
delight | +0.012 |
sight | +0.012 |
Neg logit contributions | |
ems | -0.026 |
ppy | -0.025 |
arl | -0.024 |
ophone | -0.024 |
oke | -0.023 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
ems | +0.078 |
ppy | +0.075 |
arl | +0.071 |
ophone | +0.071 |
oke | +0.070 |
Neg logit contributions | |
excitement | -0.037 |
it | -0.036 |
Mill | -0.035 |
delight | -0.034 |
sudden | -0.033 |
Token | on |
Token ID | 261 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
ems | +0.715 |
ppy | +0.670 |
arl | +0.628 |
ophone | +0.628 |
oke | +0.602 |
Neg logit contributions | |
excitement | -0.768 |
it | -0.747 |
Mill | -0.741 |
delight | -0.736 |
sudden | -0.720 |
Token | 's |
Token ID | 338 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
ems | +0.055 |
ppy | +0.052 |
arl | +0.050 |
ophone | +0.050 |
oke | +0.048 |
Neg logit contributions | |
excitement | -0.036 |
it | -0.035 |
Mill | -0.034 |
delight | -0.034 |
sudden | -0.033 |
Token | mum |
Token ID | 25682 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Mill | +0.028 |
Frankie | +0.026 |
it | +0.025 |
excitement | +0.024 |
Its | +0.023 |
Neg logit contributions | |
ppy | -0.081 |
ems | -0.080 |
ophone | -0.076 |
arl | -0.076 |
wy | -0.073 |
Token | hugged |
Token ID | 41130 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
excitement | +0.039 |
it | +0.037 |
Mill | +0.037 |
delight | +0.037 |
sudden | +0.036 |
Neg logit contributions | |
ems | -0.051 |
ppy | -0.050 |
ophone | -0.046 |
oke | -0.045 |
arl | -0.045 |
Token | him |
Token ID | 683 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
ppy | +0.051 |
ems | +0.051 |
arl | +0.048 |
oke | +0.045 |
wy | +0.045 |
Neg logit contributions | |
sudden | -0.015 |
excitement | -0.013 |
delight | -0.012 |
sight | -0.012 |
Mill | -0.011 |
Token | forgive |
Token ID | 20927 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
ems | +0.051 |
ppy | +0.050 |
ophone | +0.049 |
arl | +0.049 |
ider | +0.048 |
Neg logit contributions | |
it | -0.035 |
a | -0.033 |
an | -0.032 |
excitement | -0.031 |
delight | -0.030 |
Token | you |
Token ID | 345 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ems | +0.127 |
ppy | +0.121 |
ophone | +0.111 |
arl | +0.111 |
oke | +0.109 |
Neg logit contributions | |
excitement | -0.074 |
delight | -0.069 |
Mill | -0.069 |
sudden | -0.068 |
Frankie | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
excitement | +0.009 |
Mill | +0.009 |
sudden | +0.008 |
it | +0.008 |
delight | +0.008 |
Neg logit contributions | |
ems | -0.020 |
ppy | -0.020 |
ophone | -0.018 |
arl | -0.018 |
oke | -0.018 |
Token | my |
Token ID | 616 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
excitement | +0.017 |
it | +0.016 |
Mill | +0.016 |
delight | +0.015 |
sudden | +0.015 |
Neg logit contributions | |
ems | -0.039 |
ppy | -0.037 |
ophone | -0.035 |
arl | -0.035 |
oke | -0.034 |
Token | d |
Token ID | 288 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
ems | +0.069 |
ppy | +0.066 |
ophone | +0.063 |
arl | +0.062 |
wy | +0.061 |
Neg logit contributions | |
excitement | -0.042 |
it | -0.041 |
delight | -0.040 |
Mill | -0.040 |
an | -0.039 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
Mill | +0.004 |
Its | +0.004 |
it | +0.004 |
excitement | +0.004 |
delight | +0.004 |
Neg logit contributions | |
ems | -0.001 |
ophone | -0.001 |
ppy | -0.001 |
wy | -0.001 |
osaurs | -0.000 |
Token | ings |
Token ID | 654 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
ems | +1.191 |
ppy | +1.190 |
ophone | +1.177 |
wy | +1.111 |
oke | +1.076 |
Neg logit contributions | |
it | -0.285 |
excitement | -0.249 |
top | -0.220 |
delight | -0.218 |
sight | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
it | +0.060 |
excitement | +0.056 |
Mill | +0.055 |
an | +0.051 |
delight | +0.051 |
Neg logit contributions | |
ems | -0.176 |
ppy | -0.168 |
ophone | -0.165 |
arl | -0.161 |
wy | -0.158 |
Token | And |
Token ID | 843 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
Mill | +0.009 |
it | +0.009 |
Its | +0.009 |
excitement | +0.008 |
delight | +0.008 |
Neg logit contributions | |
ems | -0.018 |
ppy | -0.018 |
wy | -0.018 |
ophone | -0.017 |
oke | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
ems | +0.123 |
ppy | +0.119 |
ophone | +0.115 |
arl | +0.115 |
wy | +0.113 |
Neg logit contributions | |
it | -0.065 |
excitement | -0.061 |
delight | -0.058 |
Mill | -0.058 |
an | -0.057 |
Token | course |
Token ID | 1781 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
excitement | +0.007 |
it | +0.007 |
Mill | +0.007 |
delight | +0.007 |
sudden | +0.006 |
Neg logit contributions | |
ems | -0.015 |
ppy | -0.015 |
ophone | -0.014 |
arl | -0.014 |
oke | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
it | +0.020 |
excitement | +0.020 |
Mill | +0.019 |
delight | +0.019 |
an | +0.018 |
Neg logit contributions | |
ems | -0.043 |
ppy | -0.041 |
arl | -0.039 |
ophone | -0.039 |
wy | -0.038 |
Token | okay |
Token ID | 8788 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
excitement | +0.029 |
it | +0.028 |
Mill | +0.027 |
an | +0.027 |
delight | +0.026 |
Neg logit contributions | |
ems | -0.058 |
ppy | -0.055 |
ophone | -0.053 |
arl | -0.052 |
oke | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ems | +0.067 |
ppy | +0.065 |
arl | +0.061 |
ophone | +0.061 |
oke | +0.059 |
Neg logit contributions | |
excitement | -0.031 |
delight | -0.030 |
sudden | -0.029 |
Mill | -0.028 |
Frankie | -0.027 |
Token | my |
Token ID | 616 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
excitement | +0.017 |
it | +0.017 |
Mill | +0.016 |
delight | +0.016 |
sudden | +0.016 |
Neg logit contributions | |
ems | -0.034 |
ppy | -0.032 |
ophone | -0.031 |
arl | -0.031 |
oke | -0.030 |
Token | d |
Token ID | 288 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
ems | +0.047 |
ppy | +0.045 |
ophone | +0.043 |
wy | +0.042 |
arl | +0.042 |
Neg logit contributions | |
excitement | -0.030 |
it | -0.030 |
delight | -0.029 |
Mill | -0.028 |
an | -0.028 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.23e+00 |
Pos logit contributions | |
an | +0.014 |
eyes | +0.014 |
Its | +0.014 |
top | +0.014 |
Mill | +0.014 |
Neg logit contributions | |
ems | -0.004 |
ophone | -0.003 |
wy | -0.003 |
ppy | -0.002 |
osaurs | -0.002 |
Token | ings |
Token ID | 654 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ems | +1.195 |
ppy | +1.186 |
ophone | +1.172 |
wy | +1.108 |
oke | +1.070 |
Neg logit contributions | |
it | -0.285 |
excitement | -0.247 |
top | -0.230 |
sight | -0.219 |
delight | -0.216 |
Token | . |
Token ID | 13 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
it | +0.046 |
the | +0.037 |
a | +0.037 |
an | +0.035 |
her | +0.034 |
Neg logit contributions | |
ems | -0.202 |
ophone | -0.192 |
ppy | -0.191 |
wy | -0.186 |
arl | -0.182 |
Token | I |
Token ID | 314 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
it | +0.003 |
excitement | +0.003 |
Mill | +0.003 |
an | +0.003 |
delight | +0.003 |
Neg logit contributions | |
ems | -0.007 |
ppy | -0.007 |
wy | -0.007 |
ophone | -0.006 |
oke | -0.006 |
Token | forgive |
Token ID | 20927 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
ems | +0.042 |
arl | +0.042 |
ppy | +0.040 |
wy | +0.039 |
ophone | +0.039 |
Neg logit contributions | |
it | -0.026 |
a | -0.024 |
an | -0.024 |
excitement | -0.023 |
the | -0.022 |
Token | you |
Token ID | 345 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ems | +0.131 |
ppy | +0.125 |
ophone | +0.118 |
arl | +0.118 |
oke | +0.114 |
Neg logit contributions | |
excitement | -0.069 |
Mill | -0.065 |
delight | -0.064 |
it | -0.063 |
sudden | -0.063 |
Token | you |
Token ID | 345 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
excitement | +0.012 |
Mill | +0.011 |
delight | +0.011 |
sudden | +0.011 |
Frankie | +0.010 |
Neg logit contributions | |
ems | -0.051 |
ppy | -0.050 |
ophone | -0.048 |
oke | -0.047 |
arl | -0.046 |
Token | go |
Token ID | 467 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
it | +0.019 |
excitement | +0.018 |
an | +0.017 |
delight | +0.017 |
Mill | +0.017 |
Neg logit contributions | |
ems | -0.029 |
ppy | -0.028 |
arl | -0.027 |
ophone | -0.027 |
wy | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ems | +0.008 |
ppy | +0.008 |
ophone | +0.008 |
arl | +0.008 |
oke | +0.008 |
Neg logit contributions | |
it | -0.003 |
excitement | -0.003 |
Mill | -0.002 |
an | -0.002 |
delight | -0.002 |
Token | my |
Token ID | 616 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
excitement | +0.033 |
it | +0.032 |
Mill | +0.031 |
delight | +0.031 |
sudden | +0.030 |
Neg logit contributions | |
ems | -0.066 |
ppy | -0.063 |
ophone | -0.061 |
arl | -0.060 |
oke | -0.058 |
Token | d |
Token ID | 288 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ems | +0.097 |
ppy | +0.093 |
ophone | +0.089 |
arl | +0.088 |
wy | +0.086 |
Neg logit contributions | |
excitement | -0.042 |
it | -0.041 |
delight | -0.039 |
Mill | -0.039 |
sudden | -0.037 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
ems | +0.015 |
ophone | +0.012 |
ppy | +0.012 |
wy | +0.012 |
osaurs | +0.011 |
Neg logit contributions | |
an | -0.036 |
it | -0.036 |
excitement | -0.035 |
delight | -0.035 |
a | -0.035 |
Token | ings |
Token ID | 654 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ems | +1.041 |
ppy | +1.028 |
ophone | +1.006 |
wy | +0.945 |
oke | +0.920 |
Neg logit contributions | |
it | -0.436 |
excitement | -0.397 |
top | -0.384 |
delight | -0.371 |
sight | -0.365 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
it | +0.094 |
an | +0.084 |
a | +0.083 |
the | +0.083 |
Mill | +0.080 |
Neg logit contributions | |
ems | -0.183 |
ppy | -0.179 |
ophone | -0.171 |
arl | -0.169 |
wy | -0.167 |
Token | Enjoy |
Token ID | 18179 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
it | +0.010 |
excitement | +0.010 |
Mill | +0.010 |
delight | +0.010 |
an | +0.010 |
Neg logit contributions | |
ems | -0.019 |
ppy | -0.019 |
wy | -0.018 |
ophone | -0.018 |
arl | -0.018 |
Token | your |
Token ID | 534 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
ems | +0.188 |
ppy | +0.182 |
ophone | +0.182 |
oke | +0.174 |
arl | +0.172 |
Neg logit contributions | |
it | -0.070 |
excitement | -0.060 |
the | -0.059 |
her | -0.056 |
delight | -0.056 |
Token | lunch |
Token ID | 9965 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ems | +0.096 |
ppy | +0.091 |
arl | +0.089 |
ophone | +0.088 |
wy | +0.085 |
Neg logit contributions | |
Mill | -0.039 |
excitement | -0.038 |
it | -0.037 |
Frankie | -0.036 |
delight | -0.036 |
Token | 'm |
Token ID | 1101 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
ems | +0.005 |
arl | +0.005 |
ppy | +0.005 |
ophone | +0.005 |
wy | +0.005 |
Neg logit contributions | |
it | -0.003 |
an | -0.002 |
a | -0.002 |
excitement | -0.002 |
Mill | -0.002 |
Token | sorry |
Token ID | 7926 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ems | +0.125 |
ppy | +0.122 |
arl | +0.116 |
ophone | +0.116 |
oke | +0.113 |
Neg logit contributions | |
excitement | -0.104 |
sudden | -0.100 |
delight | -0.099 |
Mill | -0.098 |
it | -0.096 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ems | +0.199 |
ppy | +0.194 |
arl | +0.180 |
oke | +0.179 |
ophone | +0.169 |
Neg logit contributions | |
excitement | -0.129 |
sudden | -0.123 |
delight | -0.121 |
sight | -0.112 |
Mill | -0.110 |
Token | my |
Token ID | 616 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
excitement | +0.014 |
it | +0.013 |
Mill | +0.013 |
delight | +0.013 |
sudden | +0.012 |
Neg logit contributions | |
ems | -0.028 |
ppy | -0.027 |
ophone | -0.026 |
arl | -0.026 |
oke | -0.025 |
Token | d |
Token ID | 288 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
ems | +0.046 |
ppy | +0.043 |
ophone | +0.040 |
arl | +0.040 |
wy | +0.039 |
Neg logit contributions | |
excitement | -0.045 |
it | -0.044 |
Mill | -0.043 |
delight | -0.043 |
an | -0.042 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
Mill | +0.014 |
it | +0.014 |
excitement | +0.014 |
Its | +0.013 |
an | +0.013 |
Neg logit contributions | |
ems | -0.003 |
ophone | -0.002 |
ppy | -0.002 |
wy | -0.002 |
osaurs | -0.001 |
Token | ings |
Token ID | 654 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ems | +1.160 |
ppy | +1.126 |
ophone | +1.111 |
wy | +1.050 |
oke | +1.031 |
Neg logit contributions | |
it | -0.323 |
excitement | -0.303 |
delight | -0.271 |
Mill | -0.267 |
Frankie | -0.259 |
Token | . |
Token ID | 13 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
it | +0.050 |
the | +0.042 |
excitement | +0.041 |
a | +0.040 |
Mill | +0.040 |
Neg logit contributions | |
ems | -0.196 |
ophone | -0.187 |
ppy | -0.186 |
wy | -0.178 |
arl | -0.178 |
Token | The |
Token ID | 383 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
it | +0.007 |
excitement | +0.007 |
Mill | +0.007 |
delight | +0.007 |
Frankie | +0.007 |
Neg logit contributions | |
ems | -0.015 |
ppy | -0.014 |
ophone | -0.014 |
arl | -0.013 |
wy | -0.013 |
Token | tornado |
Token ID | 33718 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
excitement | +0.028 |
it | +0.027 |
Mill | +0.027 |
delight | +0.026 |
sudden | +0.025 |
Neg logit contributions | |
ems | -0.056 |
ppy | -0.053 |
ophone | -0.051 |
arl | -0.051 |
oke | -0.049 |
Token | took |
Token ID | 1718 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ems | +0.080 |
ppy | +0.076 |
arl | +0.074 |
ophone | +0.072 |
wy | +0.070 |
Neg logit contributions | |
it | -0.057 |
excitement | -0.056 |
Mill | -0.053 |
delight | -0.053 |
an | -0.052 |
Token | you |
Token ID | 345 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
excitement | +0.112 |
sudden | +0.110 |
delight | +0.109 |
top | +0.100 |
Its | +0.100 |
Neg logit contributions | |
ems | -0.095 |
ppy | -0.087 |
arl | -0.083 |
oke | -0.076 |
ll | -0.076 |
Token | too |
Token ID | 1165 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
excitement | +0.016 |
Mill | +0.015 |
it | +0.015 |
delight | +0.015 |
sudden | +0.014 |
Neg logit contributions | |
ems | -0.034 |
ppy | -0.033 |
arl | -0.031 |
ophone | -0.031 |
wy | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ems | +0.121 |
ppy | +0.117 |
arl | +0.114 |
oke | +0.110 |
ophone | +0.109 |
Neg logit contributions | |
excitement | -0.059 |
it | -0.058 |
Mill | -0.056 |
delight | -0.056 |
sudden | -0.055 |
Token | my |
Token ID | 616 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
excitement | +0.018 |
sudden | +0.018 |
Mill | +0.017 |
it | +0.017 |
Frankie | +0.017 |
Neg logit contributions | |
ems | -0.044 |
ppy | -0.042 |
arl | -0.040 |
oke | -0.039 |
ophone | -0.039 |
Token | d |
Token ID | 288 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ems | +0.051 |
ppy | +0.049 |
ophone | +0.047 |
arl | +0.046 |
wy | +0.045 |
Neg logit contributions | |
excitement | -0.023 |
it | -0.023 |
delight | -0.021 |
Mill | -0.021 |
an | -0.021 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
Mill | +0.021 |
it | +0.021 |
Its | +0.020 |
an | +0.020 |
excitement | +0.020 |
Neg logit contributions | |
ems | -0.005 |
ophone | -0.003 |
ppy | -0.003 |
wy | -0.003 |
osaurs | -0.002 |
Token | ings |
Token ID | 654 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ems | +1.155 |
ppy | +1.141 |
ophone | +1.125 |
wy | +1.059 |
oke | +1.023 |
Neg logit contributions | |
it | -0.321 |
excitement | -0.298 |
delight | -0.259 |
sight | -0.255 |
Frankie | -0.250 |
Token | ," |
Token ID | 553 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
it | +0.077 |
excitement | +0.073 |
Mill | +0.071 |
an | +0.067 |
delight | +0.067 |
Neg logit contributions | |
ems | -0.187 |
ppy | -0.178 |
ophone | -0.176 |
arl | -0.169 |
wy | -0.166 |
Token | she |
Token ID | 673 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
excitement | +0.061 |
sudden | +0.060 |
sight | +0.058 |
delight | +0.058 |
Frankie | +0.057 |
Neg logit contributions | |
ems | -0.100 |
ppy | -0.095 |
oke | -0.092 |
arl | -0.090 |
ophone | -0.087 |
Token | said |
Token ID | 531 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
it | +0.022 |
excitement | +0.022 |
a | +0.021 |
delight | +0.020 |
an | +0.020 |
Neg logit contributions | |
ems | -0.043 |
arl | -0.042 |
ppy | -0.040 |
ophone | -0.040 |
wy | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ppy | +0.027 |
ems | +0.026 |
arl | +0.025 |
ophone | +0.024 |
oke | +0.024 |
Neg logit contributions | |
excitement | -0.015 |
sudden | -0.015 |
delight | -0.015 |
Mill | -0.014 |
sight | -0.014 |
Token | you |
Token ID | 345 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
excitement | +0.098 |
delight | +0.092 |
Frankie | +0.092 |
Mill | +0.090 |
sudden | +0.088 |
Neg logit contributions | |
ems | -0.102 |
ppy | -0.098 |
arl | -0.092 |
wy | -0.088 |
oke | -0.085 |
Token | too |
Token ID | 1165 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
excitement | +0.009 |
it | +0.009 |
Mill | +0.008 |
delight | +0.008 |
sudden | +0.008 |
Neg logit contributions | |
ems | -0.021 |
ppy | -0.020 |
ophone | -0.019 |
arl | -0.019 |
oke | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ems | +0.142 |
ppy | +0.137 |
arl | +0.132 |
ophone | +0.130 |
oke | +0.129 |
Neg logit contributions | |
excitement | -0.060 |
it | -0.058 |
Mill | -0.057 |
delight | -0.056 |
sudden | -0.054 |
Token | my |
Token ID | 616 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
excitement | +0.017 |
it | +0.017 |
Mill | +0.017 |
delight | +0.016 |
sudden | +0.016 |
Neg logit contributions | |
ems | -0.037 |
ppy | -0.035 |
arl | -0.034 |
ophone | -0.034 |
oke | -0.033 |
Token | d |
Token ID | 288 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
ems | +0.072 |
ppy | +0.069 |
ophone | +0.066 |
arl | +0.065 |
oke | +0.064 |
Neg logit contributions | |
excitement | -0.034 |
it | -0.032 |
Mill | -0.032 |
delight | -0.031 |
sudden | -0.031 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
Mill | +0.005 |
it | +0.005 |
excitement | +0.005 |
delight | +0.005 |
Its | +0.005 |
Neg logit contributions | |
ems | -0.002 |
ophone | -0.001 |
ppy | -0.001 |
osaurs | -0.001 |
wy | -0.001 |
Token | ings |
Token ID | 654 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ems | +1.146 |
ppy | +1.122 |
ophone | +1.113 |
wy | +1.044 |
oke | +1.024 |
Neg logit contributions | |
it | -0.330 |
excitement | -0.310 |
delight | -0.278 |
Mill | -0.266 |
top | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
it | +0.051 |
the | +0.043 |
a | +0.043 |
her | +0.042 |
Mill | +0.040 |
Neg logit contributions | |
ems | -0.191 |
ophone | -0.184 |
ppy | -0.184 |
wy | -0.175 |
arl | -0.174 |
Token | Now |
Token ID | 2735 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
it | +0.000 |
excitement | +0.000 |
Mill | +0.000 |
delight | +0.000 |
an | +0.000 |
Neg logit contributions | |
ems | -0.001 |
ppy | -0.001 |
ophone | -0.001 |
wy | -0.001 |
oke | -0.001 |
Token | let |
Token ID | 1309 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ems | +0.141 |
ppy | +0.135 |
ophone | +0.129 |
arl | +0.128 |
oke | +0.125 |
Neg logit contributions | |
excitement | -0.063 |
it | -0.060 |
Mill | -0.059 |
delight | -0.058 |
sudden | -0.057 |
Token | 's |
Token ID | 338 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ems | +0.093 |
ppy | +0.091 |
ophone | +0.084 |
oke | +0.082 |
arl | +0.081 |
Neg logit contributions | |
excitement | -0.058 |
sudden | -0.055 |
Mill | -0.054 |
delight | -0.053 |
Frankie | -0.052 |
Token | 'm |
Token ID | 1101 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
it | +0.003 |
excitement | +0.003 |
an | +0.003 |
Mill | +0.003 |
a | +0.003 |
Neg logit contributions | |
ems | -0.005 |
ppy | -0.005 |
ophone | -0.005 |
arl | -0.005 |
wy | -0.005 |
Token | sorry |
Token ID | 7926 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ems | +0.105 |
ppy | +0.101 |
arl | +0.098 |
ophone | +0.095 |
oke | +0.093 |
Neg logit contributions | |
excitement | -0.103 |
delight | -0.099 |
Mill | -0.098 |
sudden | -0.097 |
it | -0.096 |
Token | , |
Token ID | 11 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
ems | +0.188 |
ppy | +0.182 |
arl | +0.175 |
oke | +0.171 |
ophone | +0.163 |
Neg logit contributions | |
excitement | -0.122 |
sudden | -0.114 |
delight | -0.113 |
Frankie | -0.107 |
Mill | -0.104 |
Token | my |
Token ID | 616 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
excitement | +0.025 |
Mill | +0.024 |
sudden | +0.024 |
delight | +0.023 |
Frankie | +0.023 |
Neg logit contributions | |
ems | -0.041 |
ppy | -0.038 |
arl | -0.037 |
oke | -0.036 |
ophone | -0.036 |
Token | d |
Token ID | 288 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
ems | +0.047 |
ppy | +0.044 |
ophone | +0.042 |
arl | +0.041 |
wy | +0.040 |
Neg logit contributions | |
excitement | -0.045 |
it | -0.044 |
Mill | -0.043 |
delight | -0.043 |
sudden | -0.042 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
Mill | +0.009 |
it | +0.009 |
Its | +0.009 |
an | +0.009 |
Frankie | +0.009 |
Neg logit contributions | |
ems | -0.002 |
ophone | -0.002 |
ppy | -0.001 |
osaurs | -0.001 |
wy | -0.001 |
Token | ings |
Token ID | 654 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ems | +1.177 |
ppy | +1.158 |
ophone | +1.140 |
wy | +1.082 |
ets | +1.037 |
Neg logit contributions | |
it | -0.297 |
excitement | -0.266 |
top | -0.235 |
delight | -0.234 |
Mill | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
it | +0.049 |
the | +0.042 |
a | +0.037 |
her | +0.037 |
an | +0.034 |
Neg logit contributions | |
ems | -0.211 |
ophone | -0.204 |
ppy | -0.201 |
wy | -0.195 |
arl | -0.188 |
Token | That |
Token ID | 1320 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
it | +0.016 |
Mill | +0.016 |
excitement | +0.015 |
an | +0.015 |
Frankie | +0.015 |
Neg logit contributions | |
ems | -0.037 |
ppy | -0.036 |
ophone | -0.035 |
wy | -0.034 |
arl | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
excitement | +0.024 |
delight | +0.024 |
Mill | +0.023 |
sudden | +0.023 |
Frankie | +0.021 |
Neg logit contributions | |
ems | -0.033 |
ophone | -0.031 |
ppy | -0.030 |
oke | -0.028 |
wy | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
it | +0.008 |
excitement | +0.008 |
Mill | +0.007 |
an | +0.007 |
delight | +0.007 |
Neg logit contributions | |
ems | -0.038 |
ppy | -0.037 |
ophone | -0.036 |
arl | -0.036 |
oke | -0.035 |
Token | your |
Token ID | 534 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
ems | +0.132 |
ppy | +0.126 |
ophone | +0.121 |
arl | +0.119 |
wy | +0.116 |
Neg logit contributions | |
excitement | -0.054 |
delight | -0.051 |
sudden | -0.051 |
it | -0.050 |
Mill | -0.050 |
Token | fault |
Token ID | 8046 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
ems | +0.065 |
arl | +0.061 |
ppy | +0.060 |
ophone | +0.060 |
oke | +0.056 |
Neg logit contributions | |
excitement | -0.045 |
sudden | -0.044 |
Mill | -0.043 |
delight | -0.043 |
it | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
excitement | +0.040 |
delight | +0.038 |
Mill | +0.037 |
sudden | +0.037 |
it | +0.037 |
Neg logit contributions | |
ems | -0.071 |
ppy | -0.069 |
arl | -0.065 |
ophone | -0.064 |
oke | -0.064 |
Token | my |
Token ID | 616 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
excitement | +0.014 |
Mill | +0.013 |
it | +0.013 |
delight | +0.013 |
sudden | +0.013 |
Neg logit contributions | |
ems | -0.030 |
ppy | -0.029 |
ophone | -0.027 |
arl | -0.027 |
oke | -0.027 |
Token | d |
Token ID | 288 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ems | +0.053 |
ppy | +0.050 |
arl | +0.049 |
ophone | +0.048 |
oke | +0.048 |
Neg logit contributions | |
excitement | -0.032 |
delight | -0.030 |
it | -0.030 |
Mill | -0.030 |
sudden | -0.029 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
Mill | +0.020 |
it | +0.020 |
excitement | +0.020 |
Frankie | +0.020 |
delight | +0.020 |
Neg logit contributions | |
ems | -0.004 |
ophone | -0.002 |
ppy | -0.002 |
wy | -0.002 |
osaurs | -0.001 |
Token | ings |
Token ID | 654 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ems | +1.125 |
ppy | +1.100 |
ophone | +1.081 |
wy | +1.015 |
oke | +1.000 |
Neg logit contributions | |
it | -0.344 |
excitement | -0.326 |
delight | -0.294 |
Mill | -0.291 |
Frankie | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
it | +0.067 |
excitement | +0.058 |
Mill | +0.058 |
the | +0.057 |
an | +0.056 |
Neg logit contributions | |
ems | -0.186 |
ppy | -0.178 |
ophone | -0.178 |
arl | -0.169 |
wy | -0.168 |
Token | You |
Token ID | 921 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
it | +0.005 |
excitement | +0.005 |
Mill | +0.005 |
delight | +0.005 |
Frankie | +0.004 |
Neg logit contributions | |
ems | -0.011 |
ppy | -0.010 |
ophone | -0.010 |
arl | -0.010 |
wy | -0.010 |
Token | didn |
Token ID | 1422 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
it | +0.013 |
excitement | +0.013 |
an | +0.012 |
Mill | +0.012 |
a | +0.012 |
Neg logit contributions | |
ems | -0.019 |
arl | -0.018 |
ppy | -0.018 |
ophone | -0.017 |
oke | -0.017 |
Token | 't |
Token ID | 470 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
excitement | +0.051 |
delight | +0.048 |
sudden | +0.047 |
Mill | +0.046 |
sight | +0.045 |
Neg logit contributions | |
ems | -0.057 |
ppy | -0.056 |
ophone | -0.055 |
arl | -0.055 |
oke | -0.053 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ems | +0.023 |
ppy | +0.022 |
ophone | +0.022 |
arl | +0.022 |
wy | +0.021 |
Neg logit contributions | |
it | -0.012 |
an | -0.011 |
Mill | -0.011 |
excitement | -0.011 |
a | -0.010 |
Token | sorry |
Token ID | 7926 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ems | +0.128 |
ppy | +0.124 |
arl | +0.118 |
ophone | +0.115 |
oke | +0.112 |
Neg logit contributions | |
excitement | -0.112 |
delight | -0.107 |
Mill | -0.106 |
it | -0.105 |
sudden | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ems | +0.203 |
ppy | +0.196 |
arl | +0.184 |
oke | +0.182 |
ophone | +0.172 |
Neg logit contributions | |
excitement | -0.131 |
sudden | -0.124 |
delight | -0.122 |
Mill | -0.113 |
Frankie | -0.112 |
Token | my |
Token ID | 616 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
excitement | +0.009 |
it | +0.009 |
Mill | +0.009 |
delight | +0.009 |
sudden | +0.008 |
Neg logit contributions | |
ems | -0.026 |
ppy | -0.025 |
arl | -0.024 |
ophone | -0.024 |
oke | -0.024 |
Token | d |
Token ID | 288 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
ems | +0.062 |
ppy | +0.059 |
ophone | +0.057 |
arl | +0.056 |
oke | +0.055 |
Neg logit contributions | |
excitement | -0.035 |
it | -0.034 |
Mill | -0.034 |
delight | -0.033 |
sudden | -0.032 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
it | +0.005 |
Mill | +0.005 |
an | +0.005 |
excitement | +0.005 |
Its | +0.005 |
Neg logit contributions | |
ems | -0.001 |
ophone | -0.001 |
ppy | -0.001 |
wy | -0.001 |
osaurs | -0.001 |
Token | ings |
Token ID | 654 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ems | +1.158 |
ppy | +1.129 |
ophone | +1.122 |
wy | +1.055 |
oke | +1.029 |
Neg logit contributions | |
it | -0.322 |
excitement | -0.295 |
delight | -0.264 |
top | -0.254 |
Mill | -0.254 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
it | +0.057 |
excitement | +0.051 |
Mill | +0.050 |
an | +0.047 |
the | +0.047 |
Neg logit contributions | |
ems | -0.182 |
ppy | -0.173 |
ophone | -0.173 |
arl | -0.165 |
wy | -0.163 |
Token | That |
Token ID | 1320 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ems | +0.020 |
ppy | +0.020 |
ophone | +0.019 |
wy | +0.019 |
arl | +0.019 |
Neg logit contributions | |
it | -0.006 |
excitement | -0.006 |
Mill | -0.006 |
delight | -0.006 |
an | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
excitement | +0.010 |
delight | +0.010 |
Mill | +0.010 |
sudden | +0.009 |
Frankie | +0.009 |
Neg logit contributions | |
ems | -0.019 |
ppy | -0.017 |
ophone | -0.017 |
oke | -0.016 |
wy | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
it | +0.006 |
excitement | +0.006 |
an | +0.005 |
Mill | +0.005 |
delight | +0.005 |
Neg logit contributions | |
ems | -0.021 |
ppy | -0.020 |
arl | -0.020 |
ophone | -0.020 |
oke | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
excitement | +0.048 |
Mill | +0.046 |
sudden | +0.046 |
delight | +0.045 |
Frankie | +0.043 |
Neg logit contributions | |
ems | -0.066 |
ppy | -0.061 |
ophone | -0.060 |
oke | -0.056 |
wy | -0.056 |
Token | wonderful |
Token ID | 7932 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
excitement | +0.024 |
delight | +0.023 |
sudden | +0.022 |
Mill | +0.022 |
it | +0.021 |
Neg logit contributions | |
ems | -0.052 |
ppy | -0.051 |
arl | -0.049 |
ophone | -0.048 |
wy | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
sudden | +0.058 |
excitement | +0.057 |
delight | +0.054 |
Its | +0.053 |
top | +0.051 |
Neg logit contributions | |
ems | -0.093 |
ppy | -0.086 |
arl | -0.082 |
oke | -0.082 |
ets | -0.079 |
Token | my |
Token ID | 616 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
ems | +0.006 |
ppy | +0.006 |
oke | +0.006 |
arl | +0.006 |
ophone | +0.005 |
Neg logit contributions | |
sudden | -0.003 |
excitement | -0.003 |
Mill | -0.003 |
delight | -0.003 |
Frankie | -0.002 |
Token | d |
Token ID | 288 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ems | +0.096 |
ppy | +0.092 |
ophone | +0.088 |
arl | +0.088 |
oke | +0.086 |
Neg logit contributions | |
excitement | -0.042 |
Mill | -0.041 |
it | -0.040 |
Frankie | -0.039 |
delight | -0.038 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
ems | +0.018 |
ophone | +0.015 |
ppy | +0.015 |
wy | +0.014 |
osaurs | +0.013 |
Neg logit contributions | |
Mill | -0.035 |
it | -0.034 |
excitement | -0.034 |
an | -0.034 |
delight | -0.034 |
Token | ings |
Token ID | 654 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ems | +1.098 |
ppy | +1.089 |
ophone | +1.060 |
wy | +0.999 |
oke | +0.983 |
Neg logit contributions | |
it | -0.360 |
excitement | -0.330 |
delight | -0.302 |
top | -0.289 |
Mill | -0.286 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
it | +0.082 |
excitement | +0.075 |
Mill | +0.075 |
an | +0.073 |
the | +0.072 |
Neg logit contributions | |
ems | -0.182 |
ppy | -0.176 |
ophone | -0.171 |
arl | -0.166 |
wy | -0.163 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ems | +0.056 |
ppy | +0.053 |
ophone | +0.051 |
arl | +0.050 |
oke | +0.050 |
Neg logit contributions | |
excitement | -0.031 |
delight | -0.029 |
sudden | -0.029 |
Mill | -0.029 |
it | -0.028 |
Token | my |
Token ID | 1820 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
it | +0.021 |
excitement | +0.020 |
Mill | +0.020 |
delight | +0.019 |
the | +0.019 |
Neg logit contributions | |
ems | -0.026 |
arl | -0.024 |
ppy | -0.024 |
ophone | -0.023 |
wy | -0.023 |
Token | says |
Token ID | 1139 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ems | +0.109 |
ppy | +0.103 |
ophone | +0.098 |
arl | +0.097 |
oke | +0.094 |
Neg logit contributions | |
excitement | -0.088 |
it | -0.086 |
Mill | -0.084 |
delight | -0.084 |
sudden | -0.082 |
Token | What |
Token ID | 2061 |
Feature activation | +8.92e-03 |
Pos logit contributions | |
excitement | +0.012 |
it | +0.012 |
Mill | +0.012 |
delight | +0.012 |
sudden | +0.012 |
Neg logit contributions | |
ems | -0.016 |
ppy | -0.016 |
ophone | -0.015 |
arl | -0.015 |
oke | -0.014 |
Token | happened |
Token ID | 3022 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
ems | +0.001 |
ppy | +0.001 |
arl | +0.001 |
ophone | +0.001 |
wy | +0.001 |
Neg logit contributions | |
excitement | -0.001 |
it | -0.001 |
Mill | -0.001 |
delight | -0.001 |
an | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
it | +0.004 |
excitement | +0.004 |
an | +0.004 |
Mill | +0.004 |
delight | +0.004 |
Neg logit contributions | |
ems | -0.009 |
ppy | -0.009 |
ophone | -0.008 |
arl | -0.008 |
wy | -0.008 |
Token | my |
Token ID | 616 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
excitement | +0.013 |
it | +0.013 |
delight | +0.012 |
Mill | +0.012 |
an | +0.011 |
Neg logit contributions | |
ems | -0.026 |
ppy | -0.025 |
ophone | -0.025 |
arl | -0.024 |
wy | -0.023 |
Token | d |
Token ID | 288 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
ems | +0.062 |
ppy | +0.059 |
ophone | +0.057 |
arl | +0.056 |
oke | +0.054 |
Neg logit contributions | |
excitement | -0.040 |
it | -0.039 |
Mill | -0.038 |
delight | -0.037 |
sudden | -0.036 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
it | +0.005 |
Its | +0.005 |
an | +0.005 |
Mill | +0.005 |
top | +0.005 |
Neg logit contributions | |
ems | -0.001 |
ophone | -0.001 |
ppy | -0.001 |
wy | -0.001 |
osaurs | -0.001 |
Token | ings |
Token ID | 654 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
ems | +1.157 |
ppy | +1.133 |
ophone | +1.130 |
wy | +1.066 |
oke | +1.035 |
Neg logit contributions | |
it | -0.315 |
excitement | -0.283 |
delight | -0.250 |
top | -0.244 |
sight | -0.241 |
Token | ? |
Token ID | 30 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
it | +0.108 |
the | +0.104 |
a | +0.098 |
an | +0.095 |
her | +0.094 |
Neg logit contributions | |
ems | -0.121 |
ppy | -0.120 |
ophone | -0.120 |
ider | -0.118 |
osaurs | -0.113 |
Token | Why |
Token ID | 4162 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ems | +0.165 |
ppy | +0.158 |
wy | +0.153 |
ets | +0.152 |
arl | +0.151 |
Neg logit contributions | |
it | -0.107 |
Mill | -0.103 |
an | -0.100 |
excitement | -0.098 |
Frankie | -0.097 |
Token | do |
Token ID | 466 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
arl | +0.074 |
ider | +0.071 |
ppy | +0.070 |
ems | +0.070 |
ophone | +0.067 |
Neg logit contributions | |
it | -0.071 |
the | -0.065 |
a | -0.064 |
an | -0.064 |
her | -0.059 |
Token | you |
Token ID | 345 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
excitement | +0.045 |
Mill | +0.044 |
delight | +0.043 |
sudden | +0.042 |
Frankie | +0.041 |
Neg logit contributions | |
ems | -0.071 |
ppy | -0.066 |
ophone | -0.063 |
oke | -0.062 |
arl | -0.061 |
Token | you |
Token ID | 345 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ems | +0.073 |
ppy | +0.070 |
ophone | +0.068 |
arl | +0.067 |
oke | +0.065 |
Neg logit contributions | |
excitement | -0.033 |
it | -0.032 |
Mill | -0.031 |
delight | -0.031 |
sudden | -0.030 |
Token | okay |
Token ID | 8788 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
excitement | +0.011 |
it | +0.011 |
Mill | +0.011 |
delight | +0.011 |
sudden | +0.010 |
Neg logit contributions | |
ems | -0.020 |
ppy | -0.019 |
ophone | -0.018 |
arl | -0.018 |
oke | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ems | +0.062 |
ppy | +0.060 |
ophone | +0.057 |
arl | +0.057 |
oke | +0.055 |
Neg logit contributions | |
excitement | -0.030 |
it | -0.028 |
delight | -0.028 |
Mill | -0.028 |
sudden | -0.027 |
Token | my |
Token ID | 616 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
excitement | +0.012 |
Mill | +0.012 |
it | +0.012 |
delight | +0.011 |
sudden | +0.011 |
Neg logit contributions | |
ems | -0.030 |
ppy | -0.029 |
arl | -0.028 |
ophone | -0.028 |
oke | -0.027 |
Token | d |
Token ID | 288 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
ems | +0.059 |
ppy | +0.056 |
ophone | +0.054 |
arl | +0.054 |
oke | +0.052 |
Neg logit contributions | |
excitement | -0.037 |
it | -0.035 |
Mill | -0.035 |
delight | -0.035 |
sudden | -0.033 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
it | +0.013 |
Mill | +0.013 |
excitement | +0.013 |
an | +0.013 |
Its | +0.013 |
Neg logit contributions | |
ems | -0.003 |
ophone | -0.002 |
ppy | -0.002 |
wy | -0.002 |
osaurs | -0.001 |
Token | ings |
Token ID | 654 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ems | +1.166 |
ppy | +1.144 |
ophone | +1.140 |
wy | +1.069 |
oke | +1.036 |
Neg logit contributions | |
it | -0.308 |
excitement | -0.273 |
delight | -0.242 |
top | -0.240 |
sight | -0.239 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
it | +0.124 |
the | +0.118 |
a | +0.116 |
an | +0.113 |
her | +0.110 |
Neg logit contributions | |
ems | -0.131 |
ophone | -0.128 |
ppy | -0.124 |
ider | -0.121 |
osaurs | -0.114 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ems | +0.290 |
arl | +0.273 |
ppy | +0.272 |
oke | +0.254 |
ophone | +0.242 |
Neg logit contributions | |
Frankie | -0.140 |
excitement | -0.136 |
Mill | -0.133 |
delight | -0.133 |
purpose | -0.126 |
Token | asked |
Token ID | 1965 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
it | +0.022 |
excitement | +0.021 |
Mill | +0.020 |
delight | +0.019 |
her | +0.019 |
Neg logit contributions | |
ems | -0.047 |
ppy | -0.044 |
arl | -0.044 |
ophone | -0.044 |
wy | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
ppy | +0.103 |
ems | +0.101 |
arl | +0.093 |
oke | +0.092 |
ophone | +0.088 |
Neg logit contributions | |
excitement | -0.063 |
delight | -0.061 |
Frankie | -0.058 |
Mill | -0.058 |
sudden | -0.058 |
Token | We |
Token ID | 1135 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
excitement | +0.018 |
Mill | +0.017 |
delight | +0.017 |
it | +0.017 |
Frankie | +0.016 |
Neg logit contributions | |
ems | -0.029 |
ppy | -0.028 |
arl | -0.026 |
ophone | -0.026 |
oke | -0.026 |
Token | know |
Token ID | 760 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
excitement | +0.057 |
it | +0.056 |
delight | +0.052 |
Mill | +0.052 |
an | +0.052 |
Neg logit contributions | |
ems | -0.113 |
ppy | -0.108 |
arl | -0.106 |
ophone | -0.105 |
oke | -0.102 |
Token | , |
Token ID | 11 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
excitement | +0.009 |
delight | +0.009 |
sudden | +0.009 |
Mill | +0.009 |
Frankie | +0.008 |
Neg logit contributions | |
ems | -0.016 |
ppy | -0.015 |
ophone | -0.014 |
oke | -0.014 |
arl | -0.014 |
Token | my |
Token ID | 616 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
excitement | +0.016 |
it | +0.015 |
Mill | +0.015 |
delight | +0.015 |
sudden | +0.014 |
Neg logit contributions | |
ems | -0.036 |
ppy | -0.035 |
ophone | -0.033 |
arl | -0.033 |
oke | -0.032 |
Token | d |
Token ID | 288 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
ems | +0.047 |
ppy | +0.044 |
ophone | +0.042 |
arl | +0.041 |
oke | +0.040 |
Neg logit contributions | |
excitement | -0.045 |
it | -0.044 |
Mill | -0.043 |
delight | -0.043 |
sudden | -0.042 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
Mill | +0.012 |
eyes | +0.012 |
excitement | +0.012 |
an | +0.012 |
her | +0.011 |
Neg logit contributions | |
ems | -0.003 |
ophone | -0.002 |
ppy | -0.002 |
wy | -0.002 |
osaurs | -0.002 |
Token | ings |
Token ID | 654 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ems | +1.152 |
ppy | +1.127 |
ophone | +1.110 |
wy | +1.050 |
oke | +1.028 |
Neg logit contributions | |
it | -0.313 |
excitement | -0.292 |
delight | -0.260 |
Mill | -0.255 |
sudden | -0.244 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
it | +0.049 |
the | +0.043 |
a | +0.040 |
her | +0.037 |
an | +0.036 |
Neg logit contributions | |
ems | -0.193 |
ophone | -0.186 |
ppy | -0.185 |
wy | -0.177 |
arl | -0.176 |
Token | We |
Token ID | 775 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
it | +0.015 |
excitement | +0.015 |
Mill | +0.015 |
delight | +0.014 |
an | +0.014 |
Neg logit contributions | |
ems | -0.032 |
ppy | -0.031 |
ophone | -0.029 |
arl | -0.029 |
wy | -0.029 |
Token | miss |
Token ID | 2051 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
it | +0.047 |
excitement | +0.046 |
an | +0.044 |
a | +0.043 |
Mill | +0.043 |
Neg logit contributions | |
ems | -0.094 |
arl | -0.092 |
ppy | -0.089 |
oke | -0.088 |
ophone | -0.087 |
Token | them |
Token ID | 606 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
ems | +0.067 |
ppy | +0.064 |
ophone | +0.061 |
arl | +0.061 |
wy | +0.059 |
Neg logit contributions | |
excitement | -0.025 |
delight | -0.023 |
Mill | -0.023 |
sudden | -0.022 |
it | -0.022 |
Token | have |
Token ID | 423 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
it | +0.010 |
a | +0.009 |
excitement | +0.009 |
an | +0.009 |
the | +0.009 |
Neg logit contributions | |
ems | -0.025 |
oke | -0.024 |
ophone | -0.023 |
arl | -0.023 |
ider | -0.023 |
Token | fun |
Token ID | 1257 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
Mill | +0.017 |
Frankie | +0.016 |
Its | +0.015 |
sudden | +0.015 |
curiously | +0.015 |
Neg logit contributions | |
ems | -0.031 |
ppy | -0.029 |
ets | -0.029 |
wy | -0.029 |
ophone | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
it | +0.067 |
excitement | +0.063 |
an | +0.062 |
Mill | +0.060 |
a | +0.060 |
Neg logit contributions | |
ems | -0.116 |
ppy | -0.111 |
ophone | -0.105 |
arl | -0.105 |
wy | -0.104 |
Token | my |
Token ID | 616 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
excitement | +0.018 |
Mill | +0.017 |
sudden | +0.017 |
delight | +0.016 |
it | +0.016 |
Neg logit contributions | |
ems | -0.049 |
ppy | -0.047 |
arl | -0.045 |
ophone | -0.044 |
oke | -0.044 |
Token | d |
Token ID | 288 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ems | +0.068 |
ppy | +0.064 |
arl | +0.062 |
ophone | +0.062 |
oke | +0.061 |
Neg logit contributions | |
excitement | -0.024 |
it | -0.024 |
delight | -0.023 |
Mill | -0.023 |
Frankie | -0.022 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
Mill | +0.019 |
it | +0.019 |
excitement | +0.019 |
an | +0.018 |
delight | +0.018 |
Neg logit contributions | |
ems | -0.005 |
ophone | -0.004 |
ppy | -0.003 |
wy | -0.003 |
osaurs | -0.003 |
Token | ings |
Token ID | 654 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ems | +1.149 |
ppy | +1.133 |
ophone | +1.119 |
wy | +1.059 |
oke | +1.026 |
Neg logit contributions | |
it | -0.315 |
excitement | -0.286 |
delight | -0.250 |
Mill | -0.250 |
top | -0.248 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
it | +0.132 |
the | +0.125 |
a | +0.121 |
her | +0.118 |
an | +0.118 |
Neg logit contributions | |
ems | -0.132 |
ppy | -0.128 |
ophone | -0.126 |
ider | -0.119 |
arl | -0.117 |
Token | Their |
Token ID | 5334 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ems | +0.266 |
ppy | +0.252 |
arl | +0.244 |
oke | +0.243 |
ber | +0.239 |
Neg logit contributions | |
sight | -0.136 |
delight | -0.136 |
excitement | -0.135 |
Frankie | -0.133 |
sudden | -0.132 |
Token | mother |
Token ID | 2802 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
arl | +0.148 |
ppy | +0.147 |
ems | +0.147 |
ber | +0.131 |
oke | +0.130 |
Neg logit contributions | |
Its | -0.073 |
it | -0.072 |
such | -0.071 |
Frankie | -0.069 |
an | -0.068 |
Token | asked |
Token ID | 1965 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
it | +0.055 |
excitement | +0.053 |
Mill | +0.051 |
delight | +0.050 |
sudden | +0.049 |
Neg logit contributions | |
ems | -0.092 |
ppy | -0.086 |
arl | -0.085 |
ophone | -0.085 |
wy | -0.081 |
Token | you |
Token ID | 345 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
excitement | +0.000 |
sudden | +0.000 |
delight | +0.000 |
Mill | +0.000 |
sight | +0.000 |
Neg logit contributions | |
ems | -0.000 |
ppy | -0.000 |
oke | -0.000 |
ophone | -0.000 |
osaurs | -0.000 |
Token | go |
Token ID | 467 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
it | +0.006 |
excitement | +0.006 |
delight | +0.006 |
Mill | +0.006 |
an | +0.006 |
Neg logit contributions | |
ems | -0.021 |
ppy | -0.020 |
ophone | -0.019 |
arl | -0.019 |
wy | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
it | +0.016 |
Mill | +0.014 |
excitement | +0.014 |
an | +0.013 |
the | +0.013 |
Neg logit contributions | |
ems | -0.052 |
ppy | -0.050 |
ophone | -0.048 |
arl | -0.047 |
wy | -0.047 |
Token | my |
Token ID | 616 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
excitement | +0.018 |
Mill | +0.017 |
sudden | +0.017 |
delight | +0.017 |
it | +0.017 |
Neg logit contributions | |
ems | -0.039 |
ppy | -0.037 |
arl | -0.036 |
ophone | -0.035 |
oke | -0.035 |
Token | d |
Token ID | 288 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
ems | +0.075 |
ppy | +0.072 |
ophone | +0.069 |
wy | +0.067 |
arl | +0.067 |
Neg logit contributions | |
excitement | -0.031 |
it | -0.030 |
Mill | -0.028 |
delight | -0.028 |
an | -0.027 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
it | +0.014 |
an | +0.013 |
Mill | +0.013 |
Its | +0.013 |
top | +0.013 |
Neg logit contributions | |
ems | -0.003 |
ophone | -0.002 |
ppy | -0.002 |
wy | -0.002 |
osaurs | -0.001 |
Token | ings |
Token ID | 654 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ems | +1.155 |
ppy | +1.137 |
ophone | +1.120 |
wy | +1.067 |
oke | +1.032 |
Neg logit contributions | |
it | -0.317 |
excitement | -0.280 |
top | -0.251 |
sight | -0.251 |
Mill | -0.247 |
Token | ," |
Token ID | 553 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
it | +0.074 |
Mill | +0.063 |
the | +0.063 |
an | +0.063 |
a | +0.062 |
Neg logit contributions | |
ems | -0.176 |
ppy | -0.169 |
ophone | -0.167 |
arl | -0.158 |
wy | -0.158 |
Token | Mom |
Token ID | 11254 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
sudden | +0.060 |
Frankie | +0.059 |
excitement | +0.058 |
sight | +0.057 |
delight | +0.057 |
Neg logit contributions | |
ems | -0.098 |
ppy | -0.087 |
oke | -0.087 |
arl | -0.086 |
ophone | -0.079 |
Token | said |
Token ID | 531 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
it | +0.004 |
excitement | +0.003 |
Mill | +0.003 |
the | +0.003 |
a | +0.003 |
Neg logit contributions | |
ems | -0.006 |
arl | -0.006 |
ppy | -0.006 |
ophone | -0.006 |
wy | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ppy | +0.026 |
ems | +0.026 |
oke | +0.025 |
arl | +0.025 |
ophone | +0.024 |
Neg logit contributions | |
excitement | -0.016 |
sudden | -0.016 |
delight | -0.015 |
Mill | -0.015 |
Frankie | -0.015 |
Token | let |
Token ID | 1309 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
excitement | +0.036 |
it | +0.035 |
Mill | +0.034 |
delight | +0.034 |
sudden | +0.032 |
Neg logit contributions | |
ems | -0.069 |
ppy | -0.066 |
ophone | -0.063 |
arl | -0.062 |
oke | -0.061 |
Token | out |
Token ID | 503 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ems | +0.109 |
ppy | +0.109 |
ophone | +0.102 |
wy | +0.100 |
oke | +0.099 |
Neg logit contributions | |
sudden | -0.032 |
excitement | -0.031 |
delight | -0.029 |
Mill | -0.026 |
sight | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
ems | +0.105 |
ppy | +0.104 |
ophone | +0.100 |
ets | +0.097 |
oke | +0.096 |
Neg logit contributions | |
sudden | -0.033 |
excitement | -0.027 |
delight | -0.026 |
Frankie | -0.026 |
purpose | -0.025 |
Token | big |
Token ID | 1263 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
Mill | +0.006 |
an | +0.006 |
it | +0.006 |
excitement | +0.006 |
Frankie | +0.006 |
Neg logit contributions | |
ems | -0.015 |
oke | -0.015 |
ppy | -0.015 |
arl | -0.014 |
ophone | -0.014 |
Token | sn |
Token ID | 3013 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
ems | +0.085 |
ppy | +0.082 |
oke | +0.078 |
arl | +0.078 |
ophone | +0.074 |
Neg logit contributions | |
sudden | -0.054 |
Mill | -0.054 |
excitement | -0.053 |
an | -0.052 |
it | -0.052 |
Token | arl |
Token ID | 7063 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
it | +0.074 |
Its | +0.072 |
Mill | +0.071 |
delight | +0.070 |
top | +0.069 |
Neg logit contributions | |
ems | -0.089 |
ppy | -0.077 |
ophone | -0.075 |
wy | -0.072 |
ccoli | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ems | +0.996 |
ppy | +0.952 |
ophone | +0.913 |
arl | +0.908 |
oke | +0.882 |
Neg logit contributions | |
excitement | -0.463 |
it | -0.447 |
Mill | -0.437 |
delight | -0.432 |
sudden | -0.416 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ems | +0.052 |
ppy | +0.050 |
ophone | +0.048 |
arl | +0.047 |
oke | +0.046 |
Neg logit contributions | |
excitement | -0.024 |
it | -0.023 |
Mill | -0.023 |
delight | -0.023 |
sudden | -0.022 |
Token | mouse |
Token ID | 10211 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
ems | +0.028 |
ppy | +0.027 |
ophone | +0.025 |
arl | +0.025 |
wy | +0.025 |
Neg logit contributions | |
Mill | -0.014 |
excitement | -0.014 |
it | -0.014 |
delight | -0.013 |
Frankie | -0.013 |
Token | knew |
Token ID | 2993 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Mill | +0.080 |
Frankie | +0.079 |
excitement | +0.079 |
purpose | +0.078 |
sight | +0.077 |
Neg logit contributions | |
ppy | -0.094 |
ems | -0.092 |
ophone | -0.088 |
oke | -0.083 |
ets | -0.082 |
Token | he |
Token ID | 339 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ems | +0.054 |
ppy | +0.052 |
ophone | +0.050 |
oke | +0.049 |
arl | +0.048 |
Neg logit contributions | |
excitement | -0.027 |
sudden | -0.026 |
delight | -0.026 |
Mill | -0.024 |
Frankie | -0.023 |
Token | wrapped |
Token ID | 12908 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
excitement | +0.015 |
it | +0.015 |
Mill | +0.014 |
delight | +0.014 |
sudden | +0.014 |
Neg logit contributions | |
ems | -0.031 |
ppy | -0.030 |
ophone | -0.028 |
arl | -0.028 |
oke | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
excitement | +0.123 |
delight | +0.116 |
Mill | +0.115 |
it | +0.113 |
sudden | +0.113 |
Neg logit contributions | |
ems | -0.247 |
ppy | -0.238 |
ophone | -0.227 |
arl | -0.225 |
wy | -0.219 |
Token | bag |
Token ID | 6131 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
excitement | +0.012 |
it | +0.011 |
Mill | +0.011 |
delight | +0.011 |
sudden | +0.010 |
Neg logit contributions | |
ems | -0.028 |
ppy | -0.027 |
ophone | -0.026 |
arl | -0.026 |
oke | -0.025 |
Token | ged |
Token ID | 2004 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
excitement | +0.071 |
it | +0.069 |
Mill | +0.068 |
delight | +0.067 |
sudden | +0.065 |
Neg logit contributions | |
ems | -0.128 |
ppy | -0.123 |
ophone | -0.117 |
arl | -0.116 |
oke | -0.113 |
Token | and |
Token ID | 290 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
ems | +0.133 |
ppy | +0.129 |
ophone | +0.122 |
arl | +0.120 |
wy | +0.118 |
Neg logit contributions | |
excitement | -0.071 |
Mill | -0.069 |
delight | -0.069 |
Frankie | -0.067 |
it | -0.066 |
Token | boxed |
Token ID | 46069 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
excitement | +0.013 |
it | +0.013 |
Mill | +0.013 |
delight | +0.013 |
sudden | +0.012 |
Neg logit contributions | |
ems | -0.028 |
ppy | -0.027 |
ophone | -0.026 |
arl | -0.026 |
wy | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
excitement | +0.336 |
it | +0.322 |
Mill | +0.319 |
delight | +0.317 |
sudden | +0.307 |
Neg logit contributions | |
ems | -0.632 |
ppy | -0.605 |
ophone | -0.578 |
arl | -0.574 |
oke | -0.556 |
Token | cart |
Token ID | 6383 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
excitement | +0.011 |
it | +0.011 |
Mill | +0.011 |
delight | +0.010 |
sudden | +0.010 |
Neg logit contributions | |
ems | -0.023 |
ppy | -0.022 |
ophone | -0.021 |
arl | -0.021 |
wy | -0.021 |
Token | oned |
Token ID | 12004 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
excitement | +0.083 |
it | +0.081 |
Mill | +0.079 |
delight | +0.078 |
sudden | +0.076 |
Neg logit contributions | |
ems | -0.104 |
ppy | -0.098 |
ophone | -0.093 |
arl | -0.092 |
oke | -0.089 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ems | +0.062 |
ppy | +0.060 |
ophone | +0.057 |
arl | +0.057 |
ets | +0.055 |
Neg logit contributions | |
excitement | -0.024 |
delight | -0.023 |
sudden | -0.023 |
Mill | -0.022 |
Frankie | -0.022 |
Token | packaged |
Token ID | 25555 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
excitement | +0.012 |
Mill | +0.011 |
it | +0.011 |
delight | +0.011 |
sudden | +0.011 |
Neg logit contributions | |
ems | -0.027 |
ppy | -0.026 |
ophone | -0.025 |
arl | -0.024 |
wy | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
ems | +0.010 |
ppy | +0.009 |
arl | +0.009 |
oke | +0.009 |
ophone | +0.009 |
Neg logit contributions | |
excitement | -0.005 |
delight | -0.004 |
sight | -0.004 |
Mill | -0.004 |
sudden | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ems | +0.006 |
ppy | +0.006 |
arl | +0.005 |
ophone | +0.005 |
oke | +0.005 |
Neg logit contributions | |
excitement | -0.003 |
Mill | -0.003 |
delight | -0.003 |
it | -0.003 |
sight | -0.003 |
Token | Ah |
Token ID | 10910 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ems | +0.024 |
ppy | +0.023 |
ophone | +0.022 |
arl | +0.021 |
oke | +0.021 |
Neg logit contributions | |
excitement | -0.019 |
it | -0.019 |
Mill | -0.019 |
delight | -0.018 |
sudden | -0.018 |
Token | h |
Token ID | 71 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ems | +0.035 |
ppy | +0.033 |
ophone | +0.032 |
arl | +0.032 |
wy | +0.031 |
Neg logit contributions | |
it | -0.018 |
excitement | -0.017 |
Mill | -0.017 |
delight | -0.016 |
sudden | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +7.22e-03 |
Pos logit contributions | |
ems | +0.273 |
wy | +0.261 |
ppy | +0.255 |
ophone | +0.252 |
arl | +0.244 |
Neg logit contributions | |
it | -0.078 |
Mill | -0.076 |
excitement | -0.069 |
an | -0.069 |
delight | -0.066 |
Token | LOOK |
Token ID | 48045 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
ems | +0.001 |
ppy | +0.001 |
ophone | +0.001 |
arl | +0.001 |
oke | +0.001 |
Neg logit contributions | |
excitement | -0.000 |
it | -0.000 |
delight | -0.000 |
Mill | -0.000 |
sudden | -0.000 |
Token | but |
Token ID | 475 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
it | +0.318 |
excitement | +0.290 |
the | +0.282 |
an | +0.278 |
Mill | +0.277 |
Neg logit contributions | |
ems | -0.584 |
ppy | -0.556 |
wy | -0.542 |
ophone | -0.542 |
arl | -0.525 |
Token | don |
Token ID | 836 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
it | +0.016 |
the | +0.014 |
excitement | +0.014 |
an | +0.014 |
Mill | +0.013 |
Neg logit contributions | |
ems | -0.037 |
ppy | -0.036 |
ophone | -0.035 |
wy | -0.035 |
arl | -0.034 |
Token | 't |
Token ID | 470 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ems | +0.036 |
ppy | +0.035 |
arl | +0.034 |
oke | +0.034 |
ophone | +0.033 |
Neg logit contributions | |
excitement | -0.023 |
delight | -0.022 |
sudden | -0.022 |
Mill | -0.021 |
sight | -0.020 |
Token | T |
Token ID | 309 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
excitement | +0.021 |
sudden | +0.019 |
delight | +0.019 |
Mill | +0.019 |
Its | +0.019 |
Neg logit contributions | |
ems | -0.037 |
ppy | -0.036 |
ophone | -0.033 |
arl | -0.033 |
oke | -0.032 |
Token | OU |
Token ID | 2606 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
excitement | +0.167 |
it | +0.160 |
delight | +0.160 |
Mill | +0.159 |
sudden | +0.158 |
Neg logit contributions | |
ems | -0.163 |
ppy | -0.153 |
ophone | -0.144 |
arl | -0.144 |
oke | -0.138 |
Token | in |
Token ID | 287 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
ems | +0.055 |
ppy | +0.053 |
arl | +0.051 |
ophone | +0.051 |
oke | +0.050 |
Neg logit contributions | |
excitement | -0.020 |
delight | -0.019 |
it | -0.018 |
sudden | -0.018 |
Mill | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e-03 |
Pos logit contributions | |
Mill | +0.003 |
sudden | +0.003 |
Frankie | +0.003 |
Its | +0.003 |
Mill | +0.003 |
Neg logit contributions | |
arl | -0.011 |
ems | -0.011 |
oke | -0.010 |
ppy | -0.010 |
ophone | -0.010 |
Token | car |
Token ID | 1097 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Mill | +0.000 |
it | +0.000 |
Frankie | +0.000 |
excitement | +0.000 |
delight | +0.000 |
Neg logit contributions | |
ems | -0.000 |
arl | -0.000 |
ophone | -0.000 |
oke | -0.000 |
ppy | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
excitement | +0.040 |
it | +0.040 |
Mill | +0.038 |
delight | +0.036 |
an | +0.035 |
Neg logit contributions | |
ems | -0.119 |
ppy | -0.115 |
arl | -0.110 |
ophone | -0.109 |
wy | -0.108 |
Token | they |
Token ID | 484 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
delight | +0.011 |
excitement | +0.011 |
Its | +0.011 |
sudden | +0.010 |
purpose | +0.010 |
Neg logit contributions | |
ems | -0.025 |
ophone | -0.024 |
ppy | -0.023 |
oke | -0.023 |
arl | -0.022 |
Token | warped |
Token ID | 43062 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
it | +0.001 |
excitement | +0.000 |
Mill | +0.000 |
the | +0.000 |
delight | +0.000 |
Neg logit contributions | |
ems | -0.001 |
arl | -0.001 |
ppy | -0.001 |
ider | -0.001 |
ophone | -0.001 |
Token | up |
Token ID | 510 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
excitement | +0.251 |
Mill | +0.233 |
delight | +0.233 |
it | +0.232 |
sudden | +0.229 |
Neg logit contributions | |
ems | -0.641 |
ppy | -0.613 |
ophone | -0.597 |
arl | -0.587 |
oke | -0.568 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
excitement | +0.016 |
delight | +0.014 |
sudden | +0.014 |
Mill | +0.013 |
Frankie | +0.012 |
Neg logit contributions | |
ems | -0.081 |
ophone | -0.078 |
ppy | -0.078 |
arl | -0.075 |
oke | -0.075 |
Token | adventure |
Token ID | 8855 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
ems | +0.004 |
ophone | +0.004 |
arl | +0.004 |
ppy | +0.004 |
oke | +0.003 |
Neg logit contributions | |
Mill | -0.002 |
excitement | -0.002 |
it | -0.002 |
Frankie | -0.002 |
delight | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
ems | +0.077 |
ppy | +0.074 |
ophone | +0.071 |
arl | +0.070 |
oke | +0.068 |
Neg logit contributions | |
excitement | -0.032 |
it | -0.031 |
Mill | -0.030 |
delight | -0.030 |
sudden | -0.029 |
Token | one |
Token ID | 530 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
delight | +0.039 |
excitement | +0.037 |
Its | +0.037 |
Frankie | +0.036 |
sudden | +0.036 |
Neg logit contributions | |
ophone | -0.132 |
ems | -0.131 |
ppy | -0.130 |
wy | -0.128 |
ets | -0.121 |
Token | mu |
Token ID | 38779 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
it | +0.145 |
excitement | +0.138 |
Mill | +0.133 |
delight | +0.131 |
an | +0.129 |
Neg logit contributions | |
ems | -0.228 |
ppy | -0.219 |
arl | -0.209 |
ophone | -0.206 |
wy | -0.200 |
Token | Ã |
Token ID | 5746 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
it | +0.029 |
excitement | +0.028 |
Its | +0.028 |
delight | +0.028 |
a | +0.028 |
Neg logit contributions | |
ems | -0.027 |
ppy | -0.026 |
arl | -0.025 |
wy | -0.025 |
ophone | -0.024 |
Token | ± |
Token ID | 22519 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
it | +0.186 |
excitement | +0.176 |
Mill | +0.168 |
delight | +0.166 |
an | +0.163 |
Neg logit contributions | |
ems | -0.420 |
ppy | -0.398 |
ophone | -0.386 |
arl | -0.386 |
wy | -0.378 |
Token | eca |
Token ID | 31047 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
it | +0.234 |
excitement | +0.217 |
Mill | +0.208 |
an | +0.204 |
delight | +0.203 |
Neg logit contributions | |
ems | -0.516 |
ppy | -0.486 |
ophone | -0.477 |
arl | -0.474 |
wy | -0.463 |
Token | , |
Token ID | 11 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
it | +0.022 |
excitement | +0.020 |
the | +0.019 |
Mill | +0.019 |
an | +0.019 |
Neg logit contributions | |
ems | -0.032 |
ppy | -0.031 |
arl | -0.030 |
wy | -0.029 |
ophone | -0.029 |
Token | es |
Token ID | 1658 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
it | +0.007 |
excitement | +0.007 |
delight | +0.007 |
an | +0.007 |
the | +0.006 |
Neg logit contributions | |
ems | -0.014 |
ppy | -0.014 |
wy | -0.013 |
ophone | -0.013 |
arl | -0.013 |
Token | bon |
Token ID | 5351 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
it | +0.435 |
the | +0.422 |
a | +0.413 |
an | +0.407 |
excitement | +0.400 |
Neg logit contributions | |
ems | -0.423 |
arl | -0.399 |
ppy | -0.392 |
oke | -0.388 |
ophone | -0.384 |
Token | ita |
Token ID | 5350 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
top | +0.099 |
instructions | +0.097 |
it | +0.097 |
a | +0.096 |
purpose | +0.096 |
Neg logit contributions | |
ems | -0.105 |
ppy | -0.095 |
wy | -0.091 |
arl | -0.087 |
ophone | -0.085 |
Token | y |
Token ID | 331 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
it | +0.026 |
excitement | +0.026 |
Mill | +0.025 |
delight | +0.024 |
an | +0.024 |
Neg logit contributions | |
ems | -0.062 |
ppy | -0.059 |
arl | -0.058 |
ophone | -0.057 |
wy | -0.056 |
Token | su |
Token ID | 424 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
Mill | +0.002 |
excitement | +0.002 |
it | +0.002 |
Frankie | +0.001 |
sudden | +0.001 |
Neg logit contributions | |
ems | -0.003 |
ppy | -0.003 |
arl | -0.003 |
ets | -0.003 |
wy | -0.003 |
Token | ave |
Token ID | 1015 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ems | +0.058 |
ppy | +0.053 |
ophone | +0.051 |
arl | +0.050 |
oke | +0.048 |
Neg logit contributions | |
it | -0.060 |
excitement | -0.060 |
sudden | -0.058 |
delight | -0.058 |
Mill | -0.058 |
Token | It |
Token ID | 632 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
excitement | +0.008 |
delight | +0.008 |
sudden | +0.008 |
Frankie | +0.007 |
Mill | +0.007 |
Neg logit contributions | |
ems | -0.026 |
ppy | -0.024 |
arl | -0.024 |
oke | -0.023 |
ophone | -0.023 |
Token | said |
Token ID | 531 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
it | +0.026 |
excitement | +0.025 |
Mill | +0.024 |
an | +0.024 |
a | +0.023 |
Neg logit contributions | |
ems | -0.059 |
ppy | -0.056 |
arl | -0.055 |
ophone | -0.053 |
wy | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
excitement | +0.001 |
delight | +0.001 |
Mill | +0.001 |
sudden | +0.001 |
Frankie | +0.001 |
Neg logit contributions | |
ems | -0.002 |
ppy | -0.002 |
ophone | -0.002 |
arl | -0.002 |
oke | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
excitement | +0.004 |
it | +0.004 |
Mill | +0.004 |
delight | +0.003 |
sudden | +0.003 |
Neg logit contributions | |
ems | -0.013 |
ppy | -0.012 |
ophone | -0.012 |
arl | -0.012 |
oke | -0.011 |
Token | Magic |
Token ID | 22975 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
excitement | +0.009 |
Mill | +0.009 |
delight | +0.009 |
it | +0.008 |
Frankie | +0.008 |
Neg logit contributions | |
ems | -0.016 |
ppy | -0.015 |
arl | -0.014 |
ophone | -0.014 |
oke | -0.014 |
Token | Trick |
Token ID | 30028 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
it | +0.014 |
excitement | +0.013 |
Mill | +0.013 |
an | +0.013 |
delight | +0.012 |
Neg logit contributions | |
ems | -0.019 |
ppy | -0.018 |
arl | -0.017 |
ophone | -0.017 |
wy | -0.017 |
Token | Wand |
Token ID | 22420 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
it | +0.364 |
a | +0.343 |
an | +0.338 |
the | +0.325 |
top | +0.319 |
Neg logit contributions | |
ems | -0.482 |
ppy | -0.455 |
ophone | -0.439 |
wy | -0.437 |
arl | -0.432 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
it | +0.127 |
excitement | +0.117 |
an | +0.110 |
the | +0.110 |
Mill | +0.109 |
Neg logit contributions | |
ems | -0.255 |
ppy | -0.246 |
arl | -0.238 |
ophone | -0.235 |
oke | -0.227 |
Token | For |
Token ID | 1114 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
it | +0.014 |
excitement | +0.014 |
Mill | +0.014 |
delight | +0.013 |
an | +0.013 |
Neg logit contributions | |
ems | -0.030 |
ppy | -0.029 |
ophone | -0.028 |
arl | -0.027 |
wy | -0.027 |
Token | ages |
Token ID | 9337 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ems | +0.040 |
ppy | +0.038 |
ophone | +0.037 |
arl | +0.036 |
oke | +0.036 |
Neg logit contributions | |
it | -0.009 |
excitement | -0.009 |
Mill | -0.009 |
an | -0.008 |
delight | -0.008 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
it | +0.018 |
excitement | +0.017 |
Mill | +0.016 |
delight | +0.016 |
an | +0.015 |
Neg logit contributions | |
ems | -0.048 |
ppy | -0.046 |
ophone | -0.044 |
arl | -0.044 |
wy | -0.043 |
Token | Soon |
Token ID | 15894 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
excitement | +0.039 |
sudden | +0.035 |
delight | +0.035 |
it | +0.033 |
Mill | +0.033 |
Neg logit contributions | |
ems | -0.102 |
ppy | -0.097 |
ophone | -0.096 |
oke | -0.093 |
arl | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
sudden | +0.030 |
excitement | +0.029 |
Mill | +0.028 |
Frankie | +0.028 |
Mill | +0.027 |
Neg logit contributions | |
ems | -0.056 |
ppy | -0.054 |
oke | -0.050 |
ets | -0.049 |
ophone | -0.048 |
Token | fish |
Token ID | 5916 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
ems | +0.002 |
ppy | +0.002 |
arl | +0.002 |
ophone | +0.002 |
wy | +0.002 |
Neg logit contributions | |
Mill | -0.001 |
excitement | -0.001 |
it | -0.001 |
Frankie | -0.001 |
delight | -0.001 |
Token | became |
Token ID | 2627 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
it | +0.031 |
excitement | +0.029 |
sudden | +0.028 |
the | +0.028 |
delight | +0.027 |
Neg logit contributions | |
ems | -0.065 |
arl | -0.062 |
ppy | -0.059 |
ophone | -0.058 |
wy | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ems | +0.008 |
ppy | +0.008 |
ophone | +0.007 |
wy | +0.007 |
arl | +0.007 |
Neg logit contributions | |
excitement | -0.002 |
delight | -0.002 |
Mill | -0.002 |
Its | -0.002 |
Frankie | -0.002 |
Token | fixture |
Token ID | 29220 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
Mill | +0.013 |
excitement | +0.013 |
it | +0.012 |
Frankie | +0.012 |
Its | +0.012 |
Neg logit contributions | |
ems | -0.024 |
ppy | -0.024 |
ophone | -0.023 |
arl | -0.023 |
oke | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
excitement | +0.236 |
it | +0.235 |
Mill | +0.222 |
delight | +0.216 |
an | +0.210 |
Neg logit contributions | |
ems | -0.626 |
ppy | -0.598 |
ophone | -0.578 |
arl | -0.577 |
oke | -0.560 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ems | +0.011 |
ppy | +0.011 |
ophone | +0.010 |
arl | +0.010 |
wy | +0.010 |
Neg logit contributions | |
excitement | -0.002 |
sudden | -0.002 |
Mill | -0.002 |
delight | -0.002 |
Frankie | -0.001 |
Token | park |
Token ID | 3952 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ems | +0.021 |
ppy | +0.020 |
arl | +0.020 |
ophone | +0.019 |
oke | +0.019 |
Neg logit contributions | |
Mill | -0.011 |
excitement | -0.010 |
Frankie | -0.010 |
it | -0.010 |
Its | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ems | +0.050 |
ppy | +0.048 |
ophone | +0.046 |
arl | +0.045 |
oke | +0.044 |
Neg logit contributions | |
excitement | -0.018 |
it | -0.018 |
Mill | -0.017 |
delight | -0.017 |
sudden | -0.016 |
Token | everyone |
Token ID | 2506 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ems | +0.039 |
ppy | +0.038 |
arl | +0.037 |
ophone | +0.037 |
wy | +0.036 |
Neg logit contributions | |
it | -0.006 |
excitement | -0.006 |
Mill | -0.005 |
delight | -0.005 |
an | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
ems | +0.011 |
ppy | +0.011 |
arl | +0.010 |
oke | +0.010 |
ophone | +0.010 |
Neg logit contributions | |
it | -0.004 |
excitement | -0.003 |
an | -0.003 |
a | -0.003 |
the | -0.003 |
Token | N |
Token ID | 399 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ems | +0.011 |
ppy | +0.010 |
ophone | +0.010 |
arl | +0.010 |
oke | +0.010 |
Neg logit contributions | |
Mill | -0.006 |
Frankie | -0.006 |
it | -0.006 |
excitement | -0.006 |
delight | -0.006 |
Token | aughty |
Token ID | 28496 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
it | +0.131 |
an | +0.129 |
a | +0.127 |
baby | +0.125 |
Mill | +0.124 |
Neg logit contributions | |
ems | -0.126 |
ophone | -0.119 |
wy | -0.113 |
osaurs | -0.111 |
arl | -0.108 |
Token | Fox |
Token ID | 5426 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
ems | +0.119 |
arl | +0.114 |
ppy | +0.113 |
ophone | +0.112 |
oke | +0.107 |
Neg logit contributions | |
it | -0.060 |
excitement | -0.058 |
Mill | -0.055 |
delight | -0.055 |
an | -0.055 |
Token | Stack |
Token ID | 23881 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ems | +0.148 |
arl | +0.144 |
ppy | +0.137 |
wy | +0.134 |
ophone | +0.133 |
Neg logit contributions | |
it | -0.075 |
a | -0.068 |
the | -0.067 |
an | -0.066 |
excitement | -0.066 |
Token | Trick |
Token ID | 30028 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
it | +0.303 |
the | +0.276 |
an | +0.271 |
a | +0.271 |
excitement | +0.267 |
Neg logit contributions | |
ems | -0.458 |
arl | -0.446 |
ppy | -0.430 |
ophone | -0.416 |
oke | -0.414 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
it | +0.283 |
a | +0.273 |
an | +0.265 |
the | +0.249 |
top | +0.245 |
Neg logit contributions | |
ems | -0.547 |
arl | -0.502 |
ppy | -0.495 |
wy | -0.491 |
oke | -0.488 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
excitement | +0.001 |
delight | +0.001 |
sudden | +0.001 |
Mill | +0.001 |
it | +0.001 |
Neg logit contributions | |
ems | -0.004 |
ppy | -0.003 |
ophone | -0.003 |
arl | -0.003 |
oke | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
ems | +0.021 |
ppy | +0.020 |
ophone | +0.019 |
arl | +0.019 |
oke | +0.019 |
Neg logit contributions | |
excitement | -0.007 |
delight | -0.006 |
Mill | -0.006 |
it | -0.006 |
Frankie | -0.006 |
Token | He |
Token ID | 1544 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ems | +0.017 |
ppy | +0.016 |
ophone | +0.015 |
arl | +0.015 |
wy | +0.015 |
Neg logit contributions | |
excitement | -0.006 |
Mill | -0.006 |
it | -0.006 |
delight | -0.005 |
Frankie | -0.005 |
Token | then |
Token ID | 788 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
ems | +0.031 |
arl | +0.031 |
ppy | +0.029 |
wy | +0.028 |
ophone | +0.028 |
Neg logit contributions | |
it | -0.018 |
excitement | -0.017 |
an | -0.017 |
a | -0.017 |
the | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
excitement | +0.118 |
Mill | +0.110 |
it | +0.109 |
delight | +0.109 |
sudden | +0.106 |
Neg logit contributions | |
ems | -0.298 |
ppy | -0.285 |
ophone | -0.274 |
arl | -0.272 |
oke | -0.265 |
Token | labeled |
Token ID | 15494 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
excitement | +0.012 |
it | +0.011 |
Mill | +0.011 |
delight | +0.011 |
sudden | +0.011 |
Neg logit contributions | |
ems | -0.026 |
ppy | -0.025 |
ophone | -0.024 |
arl | -0.024 |
wy | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
excitement | +0.100 |
sudden | +0.095 |
Mill | +0.091 |
delight | +0.091 |
Frankie | +0.087 |
Neg logit contributions | |
ems | -0.303 |
ppy | -0.292 |
ophone | -0.283 |
arl | -0.277 |
oke | -0.275 |
Token | branded |
Token ID | 23546 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
excitement | +0.009 |
it | +0.009 |
Mill | +0.009 |
delight | +0.009 |
sudden | +0.008 |
Neg logit contributions | |
ems | -0.024 |
ppy | -0.023 |
ophone | -0.022 |
arl | -0.022 |
oke | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
excitement | +0.218 |
it | +0.216 |
Mill | +0.206 |
delight | +0.202 |
an | +0.193 |
Neg logit contributions | |
ems | -0.513 |
ppy | -0.489 |
ophone | -0.473 |
arl | -0.470 |
wy | -0.460 |
Token | generic |
Token ID | 14276 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
excitement | +0.009 |
Mill | +0.008 |
it | +0.008 |
delight | +0.008 |
sudden | +0.008 |
Neg logit contributions | |
ems | -0.022 |
ppy | -0.021 |
ophone | -0.020 |
arl | -0.020 |
wy | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
it | +0.212 |
excitement | +0.210 |
Mill | +0.196 |
delight | +0.191 |
an | +0.184 |
Neg logit contributions | |
ems | -0.609 |
ppy | -0.584 |
ophone | -0.568 |
arl | -0.561 |
wy | -0.559 |
Token | fresh |
Token ID | 4713 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
excitement | +0.004 |
Mill | +0.004 |
it | +0.004 |
delight | +0.004 |
Its | +0.004 |
Neg logit contributions | |
ems | -0.011 |
ppy | -0.010 |
arl | -0.010 |
ophone | -0.010 |
wy | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
ems | +0.016 |
ppy | +0.015 |
arl | +0.015 |
ets | +0.015 |
wy | +0.014 |
Neg logit contributions | |
excitement | -0.008 |
Mill | -0.007 |
it | -0.007 |
delight | -0.007 |
Frankie | -0.007 |
Token | stale |
Token ID | 39985 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
excitement | +0.005 |
Mill | +0.005 |
it | +0.005 |
delight | +0.005 |
sudden | +0.005 |
Neg logit contributions | |
ems | -0.012 |
ppy | -0.012 |
arl | -0.011 |
ophone | -0.011 |
wy | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
excitement | +0.097 |
Mill | +0.094 |
delight | +0.090 |
Frankie | +0.090 |
it | +0.089 |
Neg logit contributions | |
ems | -0.248 |
ppy | -0.238 |
arl | -0.228 |
ophone | -0.224 |
ets | -0.222 |
Token | , |
Token ID | 11 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
ems | +0.004 |
ppy | +0.004 |
ophone | +0.003 |
arl | +0.003 |
wy | +0.003 |
Neg logit contributions | |
it | -0.001 |
excitement | -0.001 |
an | -0.001 |
delight | -0.001 |
Mill | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
ems | +0.001 |
ppy | +0.001 |
ophone | +0.001 |
arl | +0.001 |
oke | +0.001 |
Neg logit contributions | |
excitement | -0.000 |
delight | -0.000 |
Mill | -0.000 |
sudden | -0.000 |
it | -0.000 |
Token | made |
Token ID | 925 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ems | +0.011 |
arl | +0.011 |
ppy | +0.010 |
oke | +0.010 |
ophone | +0.009 |
Neg logit contributions | |
it | -0.006 |
an | -0.005 |
the | -0.005 |
a | -0.005 |
excitement | -0.005 |
Token | some |
Token ID | 617 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
ophone | +0.017 |
ems | +0.017 |
ets | +0.017 |
wy | +0.017 |
ppy | +0.017 |
Neg logit contributions | |
Mill | -0.008 |
Frankie | -0.008 |
Mill | -0.007 |
Susan | -0.006 |
sudden | -0.006 |
Token | money |
Token ID | 1637 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
ems | +0.125 |
oke | +0.118 |
ppy | +0.118 |
ets | +0.117 |
arl | +0.116 |
Neg logit contributions | |
Mill | -0.066 |
Frankie | -0.063 |
it | -0.059 |
Mill | -0.057 |
Its | -0.056 |
Token | transactions |
Token ID | 8945 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
sudden | +0.053 |
excitement | +0.051 |
Mill | +0.050 |
delight | +0.050 |
Frankie | +0.047 |
Neg logit contributions | |
ems | -0.088 |
ppy | -0.086 |
ophone | -0.082 |
arl | -0.081 |
ets | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
it | +0.155 |
the | +0.126 |
a | +0.125 |
an | +0.123 |
excitement | +0.121 |
Neg logit contributions | |
ems | -0.683 |
arl | -0.659 |
ppy | -0.645 |
wy | -0.635 |
oke | -0.634 |
Token | At |
Token ID | 1629 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
ems | +0.035 |
ppy | +0.034 |
ophone | +0.032 |
arl | +0.032 |
oke | +0.032 |
Neg logit contributions | |
excitement | -0.010 |
it | -0.009 |
delight | -0.009 |
Mill | -0.009 |
an | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ems | +0.151 |
ppy | +0.146 |
arl | +0.143 |
ophone | +0.141 |
wy | +0.139 |
Neg logit contributions | |
excitement | -0.024 |
Mill | -0.022 |
delight | -0.021 |
sudden | -0.019 |
Frankie | -0.017 |
Token | post |
Token ID | 1281 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
ems | +0.025 |
arl | +0.024 |
ider | +0.024 |
wy | +0.023 |
oke | +0.023 |
Neg logit contributions | |
Mill | -0.024 |
excitement | -0.022 |
Frankie | -0.022 |
Bobby | -0.021 |
Mill | -0.021 |
Token | office |
Token ID | 2607 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ems | +0.013 |
ppy | +0.012 |
arl | +0.012 |
ophone | +0.011 |
wy | +0.011 |
Neg logit contributions | |
it | -0.006 |
excitement | -0.006 |
Mill | -0.006 |
an | -0.005 |
delight | -0.005 |
Token | so |
Token ID | 523 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
Mill | +0.001 |
Frankie | +0.001 |
Its | +0.001 |
excitement | +0.001 |
delight | +0.001 |
Neg logit contributions | |
ppy | -0.003 |
ems | -0.003 |
wy | -0.003 |
ets | -0.003 |
arl | -0.002 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Frankie | +0.026 |
Mill | +0.025 |
it | +0.023 |
excitement | +0.023 |
an | +0.022 |
Neg logit contributions | |
oke | -0.063 |
ppy | -0.062 |
arl | -0.062 |
ems | -0.061 |
wy | -0.060 |
Token | inside |
Token ID | 2641 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
excitement | +0.026 |
delight | +0.025 |
sudden | +0.024 |
Frankie | +0.024 |
Mill | +0.024 |
Neg logit contributions | |
ems | -0.047 |
ppy | -0.044 |
ets | -0.042 |
ophone | -0.041 |
oke | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
ems | +0.064 |
ppy | +0.061 |
ets | +0.059 |
ophone | +0.058 |
oke | +0.057 |
Neg logit contributions | |
excitement | -0.023 |
sudden | -0.023 |
Frankie | -0.022 |
delight | -0.022 |
Mill | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ems | +0.017 |
ppy | +0.016 |
ophone | +0.015 |
ets | +0.015 |
oke | +0.015 |
Neg logit contributions | |
Frankie | -0.005 |
excitement | -0.005 |
sudden | -0.005 |
Mill | -0.005 |
delight | -0.005 |
Token | fringe |
Token ID | 26821 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
ems | +0.021 |
ppy | +0.020 |
arl | +0.019 |
ets | +0.019 |
ophone | +0.019 |
Neg logit contributions | |
Mill | -0.008 |
Frankie | -0.008 |
Its | -0.008 |
an | -0.007 |
it | -0.007 |
Token | from |
Token ID | 422 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
excitement | +0.283 |
delight | +0.266 |
Mill | +0.265 |
sudden | +0.263 |
it | +0.260 |
Neg logit contributions | |
ems | -0.537 |
ppy | -0.514 |
ophone | -0.492 |
arl | -0.485 |
oke | -0.478 |
Token | the |
Token ID | 262 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ems | +0.055 |
ppy | +0.054 |
ophone | +0.052 |
wy | +0.052 |
arl | +0.052 |
Neg logit contributions | |
excitement | -0.012 |
Mill | -0.012 |
delight | -0.011 |
Its | -0.011 |
Frankie | -0.011 |
Token | cut |
Token ID | 2005 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
ems | +0.022 |
ppy | +0.021 |
ophone | +0.020 |
arl | +0.020 |
wy | +0.020 |
Neg logit contributions | |
Mill | -0.011 |
excitement | -0.010 |
Frankie | -0.010 |
it | -0.010 |
delight | -0.010 |
Token | shells |
Token ID | 19679 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
excitement | +0.007 |
delight | +0.007 |
Mill | +0.007 |
sudden | +0.007 |
Frankie | +0.007 |
Neg logit contributions | |
ems | -0.008 |
ppy | -0.008 |
ophone | -0.007 |
wy | -0.007 |
arl | -0.007 |
Token | made |
Token ID | 925 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ems | +0.067 |
ppy | +0.064 |
ophone | +0.061 |
arl | +0.060 |
oke | +0.059 |
Neg logit contributions | |
excitement | -0.032 |
delight | -0.030 |
sudden | -0.030 |
Mill | -0.029 |
Frankie | -0.028 |
Token | melodies |
Token ID | 47077 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
excitement | +0.079 |
it | +0.076 |
delight | +0.073 |
Mill | +0.072 |
sudden | +0.071 |
Neg logit contributions | |
ems | -0.172 |
ppy | -0.164 |
ophone | -0.158 |
arl | -0.158 |
oke | -0.152 |
Token | and |
Token ID | 290 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
excitement | +0.040 |
it | +0.039 |
Mill | +0.037 |
delight | +0.037 |
an | +0.035 |
Neg logit contributions | |
ems | -0.102 |
ppy | -0.098 |
ophone | -0.094 |
arl | -0.094 |
wy | -0.091 |
Token | even |
Token ID | 772 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
excitement | +0.002 |
it | +0.002 |
delight | +0.002 |
Mill | +0.002 |
sudden | +0.002 |
Neg logit contributions | |
ems | -0.004 |
ppy | -0.004 |
arl | -0.004 |
ophone | -0.004 |
oke | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
it | +0.038 |
excitement | +0.038 |
the | +0.037 |
a | +0.037 |
her | +0.036 |
Neg logit contributions | |
arl | -0.077 |
ems | -0.075 |
ppy | -0.073 |
wy | -0.072 |
oke | -0.071 |
Token | own |
Token ID | 898 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Mill | +0.012 |
Frankie | +0.011 |
it | +0.011 |
excitement | +0.010 |
sudden | +0.010 |
Neg logit contributions | |
ems | -0.027 |
ppy | -0.025 |
ophone | -0.025 |
arl | -0.024 |
ets | -0.024 |
Token | compositions |
Token ID | 33543 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
Mill | +0.034 |
Frankie | +0.031 |
excitement | +0.030 |
sudden | +0.029 |
delight | +0.029 |
Neg logit contributions | |
ems | -0.062 |
ophone | -0.058 |
ppy | -0.057 |
ets | -0.055 |
arl | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
it | +0.186 |
excitement | +0.164 |
an | +0.162 |
Mill | +0.161 |
a | +0.156 |
Neg logit contributions | |
ems | -0.638 |
ppy | -0.615 |
arl | -0.600 |
wy | -0.596 |
ophone | -0.585 |
Token | Emma |
Token ID | 18966 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
excitement | +0.012 |
sudden | +0.011 |
delight | +0.011 |
it | +0.011 |
Mill | +0.011 |
Neg logit contributions | |
ems | -0.029 |
ppy | -0.027 |
ophone | -0.027 |
arl | -0.027 |
oke | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
it | +0.091 |
excitement | +0.090 |
delight | +0.085 |
sudden | +0.082 |
Mill | +0.081 |
Neg logit contributions | |
ems | -0.196 |
arl | -0.190 |
ppy | -0.186 |
ophone | -0.178 |
oke | -0.176 |
Token | so |
Token ID | 523 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
Mill | +0.007 |
excitement | +0.007 |
Frankie | +0.007 |
sudden | +0.006 |
it | +0.006 |
Neg logit contributions | |
ems | -0.028 |
ppy | -0.027 |
ophone | -0.027 |
arl | -0.025 |
oke | -0.025 |
Token | proud |
Token ID | 6613 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
excitement | +0.039 |
it | +0.038 |
delight | +0.036 |
Mill | +0.036 |
sudden | +0.035 |
Neg logit contributions | |
ems | -0.095 |
ppy | -0.091 |
ophone | -0.087 |
arl | -0.087 |
oke | -0.084 |
Token | And |
Token ID | 843 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
excitement | +0.007 |
it | +0.007 |
Mill | +0.007 |
delight | +0.007 |
Its | +0.007 |
Neg logit contributions | |
ems | -0.015 |
ppy | -0.015 |
ophone | -0.014 |
wy | -0.014 |
oke | -0.014 |
Token | ..." |
Token ID | 9313 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
ems | +0.126 |
ppy | +0.121 |
ophone | +0.118 |
arl | +0.115 |
wy | +0.113 |
Neg logit contributions | |
it | -0.058 |
excitement | -0.057 |
delight | -0.053 |
Mill | -0.053 |
an | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
ems | +0.005 |
ppy | +0.005 |
ophone | +0.005 |
arl | +0.005 |
wy | +0.005 |
Neg logit contributions | |
excitement | -0.001 |
it | -0.001 |
delight | -0.001 |
Mill | -0.001 |
an | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
ems | +0.004 |
ppy | +0.004 |
arl | +0.004 |
ophone | +0.004 |
oke | +0.004 |
Neg logit contributions | |
excitement | -0.001 |
Mill | -0.001 |
it | -0.001 |
delight | -0.001 |
Frankie | -0.001 |
Token | Anna |
Token ID | 31160 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
ems | +0.002 |
ppy | +0.002 |
ophone | +0.002 |
arl | +0.002 |
oke | +0.002 |
Neg logit contributions | |
excitement | -0.003 |
it | -0.003 |
sudden | -0.003 |
delight | -0.003 |
Mill | -0.003 |
Token | interrupts |
Token ID | 48237 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ems | +0.064 |
arl | +0.063 |
ppy | +0.061 |
ophone | +0.060 |
wy | +0.059 |
Neg logit contributions | |
it | -0.039 |
excitement | -0.038 |
the | -0.038 |
delight | -0.038 |
a | -0.037 |
Token | him |
Token ID | 683 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
excitement | +0.118 |
Mill | +0.107 |
it | +0.106 |
delight | +0.102 |
Frankie | +0.094 |
Neg logit contributions | |
ems | -0.677 |
ppy | -0.655 |
arl | -0.630 |
ophone | -0.629 |
oke | -0.612 |
Token | and |
Token ID | 290 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
it | +0.081 |
excitement | +0.074 |
a | +0.072 |
an | +0.072 |
the | +0.070 |
Neg logit contributions | |
ems | -0.267 |
ppy | -0.254 |
arl | -0.253 |
wy | -0.248 |
ophone | -0.247 |
Token | says |
Token ID | 1139 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ppy | +0.045 |
ems | +0.043 |
arl | +0.043 |
ophone | +0.043 |
wy | +0.043 |
Neg logit contributions | |
it | -0.039 |
her | -0.037 |
the | -0.037 |
excitement | -0.037 |
a | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
excitement | +0.010 |
it | +0.010 |
Mill | +0.009 |
delight | +0.009 |
an | +0.009 |
Neg logit contributions | |
ems | -0.029 |
ppy | -0.028 |
ophone | -0.027 |
arl | -0.027 |
wy | -0.026 |
Token | " |
Token ID | 366 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
it | +0.005 |
excitement | +0.004 |
the | +0.004 |
an | +0.004 |
a | +0.003 |
Neg logit contributions | |
ems | -0.024 |
ppy | -0.023 |
wy | -0.023 |
ophone | -0.023 |
ets | -0.022 |
Token | When |
Token ID | 2215 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
ems | +0.014 |
ppy | +0.013 |
arl | +0.012 |
ophone | +0.012 |
oke | +0.012 |
Neg logit contributions | |
excitement | -0.011 |
delight | -0.011 |
it | -0.011 |
Mill | -0.010 |
Frankie | -0.010 |
Token | Sally |
Token ID | 25737 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
sudden | +0.048 |
Its | +0.047 |
branches | +0.047 |
Frankie | +0.045 |
delight | +0.044 |
Neg logit contributions | |
ems | -0.068 |
ppy | -0.061 |
ophone | -0.057 |
arl | -0.056 |
osaurs | -0.056 |
Token | arrived |
Token ID | 5284 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
ems | +0.003 |
ppy | +0.002 |
arl | +0.002 |
ophone | +0.002 |
wy | +0.002 |
Neg logit contributions | |
it | -0.001 |
excitement | -0.001 |
Mill | -0.001 |
delight | -0.001 |
Frankie | -0.001 |
Token | at |
Token ID | 379 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
ems | +0.042 |
ppy | +0.040 |
arl | +0.039 |
oke | +0.038 |
ophone | +0.038 |
Neg logit contributions | |
excitement | -0.025 |
sudden | -0.024 |
delight | -0.024 |
Mill | -0.023 |
Frankie | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ems | +0.131 |
ppy | +0.128 |
arl | +0.124 |
ophone | +0.123 |
wy | +0.118 |
Neg logit contributions | |
sudden | -0.024 |
excitement | -0.022 |
delight | -0.020 |
Its | -0.017 |
it | -0.016 |
Token | appointed |
Token ID | 9899 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
ems | +0.021 |
ppy | +0.020 |
arl | +0.019 |
ophone | +0.019 |
oke | +0.018 |
Neg logit contributions | |
excitement | -0.010 |
Mill | -0.010 |
Frankie | -0.009 |
it | -0.009 |
delight | -0.009 |
Token | place |
Token ID | 1295 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
excitement | +0.257 |
Mill | +0.245 |
it | +0.244 |
delight | +0.240 |
sudden | +0.238 |
Neg logit contributions | |
ems | -0.531 |
ppy | -0.509 |
ophone | -0.488 |
arl | -0.482 |
oke | -0.470 |
Token | , |
Token ID | 11 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
ems | +0.108 |
ppy | +0.104 |
ophone | +0.100 |
oke | +0.098 |
arl | +0.097 |
Neg logit contributions | |
excitement | -0.054 |
sudden | -0.052 |
delight | -0.051 |
Mill | -0.048 |
Frankie | -0.048 |
Token | she |
Token ID | 673 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ems | +0.008 |
ppy | +0.007 |
ophone | +0.007 |
oke | +0.006 |
arl | +0.006 |
Neg logit contributions | |
sudden | -0.004 |
delight | -0.004 |
Frankie | -0.003 |
excitement | -0.003 |
purpose | -0.003 |
Token | found |
Token ID | 1043 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
it | +0.022 |
excitement | +0.021 |
an | +0.020 |
Mill | +0.020 |
the | +0.020 |
Neg logit contributions | |
ems | -0.036 |
arl | -0.036 |
ppy | -0.034 |
wy | -0.033 |
ophone | -0.033 |
Token | Jake |
Token ID | 14757 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
sudden | +0.015 |
excitement | +0.013 |
delight | +0.013 |
Frankie | +0.011 |
purpose | +0.011 |
Neg logit contributions | |
ems | -0.055 |
ppy | -0.055 |
ophone | -0.054 |
wy | -0.052 |
cher | -0.051 |
Token | reached |
Token ID | 4251 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
ems | +0.010 |
arl | +0.009 |
ppy | +0.009 |
wy | +0.009 |
ophone | +0.009 |
Neg logit contributions | |
it | -0.006 |
excitement | -0.006 |
the | -0.005 |
an | -0.005 |
a | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ems | +0.151 |
ppy | +0.142 |
ophone | +0.142 |
arl | +0.137 |
ets | +0.133 |
Neg logit contributions | |
sudden | -0.045 |
excitement | -0.041 |
delight | -0.039 |
Frankie | -0.038 |
Mill | -0.037 |
Token | special |
Token ID | 2041 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
excitement | +0.011 |
Mill | +0.011 |
delight | +0.010 |
Frankie | +0.010 |
an | +0.009 |
Neg logit contributions | |
ems | -0.033 |
ppy | -0.032 |
arl | -0.032 |
ophone | -0.031 |
oke | -0.031 |
Token | caf |
Token ID | 19945 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
ems | +0.013 |
ppy | +0.012 |
arl | +0.012 |
ophone | +0.012 |
oke | +0.011 |
Neg logit contributions | |
excitement | -0.007 |
Mill | -0.007 |
delight | -0.007 |
Frankie | -0.007 |
sudden | -0.007 |
Token | Ã |
Token ID | 5746 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
it | +0.217 |
excitement | +0.210 |
Mill | +0.199 |
delight | +0.197 |
sight | +0.190 |
Neg logit contributions | |
ems | -0.537 |
ppy | -0.509 |
arl | -0.489 |
ophone | -0.488 |
wy | -0.486 |
Token | © |
Token ID | 16224 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
it | +0.196 |
excitement | +0.189 |
Mill | +0.180 |
delight | +0.179 |
sight | +0.174 |
Neg logit contributions | |
ems | -0.469 |
ppy | -0.443 |
arl | -0.429 |
ophone | -0.429 |
wy | -0.427 |
Token | . |
Token ID | 13 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
it | +0.184 |
excitement | +0.169 |
Mill | +0.160 |
delight | +0.156 |
the | +0.155 |
Neg logit contributions | |
ems | -0.606 |
ppy | -0.571 |
wy | -0.559 |
arl | -0.556 |
ophone | -0.554 |
Token | It |
Token ID | 632 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
excitement | +0.005 |
delight | +0.005 |
sudden | +0.005 |
it | +0.005 |
Frankie | +0.005 |
Neg logit contributions | |
ems | -0.014 |
ophone | -0.014 |
ppy | -0.014 |
arl | -0.013 |
ets | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
it | +0.021 |
excitement | +0.021 |
Mill | +0.020 |
delight | +0.019 |
sudden | +0.019 |
Neg logit contributions | |
ems | -0.062 |
ppy | -0.059 |
arl | -0.058 |
ophone | -0.057 |
wy | -0.056 |
Token | time |
Token ID | 640 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
ems | +0.004 |
ppy | +0.004 |
ophone | +0.004 |
rant | +0.004 |
wy | +0.004 |
Neg logit contributions | |
excitement | -0.001 |
delight | -0.001 |
sudden | -0.001 |
Mill | -0.001 |
Frankie | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
excitement | +0.005 |
delight | +0.005 |
Mill | +0.005 |
sudden | +0.005 |
Frankie | +0.005 |
Neg logit contributions | |
ems | -0.010 |
ppy | -0.009 |
ophone | -0.009 |
arl | -0.009 |
oke | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
sudden | +0.047 |
Frankie | +0.047 |
Its | +0.045 |
Mill | +0.042 |
mistakes | +0.037 |
Neg logit contributions | |
ppy | -0.126 |
ems | -0.121 |
wy | -0.112 |
arl | -0.112 |
ophone | -0.111 |
Token | friend |
Token ID | 1545 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
excitement | +0.014 |
delight | +0.014 |
Its | +0.014 |
Mill | +0.013 |
Frankie | +0.013 |
Neg logit contributions | |
ems | -0.038 |
ppy | -0.038 |
ophone | -0.036 |
arl | -0.035 |
ber | -0.034 |
Token | Ch |
Token ID | 609 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
ppy | +0.067 |
ems | +0.067 |
ophone | +0.061 |
oke | +0.058 |
wy | +0.056 |
Neg logit contributions | |
excitement | -0.037 |
delight | -0.035 |
sudden | -0.033 |
sight | -0.032 |
it | -0.031 |
Token | lo |
Token ID | 5439 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
excitement | +0.086 |
it | +0.084 |
delight | +0.081 |
sudden | +0.080 |
Mill | +0.080 |
Neg logit contributions | |
ppy | -0.085 |
ems | -0.084 |
arl | -0.077 |
ophone | -0.076 |
oke | -0.074 |
Token | Ã |
Token ID | 5746 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ems | +0.090 |
ppy | +0.082 |
arl | +0.081 |
wy | +0.075 |
ophone | +0.075 |
Neg logit contributions | |
it | -0.077 |
Mill | -0.076 |
Frankie | -0.072 |
the | -0.071 |
an | -0.071 |
Token | © |
Token ID | 16224 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
excitement | +0.243 |
it | +0.232 |
delight | +0.230 |
Mill | +0.229 |
sudden | +0.220 |
Neg logit contributions | |
ems | -0.416 |
ppy | -0.401 |
ophone | -0.379 |
arl | -0.375 |
oke | -0.360 |
Token | when |
Token ID | 618 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
excitement | +0.353 |
it | +0.348 |
Mill | +0.341 |
delight | +0.336 |
sudden | +0.330 |
Neg logit contributions | |
ems | -0.431 |
ppy | -0.404 |
ophone | -0.387 |
arl | -0.383 |
oke | -0.372 |
Token | she |
Token ID | 673 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ems | +0.084 |
ppy | +0.081 |
ophone | +0.077 |
ider | +0.075 |
ber | +0.072 |
Neg logit contributions | |
delight | -0.057 |
excitement | -0.054 |
Frankie | -0.051 |
Mill | -0.049 |
Its | -0.049 |
Token | heard |
Token ID | 2982 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
it | +0.038 |
sudden | +0.036 |
an | +0.035 |
a | +0.034 |
the | +0.034 |
Neg logit contributions | |
ems | -0.064 |
arl | -0.063 |
ppy | -0.058 |
wy | -0.058 |
ophone | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
excitement | +0.032 |
Frankie | +0.031 |
sudden | +0.030 |
delight | +0.029 |
Mill | +0.028 |
Neg logit contributions | |
ems | -0.125 |
ppy | -0.120 |
ophone | -0.118 |
arl | -0.114 |
oke | -0.111 |
Token | noise |
Token ID | 7838 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
Mill | +0.015 |
excitement | +0.015 |
Frankie | +0.014 |
delight | +0.014 |
an | +0.014 |
Neg logit contributions | |
ems | -0.034 |
ppy | -0.033 |
arl | -0.033 |
oke | -0.033 |
ophone | -0.032 |
Token | she |
Token ID | 673 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
excitement | +0.029 |
delight | +0.029 |
Frankie | +0.027 |
Mill | +0.026 |
Its | +0.025 |
Neg logit contributions | |
ems | -0.060 |
ppy | -0.057 |
ophone | -0.054 |
arl | -0.052 |
ber | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
it | +0.021 |
excitement | +0.020 |
Mill | +0.019 |
sudden | +0.019 |
an | +0.019 |
Neg logit contributions | |
ems | -0.041 |
arl | -0.039 |
oke | -0.037 |
ppy | -0.037 |
ophone | -0.037 |
Token | Ch |
Token ID | 609 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
ems | +0.027 |
ppy | +0.026 |
ophone | +0.024 |
arl | +0.024 |
oke | +0.023 |
Neg logit contributions | |
excitement | -0.012 |
Mill | -0.011 |
delight | -0.011 |
it | -0.011 |
Frankie | -0.011 |
Token | lo |
Token ID | 5439 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
excitement | +0.083 |
it | +0.081 |
delight | +0.078 |
Mill | +0.077 |
sudden | +0.077 |
Neg logit contributions | |
ems | -0.087 |
ppy | -0.084 |
arl | -0.079 |
ophone | -0.078 |
oke | -0.076 |
Token | Ã |
Token ID | 5746 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ems | +0.067 |
ppy | +0.058 |
arl | +0.057 |
ider | +0.052 |
wy | +0.051 |
Neg logit contributions | |
it | -0.091 |
Mill | -0.090 |
excitement | -0.087 |
Frankie | -0.087 |
the | -0.085 |
Token | © |
Token ID | 16224 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
it | +0.344 |
excitement | +0.342 |
Mill | +0.335 |
delight | +0.327 |
an | +0.324 |
Neg logit contributions | |
ems | -0.310 |
ppy | -0.284 |
arl | -0.275 |
ophone | -0.272 |
oke | -0.263 |
Token | went |
Token ID | 1816 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
it | +0.430 |
excitement | +0.413 |
Mill | +0.410 |
an | +0.403 |
a | +0.397 |
Neg logit contributions | |
ems | -0.354 |
arl | -0.320 |
ppy | -0.313 |
ophone | -0.308 |
oke | -0.304 |
Token | deeper |
Token ID | 9211 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
ems | +0.030 |
ppy | +0.029 |
ophone | +0.028 |
arl | +0.027 |
oke | +0.026 |
Neg logit contributions | |
excitement | -0.015 |
delight | -0.014 |
Mill | -0.014 |
it | -0.014 |
sudden | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
ems | +0.139 |
ppy | +0.134 |
arl | +0.127 |
ophone | +0.124 |
ets | +0.123 |
Neg logit contributions | |
excitement | -0.092 |
delight | -0.090 |
Mill | -0.088 |
it | -0.086 |
Frankie | -0.086 |
Token | deeper |
Token ID | 9211 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
ems | +0.010 |
arl | +0.009 |
ppy | +0.009 |
oke | +0.009 |
wy | +0.009 |
Neg logit contributions | |
it | -0.006 |
excitement | -0.005 |
the | -0.005 |
Mill | -0.005 |
an | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
ems | +0.146 |
ppy | +0.140 |
arl | +0.133 |
ophone | +0.132 |
ets | +0.128 |
Neg logit contributions | |
excitement | -0.086 |
delight | -0.082 |
Mill | -0.082 |
it | -0.082 |
Frankie | -0.079 |
Token | event |
Token ID | 1785 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
ems | +0.126 |
ppy | +0.121 |
ophone | +0.115 |
arl | +0.115 |
oke | +0.112 |
Neg logit contributions | |
excitement | -0.056 |
it | -0.054 |
Mill | -0.052 |
delight | -0.052 |
sudden | -0.050 |
Token | was |
Token ID | 373 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ems | +0.096 |
ppy | +0.092 |
arl | +0.088 |
ophone | +0.088 |
wy | +0.085 |
Neg logit contributions | |
excitement | -0.043 |
it | -0.042 |
Mill | -0.041 |
delight | -0.040 |
Frankie | -0.038 |
Token | just |
Token ID | 655 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
excitement | +0.011 |
it | +0.010 |
Mill | +0.010 |
delight | +0.010 |
sudden | +0.010 |
Neg logit contributions | |
ems | -0.037 |
ppy | -0.035 |
ophone | -0.034 |
arl | -0.034 |
oke | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
excitement | +0.012 |
sudden | +0.011 |
Mill | +0.011 |
delight | +0.011 |
it | +0.011 |
Neg logit contributions | |
ems | -0.049 |
ppy | -0.047 |
ophone | -0.046 |
arl | -0.045 |
oke | -0.044 |
Token | pre |
Token ID | 662 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
excitement | +0.021 |
it | +0.020 |
Mill | +0.019 |
delight | +0.019 |
Frankie | +0.018 |
Neg logit contributions | |
ems | -0.056 |
ppy | -0.054 |
ophone | -0.052 |
arl | -0.052 |
oke | -0.050 |
Token | lude |
Token ID | 38792 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
it | +0.102 |
the | +0.096 |
excitement | +0.093 |
delight | +0.090 |
Its | +0.089 |
Neg logit contributions | |
ems | -0.086 |
ophone | -0.081 |
ppy | -0.078 |
arl | -0.075 |
ccoli | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
excitement | +0.209 |
it | +0.208 |
Mill | +0.197 |
delight | +0.193 |
an | +0.183 |
Neg logit contributions | |
ems | -0.564 |
ppy | -0.538 |
arl | -0.523 |
ophone | -0.519 |
wy | -0.507 |
Token | Over |
Token ID | 3827 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
excitement | +0.010 |
it | +0.010 |
sudden | +0.010 |
Mill | +0.009 |
delight | +0.009 |
Neg logit contributions | |
ems | -0.024 |
ppy | -0.022 |
arl | -0.022 |
ophone | -0.022 |
oke | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
excitement | +0.087 |
Mill | +0.083 |
it | +0.083 |
delight | +0.081 |
Frankie | +0.078 |
Neg logit contributions | |
ems | -0.220 |
ppy | -0.211 |
ophone | -0.202 |
arl | -0.200 |
oke | -0.196 |
Token | next |
Token ID | 1306 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
ems | +0.012 |
ppy | +0.011 |
ophone | +0.011 |
arl | +0.010 |
oke | +0.010 |
Neg logit contributions | |
excitement | -0.007 |
it | -0.007 |
delight | -0.006 |
Mill | -0.006 |
sudden | -0.006 |
Token | few |
Token ID | 1178 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ems | +0.116 |
ppy | +0.110 |
ophone | +0.105 |
arl | +0.104 |
wy | +0.103 |
Neg logit contributions | |
excitement | -0.061 |
it | -0.059 |
Mill | -0.057 |
delight | -0.056 |
sudden | -0.055 |
Token | little |
Token ID | 1310 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
Mill | +0.015 |
it | +0.014 |
Frankie | +0.014 |
excitement | +0.013 |
an | +0.013 |
Neg logit contributions | |
ems | -0.028 |
ppy | -0.028 |
arl | -0.027 |
ophone | -0.027 |
oke | -0.026 |
Token | confused |
Token ID | 10416 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
ems | +0.002 |
ppy | +0.002 |
oke | +0.002 |
ophone | +0.002 |
arl | +0.002 |
Neg logit contributions | |
Mill | -0.002 |
Frankie | -0.002 |
it | -0.002 |
excitement | -0.002 |
sudden | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
excitement | +0.007 |
sudden | +0.007 |
Mill | +0.007 |
delight | +0.006 |
Frankie | +0.006 |
Neg logit contributions | |
ems | -0.014 |
ppy | -0.014 |
oke | -0.013 |
arl | -0.013 |
ophone | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
excitement | +0.027 |
Mill | +0.026 |
delight | +0.025 |
sudden | +0.025 |
Frankie | +0.025 |
Neg logit contributions | |
ems | -0.065 |
ppy | -0.063 |
oke | -0.060 |
arl | -0.060 |
ophone | -0.060 |
Token | cat |
Token ID | 3797 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
ems | +0.018 |
ppy | +0.017 |
ophone | +0.016 |
arl | +0.016 |
oke | +0.016 |
Neg logit contributions | |
excitement | -0.008 |
Mill | -0.008 |
it | -0.008 |
delight | -0.008 |
Frankie | -0.008 |
Token | clarified |
Token ID | 28464 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
it | +0.035 |
excitement | +0.034 |
Mill | +0.033 |
delight | +0.032 |
an | +0.031 |
Neg logit contributions | |
ems | -0.055 |
ppy | -0.052 |
arl | -0.051 |
ophone | -0.050 |
oke | -0.048 |
Token | by |
Token ID | 416 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
excitement | +0.212 |
it | +0.208 |
Mill | +0.199 |
delight | +0.195 |
an | +0.187 |
Neg logit contributions | |
ems | -0.563 |
ppy | -0.535 |
ophone | -0.522 |
arl | -0.516 |
oke | -0.505 |
Token | showing |
Token ID | 4478 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
excitement | +0.038 |
Mill | +0.037 |
sudden | +0.035 |
Frankie | +0.035 |
delight | +0.035 |
Neg logit contributions | |
ems | -0.098 |
ppy | -0.096 |
arl | -0.092 |
ophone | -0.091 |
oke | -0.090 |
Token | him |
Token ID | 683 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ems | +0.163 |
ppy | +0.159 |
ophone | +0.151 |
arl | +0.148 |
ets | +0.147 |
Neg logit contributions | |
sudden | -0.058 |
excitement | -0.046 |
Mill | -0.046 |
Frankie | -0.041 |
sight | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
excitement | +0.066 |
sudden | +0.066 |
Mill | +0.063 |
delight | +0.059 |
Frankie | +0.056 |
Neg logit contributions | |
ems | -0.260 |
ppy | -0.252 |
ophone | -0.247 |
arl | -0.233 |
wy | -0.232 |
Token | big |
Token ID | 1263 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Mill | +0.010 |
excitement | +0.009 |
delight | +0.009 |
Frankie | +0.009 |
it | +0.008 |
Neg logit contributions | |
ems | -0.022 |
ophone | -0.021 |
ppy | -0.020 |
arl | -0.020 |
oke | -0.019 |
Token | perform |
Token ID | 1620 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
excitement | +0.014 |
sudden | +0.014 |
Frankie | +0.013 |
Mill | +0.013 |
Its | +0.013 |
Neg logit contributions | |
ems | -0.022 |
ppy | -0.021 |
arl | -0.020 |
ophone | -0.020 |
ets | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
ems | +0.011 |
ppy | +0.011 |
arl | +0.010 |
oke | +0.010 |
ophone | +0.010 |
Neg logit contributions | |
it | -0.004 |
excitement | -0.003 |
an | -0.003 |
a | -0.003 |
the | -0.003 |
Token | N |
Token ID | 399 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ems | +0.011 |
ppy | +0.010 |
ophone | +0.010 |
arl | +0.010 |
oke | +0.010 |
Neg logit contributions | |
Mill | -0.006 |
Frankie | -0.006 |
it | -0.006 |
excitement | -0.006 |
delight | -0.006 |
Token | aughty |
Token ID | 28496 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
it | +0.131 |
an | +0.129 |
a | +0.127 |
baby | +0.125 |
Mill | +0.124 |
Neg logit contributions | |
ems | -0.126 |
ophone | -0.119 |
wy | -0.113 |
osaurs | -0.111 |
arl | -0.108 |
Token | Fox |
Token ID | 5426 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
ems | +0.119 |
arl | +0.114 |
ppy | +0.113 |
ophone | +0.112 |
oke | +0.107 |
Neg logit contributions | |
it | -0.060 |
excitement | -0.058 |
Mill | -0.055 |
delight | -0.055 |
an | -0.055 |
Token | Stack |
Token ID | 23881 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ems | +0.148 |
arl | +0.144 |
ppy | +0.137 |
wy | +0.134 |
ophone | +0.133 |
Neg logit contributions | |
it | -0.075 |
a | -0.068 |
the | -0.067 |
an | -0.066 |
excitement | -0.066 |
Token | Trick |
Token ID | 30028 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
it | +0.303 |
the | +0.276 |
an | +0.271 |
a | +0.271 |
excitement | +0.267 |
Neg logit contributions | |
ems | -0.458 |
arl | -0.446 |
ppy | -0.430 |
ophone | -0.416 |
oke | -0.414 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
it | +0.283 |
a | +0.273 |
an | +0.265 |
the | +0.249 |
top | +0.245 |
Neg logit contributions | |
ems | -0.547 |
arl | -0.502 |
ppy | -0.495 |
wy | -0.491 |
oke | -0.488 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
excitement | +0.001 |
delight | +0.001 |
sudden | +0.001 |
Mill | +0.001 |
it | +0.001 |
Neg logit contributions | |
ems | -0.004 |
ppy | -0.003 |
ophone | -0.003 |
arl | -0.003 |
oke | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
ems | +0.021 |
ppy | +0.020 |
ophone | +0.019 |
arl | +0.019 |
oke | +0.019 |
Neg logit contributions | |
excitement | -0.007 |
delight | -0.006 |
Mill | -0.006 |
it | -0.006 |
Frankie | -0.006 |
Token | He |
Token ID | 1544 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ems | +0.017 |
ppy | +0.016 |
ophone | +0.015 |
arl | +0.015 |
wy | +0.015 |
Neg logit contributions | |
excitement | -0.006 |
Mill | -0.006 |
it | -0.006 |
delight | -0.005 |
Frankie | -0.005 |
Token | ere |
Token ID | 567 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
ems | +0.134 |
ppy | +0.124 |
ophone | +0.115 |
arl | +0.114 |
oke | +0.108 |
Neg logit contributions | |
excitement | -0.189 |
it | -0.185 |
Mill | -0.183 |
delight | -0.182 |
sudden | -0.178 |
Token | and |
Token ID | 290 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
it | +0.065 |
excitement | +0.064 |
Mill | +0.063 |
delight | +0.062 |
an | +0.061 |
Neg logit contributions | |
ems | -0.069 |
ppy | -0.064 |
arl | -0.061 |
ophone | -0.061 |
oke | -0.058 |
Token | sum |
Token ID | 2160 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
excitement | +0.003 |
it | +0.003 |
Mill | +0.002 |
delight | +0.002 |
sudden | +0.002 |
Neg logit contributions | |
ems | -0.006 |
ppy | -0.006 |
ophone | -0.005 |
arl | -0.005 |
oke | -0.005 |
Token | ac |
Token ID | 330 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
it | +0.119 |
her | +0.105 |
the | +0.105 |
excitement | +0.102 |
an | +0.102 |
Neg logit contributions | |
ems | -0.150 |
arl | -0.136 |
ophone | -0.135 |
ppy | -0.135 |
oke | -0.131 |
Token | and |
Token ID | 290 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
ems | +0.113 |
ppy | +0.109 |
ophone | +0.100 |
ets | +0.100 |
oke | +0.100 |
Neg logit contributions | |
excitement | -0.111 |
Mill | -0.110 |
it | -0.107 |
Frankie | -0.107 |
delight | -0.105 |
Token | tam |
Token ID | 21885 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
excitement | +0.003 |
it | +0.003 |
Mill | +0.003 |
delight | +0.003 |
sudden | +0.003 |
Neg logit contributions | |
ems | -0.008 |
ppy | -0.007 |
ophone | -0.007 |
arl | -0.007 |
oke | -0.007 |
Token | ar |
Token ID | 283 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
it | +0.373 |
an | +0.365 |
excitement | +0.358 |
a | +0.355 |
the | +0.351 |
Neg logit contributions | |
ems | -0.369 |
ppy | -0.337 |
arl | -0.327 |
ophone | -0.322 |
wy | -0.320 |
Token | ind |
Token ID | 521 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
it | +0.045 |
the | +0.041 |
excitement | +0.041 |
an | +0.041 |
Mill | +0.041 |
Neg logit contributions | |
ems | -0.062 |
ppy | -0.057 |
arl | -0.057 |
ophone | -0.055 |
wy | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
ems | +0.021 |
arl | +0.019 |
ophone | +0.019 |
ider | +0.019 |
ppy | +0.018 |
Neg logit contributions | |
it | -0.022 |
the | -0.022 |
a | -0.021 |
an | -0.021 |
her | -0.021 |
Token | lemon |
Token ID | 18873 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
excitement | +0.003 |
it | +0.003 |
delight | +0.003 |
Mill | +0.003 |
an | +0.003 |
Neg logit contributions | |
ems | -0.006 |
ppy | -0.006 |
ophone | -0.006 |
arl | -0.006 |
oke | -0.006 |
Token | grass |
Token ID | 8701 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
it | +0.028 |
excitement | +0.027 |
Mill | +0.026 |
delight | +0.026 |
an | +0.026 |
Neg logit contributions | |
ems | -0.028 |
ppy | -0.026 |
ophone | -0.025 |
arl | -0.025 |
oke | -0.024 |
Token | many |
Token ID | 867 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ppy | +0.004 |
ems | +0.004 |
ets | +0.004 |
arl | +0.004 |
wy | +0.004 |
Neg logit contributions | |
Mill | -0.001 |
Frankie | -0.001 |
sudden | -0.001 |
excitement | -0.001 |
Samantha | -0.001 |
Token | ways |
Token ID | 2842 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
ems | +0.185 |
ppy | +0.180 |
ets | +0.176 |
wy | +0.168 |
oke | +0.168 |
Neg logit contributions | |
Mill | -0.091 |
Frankie | -0.087 |
excitement | -0.078 |
an | -0.077 |
Bobby | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
excitement | +0.050 |
sudden | +0.047 |
delight | +0.046 |
Mill | +0.045 |
Frankie | +0.044 |
Neg logit contributions | |
ems | -0.104 |
ppy | -0.102 |
ophone | -0.097 |
arl | -0.094 |
oke | -0.093 |
Token | The |
Token ID | 383 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ems | +0.001 |
ppy | +0.001 |
oke | +0.001 |
ophone | +0.001 |
arl | +0.001 |
Neg logit contributions | |
excitement | -0.000 |
sudden | -0.000 |
delight | -0.000 |
it | -0.000 |
sight | -0.000 |
Token | all |
Token ID | 477 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
excitement | +0.015 |
it | +0.014 |
Mill | +0.014 |
delight | +0.014 |
sudden | +0.013 |
Neg logit contributions | |
ems | -0.034 |
ppy | -0.033 |
arl | -0.032 |
ophone | -0.032 |
wy | -0.031 |
Token | igator |
Token ID | 23823 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
ems | +0.096 |
ppy | +0.085 |
arl | +0.076 |
ophone | +0.075 |
oke | +0.068 |
Neg logit contributions | |
excitement | -0.255 |
it | -0.252 |
Mill | -0.249 |
delight | -0.247 |
Frankie | -0.243 |
Token | wanted |
Token ID | 2227 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
ems | +0.604 |
arl | +0.583 |
ppy | +0.571 |
ophone | +0.547 |
wy | +0.534 |
Neg logit contributions | |
it | -0.327 |
excitement | -0.322 |
delight | -0.303 |
Mill | -0.299 |
sudden | -0.295 |
Token | to |
Token ID | 284 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
sudden | +0.004 |
excitement | +0.004 |
delight | +0.004 |
Mill | +0.004 |
Frankie | +0.004 |
Neg logit contributions | |
ems | -0.006 |
ppy | -0.006 |
ophone | -0.006 |
ets | -0.006 |
oke | -0.006 |
Token | be |
Token ID | 307 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
sudden | +0.018 |
excitement | +0.017 |
Mill | +0.017 |
Frankie | +0.016 |
delight | +0.016 |
Neg logit contributions | |
ems | -0.030 |
ppy | -0.029 |
ophone | -0.027 |
arl | -0.027 |
wy | -0.025 |
Token | flexible |
Token ID | 12846 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ems | +0.036 |
ppy | +0.035 |
ophone | +0.033 |
wy | +0.032 |
arl | +0.032 |
Neg logit contributions | |
excitement | -0.012 |
Mill | -0.012 |
sudden | -0.012 |
delight | -0.012 |
Frankie | -0.011 |
Token | too |
Token ID | 1165 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
excitement | +0.019 |
Mill | +0.019 |
it | +0.018 |
delight | +0.018 |
sudden | +0.018 |
Neg logit contributions | |
ems | -0.043 |
ppy | -0.041 |
ophone | -0.039 |
arl | -0.038 |
oke | -0.038 |
Token | ! |
Token ID | 0 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ems | +0.041 |
ppy | +0.039 |
arl | +0.037 |
ophone | +0.037 |
oke | +0.037 |
Neg logit contributions | |
excitement | -0.021 |
Mill | -0.020 |
sudden | -0.020 |
delight | -0.020 |
it | -0.020 |
Token | We |
Token ID | 775 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
excitement | +0.023 |
it | +0.022 |
delight | +0.021 |
Mill | +0.021 |
sudden | +0.021 |
Neg logit contributions | |
ems | -0.044 |
ppy | -0.042 |
ophone | -0.040 |
arl | -0.040 |
oke | -0.039 |
Token | â |
Token ID | 22940 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
it | +0.036 |
excitement | +0.035 |
Mill | +0.034 |
delight | +0.033 |
an | +0.033 |
Neg logit contributions | |
ems | -0.045 |
arl | -0.042 |
ppy | -0.042 |
ophone | -0.041 |
oke | -0.040 |
Token | € |
Token ID | 26391 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
excitement | +0.030 |
it | +0.029 |
delight | +0.029 |
Mill | +0.029 |
Frankie | +0.028 |
Neg logit contributions | |
ems | -0.034 |
ppy | -0.032 |
ophone | -0.031 |
arl | -0.030 |
ider | -0.029 |
Token | ™ |
Token ID | 8151 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ems | +0.191 |
ppy | +0.179 |
ophone | +0.171 |
arl | +0.167 |
oke | +0.164 |
Neg logit contributions | |
excitement | -0.155 |
Mill | -0.148 |
delight | -0.147 |
it | -0.147 |
sudden | -0.143 |
Token | ll |
Token ID | 297 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
ems | +0.137 |
ppy | +0.126 |
ophone | +0.119 |
arl | +0.118 |
wy | +0.116 |
Neg logit contributions | |
it | -0.113 |
excitement | -0.111 |
Mill | -0.110 |
an | -0.106 |
delight | -0.105 |
Token | use |
Token ID | 779 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
ems | +0.581 |
ppy | +0.558 |
ophone | +0.530 |
arl | +0.525 |
wy | +0.512 |
Neg logit contributions | |
excitement | -0.321 |
it | -0.307 |
Mill | -0.305 |
delight | -0.301 |
sudden | -0.295 |
Token | it |
Token ID | 340 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
excitement | +0.027 |
sudden | +0.025 |
delight | +0.025 |
Mill | +0.024 |
Frankie | +0.023 |
Neg logit contributions | |
ems | -0.082 |
ppy | -0.079 |
ophone | -0.077 |
arl | -0.075 |
wy | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
it | +0.014 |
Mill | +0.013 |
excitement | +0.013 |
an | +0.013 |
a | +0.012 |
Neg logit contributions | |
ems | -0.039 |
ppy | -0.037 |
arl | -0.036 |
oke | -0.036 |
ophone | -0.035 |
Token | chop |
Token ID | 30506 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
excitement | +0.013 |
Mill | +0.012 |
it | +0.012 |
sudden | +0.012 |
delight | +0.012 |
Neg logit contributions | |
ems | -0.024 |
ppy | -0.023 |
arl | -0.022 |
ophone | -0.022 |
wy | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ems | +0.111 |
ppy | +0.106 |
ophone | +0.102 |
arl | +0.102 |
wy | +0.100 |
Neg logit contributions | |
excitement | -0.035 |
Mill | -0.032 |
delight | -0.032 |
it | -0.031 |
sudden | -0.030 |
Token | nos |
Token ID | 43630 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Mill | +0.016 |
Frankie | +0.016 |
it | +0.015 |
excitement | +0.015 |
delight | +0.014 |
Neg logit contributions | |
ems | -0.062 |
ppy | -0.060 |
ophone | -0.057 |
arl | -0.057 |
ets | -0.054 |
Token | y |
Token ID | 88 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ems | +0.015 |
ppy | +0.014 |
ophone | +0.013 |
arl | +0.013 |
wy | +0.012 |
Neg logit contributions | |
excitement | -0.025 |
it | -0.025 |
Mill | -0.025 |
delight | -0.024 |
sudden | -0.024 |
Token | cat |
Token ID | 3797 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
ems | +0.160 |
ppy | +0.154 |
ophone | +0.145 |
arl | +0.141 |
oke | +0.138 |
Neg logit contributions | |
excitement | -0.092 |
it | -0.089 |
Mill | -0.089 |
delight | -0.087 |
Frankie | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
excitement | +0.049 |
it | +0.047 |
delight | +0.046 |
Mill | +0.046 |
sudden | +0.044 |
Neg logit contributions | |
ems | -0.116 |
ppy | -0.112 |
ophone | -0.107 |
arl | -0.105 |
oke | -0.103 |
Token | Wh |
Token ID | 854 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
excitement | +0.014 |
delight | +0.014 |
purpose | +0.013 |
sight | +0.013 |
sudden | +0.012 |
Neg logit contributions | |
ppy | -0.018 |
ems | -0.018 |
ophone | -0.016 |
oke | -0.015 |
ets | -0.015 |
Token | isk |
Token ID | 1984 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
ems | +0.010 |
ophone | +0.009 |
arl | +0.009 |
oke | +0.008 |
ber | +0.008 |
Neg logit contributions | |
her | -0.027 |
Mill | -0.026 |
an | -0.026 |
a | -0.025 |
Frankie | -0.025 |
Token | ers |
Token ID | 364 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
ems | +0.556 |
arl | +0.508 |
ppy | +0.499 |
ophone | +0.473 |
oke | +0.461 |
Neg logit contributions | |
it | -0.679 |
her | -0.639 |
Mill | -0.630 |
the | -0.627 |
an | -0.626 |
Token | , |
Token ID | 11 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
excitement | +0.064 |
it | +0.059 |
delight | +0.059 |
Mill | +0.059 |
sudden | +0.057 |
Neg logit contributions | |
ems | -0.152 |
ppy | -0.147 |
ophone | -0.139 |
arl | -0.137 |
oke | -0.136 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
excitement | +0.018 |
delight | +0.017 |
Mill | +0.016 |
it | +0.016 |
sudden | +0.016 |
Neg logit contributions | |
ems | -0.023 |
ppy | -0.022 |
ophone | -0.020 |
arl | -0.019 |
oke | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ems | +0.033 |
ppy | +0.032 |
ophone | +0.031 |
arl | +0.031 |
oke | +0.030 |
Neg logit contributions | |
excitement | -0.009 |
delight | -0.008 |
Mill | -0.007 |
Frankie | -0.007 |
sudden | -0.006 |
Token | searching |
Token ID | 10342 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
excitement | +0.019 |
Mill | +0.019 |
it | +0.018 |
Frankie | +0.018 |
delight | +0.018 |
Neg logit contributions | |
ems | -0.034 |
ppy | -0.032 |
ophone | -0.031 |
arl | -0.030 |
oke | -0.029 |
Token | � |
Token ID | 241 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ems | +0.029 |
ppy | +0.027 |
ophone | +0.026 |
arl | +0.026 |
wy | +0.025 |
Neg logit contributions | |
excitement | -0.025 |
it | -0.024 |
Mill | -0.024 |
delight | -0.024 |
sudden | -0.023 |
Token | I |
Token ID | 40 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
excitement | +0.022 |
delight | +0.021 |
Mill | +0.021 |
Frankie | +0.020 |
it | +0.020 |
Neg logit contributions | |
ems | -0.039 |
ppy | -0.037 |
arl | -0.036 |
ophone | -0.036 |
oke | -0.035 |
Token | â |
Token ID | 22940 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ems | +0.016 |
ppy | +0.015 |
arl | +0.015 |
ophone | +0.015 |
oke | +0.014 |
Neg logit contributions | |
it | -0.009 |
a | -0.009 |
an | -0.009 |
excitement | -0.008 |
Mill | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Mill | +0.029 |
excitement | +0.028 |
it | +0.028 |
Frankie | +0.028 |
Its | +0.028 |
Neg logit contributions | |
ems | -0.035 |
ppy | -0.034 |
arl | -0.032 |
ophone | -0.032 |
oke | -0.030 |
Token | ™ |
Token ID | 8151 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ems | +0.215 |
ppy | +0.204 |
ophone | +0.194 |
arl | +0.192 |
oke | +0.187 |
Neg logit contributions | |
excitement | -0.145 |
it | -0.140 |
Mill | -0.138 |
delight | -0.137 |
sudden | -0.133 |
Token | ll |
Token ID | 297 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
ems | +0.132 |
ppy | +0.121 |
ophone | +0.114 |
arl | +0.113 |
wy | +0.111 |
Neg logit contributions | |
it | -0.115 |
excitement | -0.113 |
Mill | -0.113 |
delight | -0.108 |
an | -0.108 |
Token | help |
Token ID | 1037 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
ems | +0.563 |
ppy | +0.543 |
ophone | +0.517 |
arl | +0.514 |
wy | +0.498 |
Neg logit contributions | |
excitement | -0.307 |
Mill | -0.294 |
sudden | -0.292 |
delight | -0.288 |
it | -0.282 |
Token | you |
Token ID | 345 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
ems | +0.009 |
ppy | +0.008 |
ophone | +0.008 |
arl | +0.008 |
oke | +0.008 |
Neg logit contributions | |
excitement | -0.004 |
delight | -0.004 |
Mill | -0.004 |
sudden | -0.004 |
it | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ems | +0.013 |
ppy | +0.012 |
arl | +0.012 |
ophone | +0.012 |
oke | +0.011 |
Neg logit contributions | |
it | -0.006 |
excitement | -0.006 |
Mill | -0.006 |
delight | -0.006 |
an | -0.006 |
Token | but |
Token ID | 475 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ems | +0.002 |
ppy | +0.002 |
ophone | +0.002 |
arl | +0.002 |
oke | +0.002 |
Neg logit contributions | |
excitement | -0.001 |
it | -0.001 |
Mill | -0.001 |
delight | -0.001 |
sudden | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
it | +0.019 |
excitement | +0.017 |
Mill | +0.017 |
the | +0.016 |
an | +0.016 |
Neg logit contributions | |
ems | -0.033 |
ppy | -0.032 |
ophone | -0.031 |
arl | -0.031 |
wy | -0.031 |
Token | on |
Token ID | 319 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
ems | +0.016 |
ppy | +0.015 |
ophone | +0.015 |
oke | +0.014 |
arl | +0.014 |
Neg logit contributions | |
it | -0.007 |
excitement | -0.006 |
an | -0.006 |
the | -0.006 |
a | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ems | +0.002 |
ppy | +0.002 |
oke | +0.001 |
arl | +0.001 |
ophone | +0.001 |
Neg logit contributions | |
excitement | -0.001 |
delight | -0.001 |
sudden | -0.001 |
Mill | -0.001 |
sight | -0.001 |
Token | Buddy |
Token ID | 36896 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
excitement | +0.010 |
delight | +0.009 |
Mill | +0.009 |
it | +0.009 |
sudden | +0.009 |
Neg logit contributions | |
ems | -0.023 |
ppy | -0.022 |
ophone | -0.021 |
arl | -0.021 |
oke | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
ems | +0.045 |
arl | +0.043 |
ppy | +0.043 |
ophone | +0.042 |
oke | +0.041 |
Neg logit contributions | |
it | -0.018 |
excitement | -0.017 |
Mill | -0.017 |
delight | -0.016 |
an | -0.016 |
Token | Wh |
Token ID | 854 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
ems | +0.000 |
ppy | +0.000 |
ophone | +0.000 |
arl | +0.000 |
oke | +0.000 |
Neg logit contributions | |
excitement | -0.000 |
delight | -0.000 |
Mill | -0.000 |
sudden | -0.000 |
it | -0.000 |
Token | isk |
Token ID | 1984 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
ems | +0.023 |
ophone | +0.019 |
arl | +0.017 |
ppy | +0.016 |
ider | +0.016 |
Neg logit contributions | |
Mill | -0.065 |
Frankie | -0.063 |
it | -0.062 |
her | -0.062 |
an | -0.062 |
Token | ers |
Token ID | 364 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
ems | +0.531 |
ppy | +0.474 |
arl | +0.474 |
ophone | +0.453 |
oke | +0.433 |
Neg logit contributions | |
it | -0.671 |
Mill | -0.641 |
excitement | -0.639 |
the | -0.631 |
an | -0.631 |
Token | were |
Token ID | 547 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
it | +0.054 |
excitement | +0.053 |
the | +0.051 |
Mill | +0.050 |
delight | +0.050 |
Neg logit contributions | |
ems | -0.105 |
arl | -0.099 |
ppy | -0.097 |
ophone | -0.095 |
oke | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
excitement | +0.014 |
sudden | +0.013 |
Mill | +0.013 |
delight | +0.012 |
sight | +0.012 |
Neg logit contributions | |
ppy | -0.035 |
ems | -0.035 |
wy | -0.033 |
ophone | -0.033 |
oke | -0.031 |
Token | best |
Token ID | 1266 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
ems | +0.003 |
ppy | +0.003 |
ophone | +0.003 |
arl | +0.003 |
wy | +0.003 |
Neg logit contributions | |
excitement | -0.002 |
Mill | -0.002 |
it | -0.002 |
delight | -0.002 |
Frankie | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
excitement | +0.041 |
Mill | +0.039 |
delight | +0.038 |
Frankie | +0.037 |
sudden | +0.037 |
Neg logit contributions | |
ems | -0.073 |
ppy | -0.071 |
oke | -0.070 |
ophone | -0.067 |
arl | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e-03 |
Pos logit contributions | |
excitement | +0.028 |
sudden | +0.027 |
delight | +0.025 |
Mill | +0.025 |
Frankie | +0.024 |
Neg logit contributions | |
ems | -0.055 |
ppy | -0.053 |
ophone | -0.050 |
arl | -0.049 |
oke | -0.049 |
Token | " |
Token ID | 366 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
excitement | +0.000 |
delight | +0.000 |
Mill | +0.000 |
sudden | +0.000 |
it | +0.000 |
Neg logit contributions | |
ems | -0.000 |
ppy | -0.000 |
arl | -0.000 |
ophone | -0.000 |
oke | -0.000 |
Token | Berry |
Token ID | 25215 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
excitement | +0.009 |
it | +0.009 |
Mill | +0.009 |
delight | +0.008 |
sudden | +0.008 |
Neg logit contributions | |
ems | -0.018 |
ppy | -0.017 |
ophone | -0.017 |
arl | -0.017 |
oke | -0.016 |
Token | - |
Token ID | 12 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
it | +0.014 |
Mill | +0.013 |
excitement | +0.013 |
Frankie | +0.012 |
an | +0.012 |
Neg logit contributions | |
ems | -0.030 |
ppy | -0.029 |
ophone | -0.028 |
arl | -0.028 |
wy | -0.027 |
Token | bus |
Token ID | 10885 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ems | +0.015 |
ppy | +0.014 |
ophone | +0.013 |
arl | +0.013 |
oke | +0.013 |
Neg logit contributions | |
excitement | -0.010 |
it | -0.009 |
Mill | -0.009 |
delight | -0.009 |
sudden | -0.009 |
Token | hes |
Token ID | 956 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
it | +0.217 |
Mill | +0.207 |
the | +0.203 |
an | +0.202 |
a | +0.201 |
Neg logit contributions | |
ems | -0.196 |
ppy | -0.175 |
ophone | -0.175 |
arl | -0.165 |
ider | -0.162 |
Token | are |
Token ID | 389 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
ems | +0.383 |
ppy | +0.366 |
ophone | +0.352 |
arl | +0.350 |
oke | +0.340 |
Neg logit contributions | |
excitement | -0.170 |
it | -0.168 |
Mill | -0.161 |
delight | -0.159 |
an | -0.152 |
Token | very |
Token ID | 845 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
ems | +0.112 |
ppy | +0.108 |
ophone | +0.103 |
arl | +0.102 |
wy | +0.100 |
Neg logit contributions | |
excitement | -0.041 |
Mill | -0.038 |
delight | -0.038 |
sudden | -0.038 |
it | -0.037 |
Token | boring |
Token ID | 14262 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
excitement | +0.039 |
it | +0.036 |
Mill | +0.036 |
delight | +0.035 |
sudden | +0.034 |
Neg logit contributions | |
ems | -0.119 |
ppy | -0.115 |
arl | -0.110 |
ophone | -0.110 |
oke | -0.107 |
Token | plants |
Token ID | 6134 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ems | +0.068 |
ppy | +0.065 |
ophone | +0.062 |
arl | +0.062 |
oke | +0.060 |
Neg logit contributions | |
excitement | -0.029 |
it | -0.028 |
Mill | -0.027 |
delight | -0.027 |
sudden | -0.026 |
Token | with |
Token ID | 351 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
ems | +0.022 |
ppy | +0.021 |
ophone | +0.020 |
arl | +0.020 |
oke | +0.019 |
Neg logit contributions | |
it | -0.009 |
excitement | -0.009 |
Mill | -0.008 |
delight | -0.008 |
an | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
excitement | +0.082 |
delight | +0.080 |
it | +0.080 |
Mill | +0.079 |
Its | +0.078 |
Neg logit contributions | |
ems | -0.120 |
ppy | -0.114 |
arl | -0.108 |
ophone | -0.105 |
wy | -0.103 |
Token | � |
Token ID | 129 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ems | +0.205 |
ppy | +0.195 |
arl | +0.187 |
ophone | +0.185 |
wy | +0.183 |
Neg logit contributions | |
it | -0.143 |
excitement | -0.143 |
Mill | -0.139 |
delight | -0.135 |
sudden | -0.133 |
Token | � |
Token ID | 241 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ems | +0.027 |
ppy | +0.026 |
ophone | +0.025 |
arl | +0.024 |
wy | +0.023 |
Neg logit contributions | |
excitement | -0.024 |
it | -0.024 |
Mill | -0.023 |
sudden | -0.023 |
delight | -0.023 |
Token | Let |
Token ID | 5756 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
excitement | +0.018 |
delight | +0.018 |
Mill | +0.017 |
it | +0.016 |
Frankie | +0.016 |
Neg logit contributions | |
ems | -0.036 |
ppy | -0.034 |
ophone | -0.033 |
arl | -0.033 |
oke | -0.032 |
Token | â |
Token ID | 22940 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
excitement | +0.094 |
sudden | +0.091 |
Mill | +0.089 |
delight | +0.087 |
sight | +0.085 |
Neg logit contributions | |
ems | -0.166 |
ppy | -0.158 |
ophone | -0.150 |
arl | -0.144 |
oke | -0.143 |
Token | € |
Token ID | 26391 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
excitement | +0.031 |
delight | +0.031 |
Mill | +0.030 |
it | +0.029 |
Frankie | +0.029 |
Neg logit contributions | |
ems | -0.037 |
ppy | -0.034 |
arl | -0.033 |
ophone | -0.032 |
oke | -0.032 |
Token | ™ |
Token ID | 8151 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
ems | +0.222 |
ppy | +0.212 |
arl | +0.202 |
ophone | +0.202 |
wy | +0.196 |
Neg logit contributions | |
excitement | -0.131 |
it | -0.129 |
Mill | -0.126 |
delight | -0.123 |
sudden | -0.120 |
Token | s |
Token ID | 82 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ems | +0.125 |
ppy | +0.115 |
ophone | +0.107 |
arl | +0.107 |
wy | +0.106 |
Neg logit contributions | |
it | -0.110 |
Mill | -0.108 |
excitement | -0.107 |
delight | -0.103 |
an | -0.103 |
Token | un |
Token ID | 555 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
ems | +0.068 |
ppy | +0.065 |
ophone | +0.062 |
arl | +0.061 |
wy | +0.058 |
Neg logit contributions | |
excitement | -0.032 |
sudden | -0.031 |
Mill | -0.030 |
delight | -0.030 |
it | -0.030 |
Token | pack |
Token ID | 8002 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
ems | +0.110 |
ppy | +0.103 |
ophone | +0.097 |
arl | +0.096 |
oke | +0.092 |
Neg logit contributions | |
excitement | -0.114 |
it | -0.111 |
Mill | -0.110 |
delight | -0.109 |
sudden | -0.107 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ems | +0.076 |
ppy | +0.072 |
ophone | +0.071 |
arl | +0.070 |
wy | +0.068 |
Neg logit contributions | |
excitement | -0.021 |
Mill | -0.020 |
sudden | -0.020 |
delight | -0.020 |
Frankie | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
ems | +0.038 |
ppy | +0.036 |
ophone | +0.035 |
arl | +0.035 |
oke | +0.034 |
Neg logit contributions | |
it | -0.014 |
excitement | -0.013 |
Mill | -0.013 |
delight | -0.012 |
an | -0.012 |
Token | But |
Token ID | 887 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
excitement | +0.004 |
it | +0.004 |
delight | +0.004 |
sudden | +0.004 |
Mill | +0.003 |
Neg logit contributions | |
ems | -0.012 |
ppy | -0.011 |
ophone | -0.011 |
arl | -0.011 |
oke | -0.011 |
Token | soon |
Token ID | 2582 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ems | +0.039 |
ppy | +0.037 |
ophone | +0.036 |
arl | +0.036 |
oke | +0.035 |
Neg logit contributions | |
excitement | -0.015 |
it | -0.014 |
Mill | -0.014 |
delight | -0.014 |
Frankie | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ems | +0.025 |
ppy | +0.024 |
ophone | +0.022 |
oke | +0.022 |
ets | +0.022 |
Neg logit contributions | |
excitement | -0.010 |
delight | -0.009 |
sudden | -0.009 |
Mill | -0.009 |
Its | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
excitement | +0.019 |
delight | +0.018 |
sudden | +0.017 |
Its | +0.016 |
Mill | +0.015 |
Neg logit contributions | |
ems | -0.063 |
ppy | -0.059 |
ophone | -0.057 |
arl | -0.054 |
oke | -0.054 |
Token | storm |
Token ID | 6388 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
excitement | +0.001 |
it | +0.001 |
Mill | +0.001 |
delight | +0.000 |
Frankie | +0.000 |
Neg logit contributions | |
ems | -0.001 |
ppy | -0.001 |
ophone | -0.001 |
arl | -0.001 |
oke | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ems | +0.197 |
ppy | +0.189 |
arl | +0.181 |
ophone | +0.178 |
wy | +0.176 |
Neg logit contributions | |
it | -0.126 |
excitement | -0.122 |
Mill | -0.118 |
delight | -0.114 |
sudden | -0.113 |
Token | so |
Token ID | 523 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
excitement | +0.025 |
delight | +0.024 |
Mill | +0.024 |
it | +0.023 |
sudden | +0.023 |
Neg logit contributions | |
ems | -0.051 |
ppy | -0.049 |
ophone | -0.047 |
arl | -0.047 |
wy | -0.045 |
Token | strong |
Token ID | 1913 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
excitement | +0.042 |
delight | +0.040 |
Mill | +0.039 |
it | +0.039 |
Frankie | +0.037 |
Neg logit contributions | |
ems | -0.094 |
ppy | -0.090 |
arl | -0.088 |
ophone | -0.086 |
oke | -0.084 |
Token | that |
Token ID | 326 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
ems | +0.080 |
ppy | +0.076 |
ophone | +0.073 |
arl | +0.073 |
oke | +0.071 |
Neg logit contributions | |
excitement | -0.031 |
it | -0.029 |
Mill | -0.029 |
delight | -0.029 |
sudden | -0.028 |
Token | everyone |
Token ID | 2506 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ems | +0.010 |
ppy | +0.009 |
ophone | +0.009 |
oke | +0.009 |
ets | +0.009 |
Neg logit contributions | |
excitement | -0.002 |
sudden | -0.002 |
delight | -0.002 |
Mill | -0.002 |
Its | -0.002 |
Token | careful |
Token ID | 8161 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
excitement | +0.054 |
it | +0.054 |
Mill | +0.050 |
delight | +0.049 |
sudden | +0.049 |
Neg logit contributions | |
ems | -0.123 |
ppy | -0.115 |
ophone | -0.111 |
arl | -0.108 |
oke | -0.107 |
Token | not |
Token ID | 407 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
excitement | +0.017 |
delight | +0.016 |
Mill | +0.016 |
sudden | +0.016 |
Frankie | +0.015 |
Neg logit contributions | |
ems | -0.027 |
ppy | -0.026 |
ophone | -0.025 |
ets | -0.024 |
arl | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ems | +0.128 |
ppy | +0.127 |
arl | +0.117 |
ophone | +0.116 |
ets | +0.115 |
Neg logit contributions | |
excitement | -0.049 |
delight | -0.048 |
sudden | -0.042 |
Its | -0.040 |
Mill | -0.040 |
Token | let |
Token ID | 1309 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
excitement | +0.025 |
delight | +0.024 |
sudden | +0.023 |
Its | +0.023 |
Mill | +0.022 |
Neg logit contributions | |
ems | -0.038 |
ppy | -0.037 |
arl | -0.034 |
ophone | -0.032 |
ets | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
ems | +0.078 |
ppy | +0.076 |
ophone | +0.072 |
ets | +0.069 |
oke | +0.069 |
Neg logit contributions | |
sudden | -0.027 |
excitement | -0.025 |
delight | -0.024 |
Mill | -0.023 |
Mill | -0.021 |
Token | wind |
Token ID | 2344 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Frankie | +0.001 |
Mill | +0.001 |
Its | +0.001 |
Bobby | +0.001 |
delight | +0.001 |
Neg logit contributions | |
ems | -0.003 |
ppy | -0.002 |
arl | -0.002 |
ets | -0.002 |
ophone | -0.002 |
Token | take |
Token ID | 1011 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
ems | +0.181 |
ppy | +0.174 |
ophone | +0.166 |
arl | +0.165 |
oke | +0.160 |
Neg logit contributions | |
excitement | -0.089 |
delight | -0.083 |
it | -0.083 |
Mill | -0.083 |
sudden | -0.081 |
Token | it |
Token ID | 340 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
sudden | +0.056 |
excitement | +0.050 |
Mill | +0.049 |
delight | +0.049 |
Mill | +0.046 |
Neg logit contributions | |
ppy | -0.134 |
ems | -0.134 |
ets | -0.129 |
arl | -0.124 |
ophone | -0.123 |
Token | away |
Token ID | 1497 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
excitement | +0.049 |
delight | +0.046 |
sudden | +0.046 |
Mill | +0.045 |
it | +0.045 |
Neg logit contributions | |
ems | -0.078 |
ppy | -0.076 |
ophone | -0.072 |
arl | -0.072 |
ets | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
excitement | +0.015 |
delight | +0.014 |
sudden | +0.014 |
Mill | +0.014 |
it | +0.014 |
Neg logit contributions | |
ems | -0.030 |
ppy | -0.029 |
ophone | -0.027 |
arl | -0.027 |
wy | -0.026 |
Token | He |
Token ID | 679 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
excitement | +0.010 |
sudden | +0.010 |
delight | +0.009 |
it | +0.009 |
Mill | +0.009 |
Neg logit contributions | |
ems | -0.025 |
ppy | -0.024 |
ophone | -0.023 |
arl | -0.023 |
oke | -0.023 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
excitement | +0.010 |
delight | +0.010 |
Frankie | +0.009 |
Mill | +0.009 |
sudden | +0.009 |
Neg logit contributions | |
ems | -0.017 |
ppy | -0.016 |
ophone | -0.015 |
arl | -0.014 |
wy | -0.014 |
Token | put |
Token ID | 1234 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ems | +0.065 |
arl | +0.061 |
ppy | +0.061 |
ophone | +0.059 |
oke | +0.057 |
Neg logit contributions | |
it | -0.034 |
excitement | -0.034 |
delight | -0.031 |
sudden | -0.031 |
an | -0.031 |
Token | on |
Token ID | 319 |
Feature activation | -3.93e-04 |
Pos logit contributions | |
it | +0.041 |
excitement | +0.040 |
an | +0.038 |
Mill | +0.037 |
delight | +0.037 |
Neg logit contributions | |
ems | -0.083 |
ppy | -0.079 |
ophone | -0.076 |
oke | -0.075 |
arl | -0.075 |
Token | her |
Token ID | 607 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Mill | +0.000 |
Frankie | +0.000 |
delight | +0.000 |
Susan | +0.000 |
Frank | +0.000 |
Neg logit contributions | |
ems | -0.000 |
wy | -0.000 |
ppy | -0.000 |
ophone | -0.000 |
arl | -0.000 |
Token | swim |
Token ID | 9422 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
excitement | +0.014 |
Mill | +0.014 |
it | +0.014 |
delight | +0.014 |
Frankie | +0.013 |
Neg logit contributions | |
ems | -0.032 |
ppy | -0.030 |
ophone | -0.029 |
arl | -0.029 |
wy | -0.028 |
Token | suit |
Token ID | 6063 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ems | +0.018 |
oke | +0.017 |
ppy | +0.015 |
wy | +0.015 |
ophone | +0.014 |
Neg logit contributions | |
a | -0.024 |
it | -0.024 |
the | -0.023 |
new | -0.023 |
excitement | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
ems | +0.341 |
ppy | +0.327 |
arl | +0.314 |
ophone | +0.314 |
oke | +0.309 |
Neg logit contributions | |
it | -0.107 |
excitement | -0.102 |
an | -0.093 |
Mill | -0.090 |
delight | -0.090 |
Token | rode |
Token ID | 22075 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
ems | +0.008 |
ppy | +0.008 |
arl | +0.008 |
ophone | +0.008 |
oke | +0.007 |
Neg logit contributions | |
excitement | -0.004 |
it | -0.004 |
Mill | -0.004 |
delight | -0.004 |
sudden | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ems | +0.129 |
ppy | +0.123 |
ophone | +0.120 |
arl | +0.117 |
ets | +0.114 |
Neg logit contributions | |
sudden | -0.041 |
excitement | -0.041 |
delight | -0.040 |
Mill | -0.040 |
Frankie | -0.039 |
Token | bike |
Token ID | 7161 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Mill | +0.016 |
excitement | +0.016 |
delight | +0.016 |
Frankie | +0.015 |
it | +0.015 |
Neg logit contributions | |
ems | -0.031 |
ppy | -0.029 |
ophone | -0.029 |
arl | -0.028 |
wy | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
it | +0.006 |
excitement | +0.005 |
a | +0.005 |
an | +0.005 |
the | +0.005 |
Neg logit contributions | |
ems | -0.021 |
ppy | -0.020 |
oke | -0.019 |
arl | -0.019 |
wy | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
ems | +0.027 |
ppy | +0.026 |
arl | +0.025 |
ophone | +0.025 |
wy | +0.025 |
Neg logit contributions | |
it | -0.013 |
excitement | -0.012 |
Mill | -0.012 |
an | -0.011 |
delight | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
ems | +0.012 |
arl | +0.011 |
ppy | +0.011 |
rant | +0.011 |
wy | +0.011 |
Neg logit contributions | |
sudden | -0.006 |
Frankie | -0.004 |
excitement | -0.004 |
Mill | -0.004 |
Bobby | -0.004 |
Token | sky |
Token ID | 6766 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
ems | +0.029 |
ppy | +0.028 |
ophone | +0.027 |
arl | +0.026 |
wy | +0.026 |
Neg logit contributions | |
excitement | -0.013 |
Mill | -0.012 |
it | -0.012 |
delight | -0.012 |
Frankie | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
ems | +0.077 |
ppy | +0.073 |
ophone | +0.071 |
arl | +0.070 |
oke | +0.068 |
Neg logit contributions | |
excitement | -0.030 |
Mill | -0.028 |
it | -0.028 |
delight | -0.027 |
sudden | -0.026 |
Token | She |
Token ID | 1375 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ems | +0.045 |
ophone | +0.040 |
arl | +0.039 |
ppy | +0.038 |
oke | +0.038 |
Neg logit contributions | |
sudden | -0.020 |
excitement | -0.019 |
delight | -0.018 |
Frankie | -0.018 |
baby | -0.017 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
ems | +0.044 |
ppy | +0.042 |
ophone | +0.040 |
oke | +0.037 |
arl | +0.036 |
Neg logit contributions | |
excitement | -0.036 |
Mill | -0.035 |
delight | -0.035 |
Frankie | -0.034 |
sight | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
ems | +0.000 |
ophone | +0.000 |
ppy | +0.000 |
ets | +0.000 |
ber | +0.000 |
Neg logit contributions | |
sudden | -0.000 |
delight | -0.000 |
excitement | -0.000 |
Frankie | -0.000 |
Bobby | -0.000 |
Token | know |
Token ID | 760 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
sudden | +0.008 |
excitement | +0.007 |
Frankie | +0.007 |
Mill | +0.007 |
sight | +0.007 |
Neg logit contributions | |
ems | -0.010 |
ppy | -0.010 |
ophone | -0.009 |
arl | -0.009 |
ets | -0.009 |
Token | what |
Token ID | 644 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ems | +0.019 |
ophone | +0.017 |
ppy | +0.017 |
oke | +0.016 |
arl | +0.015 |
Neg logit contributions | |
sudden | -0.018 |
excitement | -0.018 |
delight | -0.017 |
sight | -0.016 |
mischief | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ems | +0.038 |
ophone | +0.037 |
ppy | +0.035 |
oke | +0.034 |
ber | +0.033 |
Neg logit contributions | |
excitement | -0.016 |
delight | -0.015 |
sudden | -0.015 |
Mill | -0.013 |
Frankie | -0.013 |
Token | inside |
Token ID | 2641 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
ems | +0.022 |
ppy | +0.022 |
arl | +0.021 |
ophone | +0.020 |
oke | +0.020 |
Neg logit contributions | |
it | -0.014 |
Mill | -0.014 |
excitement | -0.014 |
an | -0.013 |
Frankie | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
ems | +0.003 |
ppy | +0.003 |
oke | +0.003 |
arl | +0.003 |
ophone | +0.003 |
Neg logit contributions | |
excitement | -0.002 |
sudden | -0.002 |
delight | -0.002 |
sight | -0.002 |
colourful | -0.002 |
Token | tried |
Token ID | 3088 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
excitement | +0.003 |
Mill | +0.003 |
delight | +0.003 |
it | +0.003 |
Frankie | +0.003 |
Neg logit contributions | |
ems | -0.004 |
ppy | -0.004 |
ophone | -0.004 |
wy | -0.004 |
oke | -0.004 |
Token | as |
Token ID | 355 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
ems | +0.063 |
ppy | +0.061 |
arl | +0.057 |
ophone | +0.056 |
ll | +0.054 |
Neg logit contributions | |
excitement | -0.032 |
delight | -0.032 |
Frankie | -0.031 |
Mill | -0.030 |
sudden | -0.029 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ems | +0.067 |
ppy | +0.065 |
arl | +0.063 |
ophone | +0.060 |
wy | +0.059 |
Neg logit contributions | |
excitement | -0.035 |
delight | -0.035 |
Mill | -0.034 |
Frankie | -0.032 |
sudden | -0.031 |
Token | as |
Token ID | 355 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
excitement | +0.012 |
delight | +0.011 |
Mill | +0.011 |
sudden | +0.011 |
Frankie | +0.011 |
Neg logit contributions | |
ems | -0.017 |
ppy | -0.016 |
arl | -0.016 |
ets | -0.015 |
oke | -0.014 |
Token | she |
Token ID | 673 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ems | +0.063 |
ppy | +0.061 |
arl | +0.057 |
ophone | +0.055 |
ider | +0.052 |
Neg logit contributions | |
excitement | -0.032 |
delight | -0.032 |
sudden | -0.029 |
Frankie | -0.029 |
Its | -0.029 |
Token | could |
Token ID | 714 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
it | +0.047 |
excitement | +0.046 |
sudden | +0.044 |
delight | +0.044 |
Mill | +0.044 |
Neg logit contributions | |
ems | -0.046 |
ppy | -0.042 |
arl | -0.041 |
ophone | -0.041 |
wy | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ems | +0.097 |
ppy | +0.097 |
arl | +0.090 |
ophone | +0.088 |
oke | +0.086 |
Neg logit contributions | |
excitement | -0.054 |
sudden | -0.054 |
Mill | -0.054 |
Frankie | -0.053 |
delight | -0.051 |
Token | but |
Token ID | 475 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Mill | +0.010 |
excitement | +0.010 |
Frankie | +0.009 |
delight | +0.009 |
sudden | +0.009 |
Neg logit contributions | |
ems | -0.015 |
ppy | -0.014 |
ets | -0.013 |
ophone | -0.013 |
arl | -0.012 |
Token | she |
Token ID | 673 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
excitement | +0.012 |
Mill | +0.011 |
delight | +0.011 |
sudden | +0.011 |
Frankie | +0.010 |
Neg logit contributions | |
ems | -0.062 |
ppy | -0.060 |
ophone | -0.057 |
arl | -0.055 |
oke | -0.055 |
Token | just |
Token ID | 655 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
it | +0.037 |
excitement | +0.036 |
sudden | +0.034 |
Mill | +0.034 |
delight | +0.034 |
Neg logit contributions | |
ems | -0.064 |
arl | -0.060 |
ppy | -0.059 |
ophone | -0.058 |
oke | -0.056 |
Token | idea |
Token ID | 2126 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
ems | +0.021 |
ppy | +0.021 |
ets | +0.021 |
oke | +0.020 |
ophone | +0.020 |
Neg logit contributions | |
sudden | -0.014 |
it | -0.014 |
Mill | -0.013 |
Frankie | -0.013 |
excitement | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ems | +0.114 |
ppy | +0.109 |
ophone | +0.105 |
arl | +0.102 |
oke | +0.102 |
Neg logit contributions | |
excitement | -0.050 |
sudden | -0.047 |
delight | -0.047 |
Mill | -0.044 |
it | -0.043 |
Token | It |
Token ID | 632 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
excitement | +0.007 |
sudden | +0.006 |
delight | +0.006 |
it | +0.006 |
sight | +0.006 |
Neg logit contributions | |
ems | -0.017 |
ppy | -0.017 |
oke | -0.016 |
arl | -0.016 |
ophone | -0.016 |
Token | told |
Token ID | 1297 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
it | +0.037 |
excitement | +0.037 |
Mill | +0.036 |
delight | +0.034 |
an | +0.034 |
Neg logit contributions | |
ems | -0.065 |
arl | -0.062 |
ppy | -0.061 |
ophone | -0.058 |
wy | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ems | +0.064 |
ppy | +0.062 |
arl | +0.058 |
ophone | +0.057 |
ets | +0.056 |
Neg logit contributions | |
sudden | -0.021 |
excitement | -0.018 |
delight | -0.016 |
Frankie | -0.016 |
Mill | -0.016 |
Token | teaspoon |
Token ID | 22326 |
Feature activation | +8.28e-03 |
Pos logit contributions | |
ems | +0.028 |
ppy | +0.027 |
arl | +0.026 |
ophone | +0.026 |
oke | +0.025 |
Neg logit contributions | |
Mill | -0.015 |
excitement | -0.015 |
Frankie | -0.015 |
it | -0.015 |
delight | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ems | +0.001 |
ppy | +0.001 |
ophone | +0.001 |
oke | +0.001 |
ets | +0.001 |
Neg logit contributions | |
excitement | -0.001 |
sudden | -0.001 |
delight | -0.001 |
Mill | -0.001 |
Frankie | -0.001 |
Token | if |
Token ID | 611 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
ems | +0.058 |
ppy | +0.055 |
ophone | +0.054 |
arl | +0.053 |
oke | +0.052 |
Neg logit contributions | |
excitement | -0.014 |
it | -0.013 |
delight | -0.013 |
Mill | -0.013 |
sudden | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ems | +0.103 |
ppy | +0.098 |
ophone | +0.094 |
arl | +0.092 |
oke | +0.092 |
Neg logit contributions | |
excitement | -0.036 |
delight | -0.034 |
Mill | -0.033 |
sudden | -0.032 |
Frankie | -0.031 |
Token | stayed |
Token ID | 9658 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
it | +0.027 |
excitement | +0.026 |
Mill | +0.025 |
an | +0.024 |
delight | +0.024 |
Neg logit contributions | |
ems | -0.048 |
arl | -0.047 |
ppy | -0.046 |
ophone | -0.044 |
wy | -0.043 |
Token | inside |
Token ID | 2641 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
ems | +0.073 |
ppy | +0.070 |
ophone | +0.067 |
arl | +0.066 |
wy | +0.064 |
Neg logit contributions | |
excitement | -0.035 |
it | -0.033 |
Mill | -0.033 |
delight | -0.033 |
sudden | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
excitement | +0.007 |
it | +0.007 |
Mill | +0.006 |
delight | +0.006 |
an | +0.006 |
Neg logit contributions | |
ems | -0.021 |
ppy | -0.020 |
ophone | -0.020 |
arl | -0.020 |
wy | -0.019 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
excitement | +0.012 |
Mill | +0.011 |
delight | +0.011 |
it | +0.011 |
sudden | +0.011 |
Neg logit contributions | |
ems | -0.025 |
ppy | -0.024 |
ophone | -0.023 |
arl | -0.023 |
oke | -0.022 |
Token | with |
Token ID | 351 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
ems | +0.036 |
ppy | +0.035 |
ophone | +0.033 |
arl | +0.033 |
oke | +0.032 |
Neg logit contributions | |
excitement | -0.013 |
delight | -0.012 |
Mill | -0.012 |
sudden | -0.012 |
Frankie | -0.012 |
Token | his |
Token ID | 465 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
sudden | +0.052 |
excitement | +0.044 |
Mill | +0.043 |
Its | +0.042 |
delight | +0.041 |
Neg logit contributions | |
ems | -0.121 |
ppy | -0.121 |
arl | -0.118 |
wy | -0.116 |
ophone | -0.115 |
Token | new |
Token ID | 649 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ems | +0.086 |
arl | +0.083 |
ppy | +0.082 |
ophone | +0.082 |
oke | +0.080 |
Neg logit contributions | |
Mill | -0.027 |
it | -0.024 |
Frankie | -0.024 |
excitement | -0.023 |
Its | -0.022 |
Token | friend |
Token ID | 1545 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
Mill | +0.034 |
sudden | +0.032 |
it | +0.032 |
Its | +0.032 |
Frankie | +0.031 |
Neg logit contributions | |
ems | -0.057 |
ophone | -0.055 |
arl | -0.055 |
ppy | -0.053 |
osaurs | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
ems | +0.100 |
ppy | +0.097 |
ophone | +0.092 |
arl | +0.090 |
oke | +0.089 |
Neg logit contributions | |
excitement | -0.042 |
Mill | -0.039 |
it | -0.039 |
delight | -0.039 |
sudden | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +5.13e-03 |
Pos logit contributions | |
ems | +0.006 |
ppy | +0.005 |
ophone | +0.005 |
arl | +0.005 |
oke | +0.005 |
Neg logit contributions | |
excitement | -0.002 |
it | -0.002 |
Mill | -0.002 |
delight | -0.002 |
sudden | -0.002 |
Token | fun |
Token ID | 1257 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
ems | +0.001 |
arl | +0.001 |
ppy | +0.001 |
ophone | +0.001 |
wy | +0.001 |
Neg logit contributions | |
Mill | -0.000 |
Its | -0.000 |
Frankie | -0.000 |
it | -0.000 |
excitement | -0.000 |
Token | day |
Token ID | 1110 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
sudden | +0.067 |
excitement | +0.067 |
delight | +0.067 |
Mill | +0.066 |
Its | +0.066 |
Neg logit contributions | |
ems | -0.089 |
ophone | -0.083 |
ppy | -0.082 |
oke | -0.082 |
ets | -0.082 |
Token | they |
Token ID | 484 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ems | +0.013 |
ppy | +0.013 |
oke | +0.013 |
ophone | +0.012 |
ets | +0.012 |
Neg logit contributions | |
excitement | -0.007 |
delight | -0.007 |
Mill | -0.007 |
sudden | -0.007 |
Frankie | -0.007 |
Token | After |
Token ID | 2293 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
excitement | +0.006 |
sudden | +0.005 |
it | +0.005 |
Mill | +0.005 |
Frankie | +0.005 |
Neg logit contributions | |
ems | -0.011 |
ppy | -0.010 |
ophone | -0.010 |
arl | -0.010 |
oke | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Frankie | +0.041 |
excitement | +0.039 |
Mill | +0.039 |
delight | +0.038 |
Its | +0.037 |
Neg logit contributions | |
ems | -0.101 |
ppy | -0.098 |
arl | -0.097 |
ophone | -0.094 |
oke | -0.093 |
Token | 'd |
Token ID | 1549 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ems | +0.021 |
ppy | +0.019 |
arl | +0.019 |
ophone | +0.018 |
ider | +0.018 |
Neg logit contributions | |
it | -0.011 |
excitement | -0.011 |
delight | -0.010 |
the | -0.010 |
Mill | -0.010 |
Token | finished |
Token ID | 5201 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
ems | +0.054 |
ppy | +0.051 |
ophone | +0.049 |
arl | +0.049 |
wy | +0.047 |
Neg logit contributions | |
excitement | -0.032 |
Mill | -0.031 |
sudden | -0.031 |
it | -0.030 |
delight | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
excitement | +0.062 |
sudden | +0.060 |
delight | +0.060 |
Its | +0.057 |
Mill | +0.054 |
Neg logit contributions | |
ems | -0.109 |
arl | -0.104 |
ophone | -0.101 |
oke | -0.101 |
ppy | -0.100 |
Token | Molly |
Token ID | 30236 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
excitement | +0.008 |
Mill | +0.008 |
Frankie | +0.008 |
sudden | +0.008 |
delight | +0.008 |
Neg logit contributions | |
ems | -0.019 |
ppy | -0.018 |
ophone | -0.017 |
oke | -0.016 |
arl | -0.016 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
excitement | +0.077 |
it | +0.074 |
Mill | +0.073 |
delight | +0.072 |
sudden | +0.070 |
Neg logit contributions | |
ems | -0.133 |
ppy | -0.127 |
ophone | -0.121 |
arl | -0.119 |
oke | -0.117 |
Token | Julia |
Token ID | 22300 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
sudden | +0.013 |
excitement | +0.011 |
Frankie | +0.011 |
Mill | +0.010 |
sight | +0.010 |
Neg logit contributions | |
ems | -0.027 |
ppy | -0.026 |
ophone | -0.024 |
arl | -0.023 |
oke | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
excitement | +0.077 |
it | +0.076 |
Mill | +0.073 |
delight | +0.072 |
an | +0.069 |
Neg logit contributions | |
ems | -0.163 |
ppy | -0.154 |
arl | -0.150 |
ophone | -0.149 |
wy | -0.145 |
Token | spo |
Token ID | 15106 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
ems | +0.100 |
ppy | +0.098 |
arl | +0.095 |
ophone | +0.093 |
wy | +0.091 |
Neg logit contributions | |
sudden | -0.035 |
excitement | -0.035 |
Mill | -0.034 |
delight | -0.032 |
Frankie | -0.031 |
Token | iling |
Token ID | 4386 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
excitement | +0.151 |
delight | +0.148 |
it | +0.146 |
Mill | +0.142 |
sudden | +0.141 |
Neg logit contributions | |
ems | -0.088 |
ppy | -0.079 |
ophone | -0.075 |
arl | -0.072 |
oke | -0.068 |
Token | She |
Token ID | 1375 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ems | +0.005 |
ppy | +0.005 |
ophone | +0.005 |
oke | +0.005 |
arl | +0.005 |
Neg logit contributions | |
excitement | -0.002 |
sudden | -0.002 |
it | -0.002 |
Frankie | -0.002 |
delight | -0.002 |
Token | went |
Token ID | 1816 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
it | +0.010 |
excitement | +0.010 |
Mill | +0.009 |
delight | +0.009 |
sudden | +0.009 |
Neg logit contributions | |
ems | -0.017 |
arl | -0.016 |
ppy | -0.016 |
ophone | -0.016 |
oke | -0.015 |
Token | outside |
Token ID | 2354 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
ems | +0.032 |
ppy | +0.031 |
ophone | +0.029 |
arl | +0.029 |
oke | +0.028 |
Neg logit contributions | |
excitement | -0.013 |
it | -0.013 |
Mill | -0.012 |
delight | -0.012 |
sudden | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ems | +0.003 |
ppy | +0.003 |
ophone | +0.003 |
arl | +0.003 |
oke | +0.003 |
Neg logit contributions | |
excitement | -0.002 |
Frankie | -0.002 |
delight | -0.002 |
Mill | -0.002 |
sudden | -0.002 |
Token | when |
Token ID | 618 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
ems | +0.003 |
arl | +0.003 |
ppy | +0.003 |
oke | +0.003 |
wy | +0.002 |
Neg logit contributions | |
it | -0.002 |
excitement | -0.002 |
Mill | -0.002 |
the | -0.002 |
an | -0.002 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ems | +0.095 |
ppy | +0.088 |
ophone | +0.085 |
ber | +0.082 |
ider | +0.081 |
Neg logit contributions | |
Frankie | -0.045 |
excitement | -0.044 |
delight | -0.043 |
Its | -0.042 |
sudden | -0.042 |
Token | noticed |
Token ID | 6810 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
it | +0.139 |
excitement | +0.138 |
sudden | +0.133 |
Mill | +0.133 |
delight | +0.131 |
Neg logit contributions | |
ems | -0.224 |
arl | -0.211 |
ppy | -0.206 |
ophone | -0.205 |
wy | -0.195 |
Token | she |
Token ID | 673 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
excitement | +0.059 |
delight | +0.055 |
Frankie | +0.054 |
sudden | +0.053 |
Mill | +0.048 |
Neg logit contributions | |
ems | -0.180 |
ppy | -0.172 |
ophone | -0.167 |
oke | -0.156 |
ets | -0.152 |
Token | chased |
Token ID | 26172 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
excitement | +0.018 |
Mill | +0.018 |
delight | +0.017 |
it | +0.017 |
Frankie | +0.017 |
Neg logit contributions | |
ems | -0.032 |
ppy | -0.031 |
ophone | -0.029 |
oke | -0.028 |
wy | -0.028 |
Token | after |
Token ID | 706 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ppy | +0.013 |
ems | +0.013 |
ets | +0.012 |
ms | +0.011 |
ophone | +0.011 |
Neg logit contributions | |
Frankie | -0.005 |
sudden | -0.005 |
excitement | -0.005 |
Mill | -0.005 |
Its | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ppy | +0.040 |
ems | +0.040 |
ophone | +0.036 |
arl | +0.036 |
ider | +0.035 |
Neg logit contributions | |
Frankie | -0.012 |
excitement | -0.011 |
delight | -0.010 |
Mill | -0.010 |
sudden | -0.010 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
excitement | +0.001 |
it | +0.001 |
Mill | +0.001 |
delight | +0.001 |
sudden | +0.001 |
Neg logit contributions | |
ems | -0.006 |
ppy | -0.006 |
ophone | -0.005 |
arl | -0.005 |
oke | -0.005 |
Token | M |
Token ID | 44 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
ems | +0.011 |
ppy | +0.010 |
ophone | +0.010 |
arl | +0.010 |
oke | +0.010 |
Neg logit contributions | |
excitement | -0.006 |
it | -0.006 |
Mill | -0.006 |
delight | -0.006 |
sudden | -0.006 |
Token | ia |
Token ID | 544 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ems | +0.062 |
ppy | +0.061 |
arl | +0.058 |
oke | +0.056 |
ophone | +0.055 |
Neg logit contributions | |
excitement | -0.085 |
it | -0.084 |
Mill | -0.083 |
sudden | -0.080 |
delight | -0.080 |
Token | was |
Token ID | 373 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ems | +0.102 |
arl | +0.098 |
ppy | +0.097 |
ophone | +0.094 |
oke | +0.092 |
Neg logit contributions | |
it | -0.044 |
excitement | -0.042 |
Mill | -0.041 |
an | -0.039 |
delight | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
ems | +0.028 |
ppy | +0.027 |
ophone | +0.027 |
arl | +0.026 |
wy | +0.025 |
Neg logit contributions | |
Mill | -0.010 |
excitement | -0.010 |
Frankie | -0.010 |
it | -0.010 |
delight | -0.010 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
excitement | +0.001 |
it | +0.001 |
Mill | +0.001 |
delight | +0.001 |
sudden | +0.001 |
Neg logit contributions | |
ems | -0.003 |
ppy | -0.003 |
ophone | -0.003 |
arl | -0.003 |
oke | -0.003 |
Token | year |
Token ID | 614 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
excitement | +0.145 |
it | +0.140 |
Mill | +0.138 |
delight | +0.136 |
Frankie | +0.131 |
Neg logit contributions | |
ems | -0.279 |
ppy | -0.268 |
ophone | -0.256 |
arl | -0.253 |
oke | -0.248 |
Token | old |
Token ID | 1468 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
excitement | +0.030 |
it | +0.029 |
Mill | +0.028 |
delight | +0.026 |
sudden | +0.024 |
Neg logit contributions | |
ems | -0.131 |
ppy | -0.125 |
ophone | -0.121 |
arl | -0.119 |
wy | -0.118 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ems | +0.041 |
ppy | +0.040 |
ophone | +0.037 |
arl | +0.037 |
oke | +0.037 |
Neg logit contributions | |
excitement | -0.029 |
delight | -0.028 |
it | -0.027 |
Mill | -0.027 |
Frankie | -0.026 |
Token | who |
Token ID | 508 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
excitement | +0.032 |
delight | +0.030 |
it | +0.029 |
Mill | +0.029 |
Frankie | +0.029 |
Neg logit contributions | |
ems | -0.040 |
ppy | -0.039 |
ophone | -0.037 |
oke | -0.035 |
arl | -0.035 |
Token | had |
Token ID | 550 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ems | +0.054 |
ppy | +0.052 |
arl | +0.050 |
ophone | +0.049 |
oke | +0.048 |
Neg logit contributions | |
excitement | -0.038 |
it | -0.037 |
Mill | -0.036 |
delight | -0.035 |
an | -0.035 |
Token | fast |
Token ID | 3049 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
ems | +0.144 |
ppy | +0.137 |
ophone | +0.132 |
arl | +0.129 |
wy | +0.128 |
Neg logit contributions | |
it | -0.051 |
excitement | -0.050 |
an | -0.046 |
Mill | -0.045 |
sudden | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
ems | +0.001 |
ppy | +0.001 |
ophone | +0.001 |
wy | +0.001 |
arl | +0.001 |
Neg logit contributions | |
it | -0.000 |
excitement | -0.000 |
an | -0.000 |
Mill | -0.000 |
the | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -6.60e-03 |
Pos logit contributions | |
ems | +0.014 |
ppy | +0.013 |
arl | +0.013 |
ophone | +0.013 |
wy | +0.012 |
Neg logit contributions | |
it | -0.005 |
excitement | -0.004 |
an | -0.004 |
Mill | -0.004 |
the | -0.004 |
Token | policeman |
Token ID | 32166 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Mill | +0.001 |
excitement | +0.001 |
Frankie | +0.001 |
delight | +0.000 |
it | +0.000 |
Neg logit contributions | |
ems | -0.001 |
ophone | -0.001 |
ppy | -0.001 |
arl | -0.001 |
oke | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
it | +0.028 |
excitement | +0.026 |
sudden | +0.025 |
the | +0.024 |
an | +0.024 |
Neg logit contributions | |
ems | -0.045 |
arl | -0.043 |
ppy | -0.042 |
wy | -0.039 |
ophone | -0.038 |
Token | him |
Token ID | 683 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ems | +0.037 |
ppy | +0.035 |
ophone | +0.035 |
arl | +0.034 |
oke | +0.033 |
Neg logit contributions | |
excitement | -0.009 |
Mill | -0.008 |
delight | -0.008 |
sudden | -0.008 |
Frankie | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
excitement | +0.111 |
Mill | +0.108 |
delight | +0.104 |
it | +0.101 |
Frankie | +0.100 |
Neg logit contributions | |
ems | -0.244 |
ppy | -0.235 |
ophone | -0.229 |
arl | -0.222 |
oke | -0.220 |
Token | The |
Token ID | 383 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
ems | +0.019 |
ppy | +0.019 |
oke | +0.019 |
arl | +0.018 |
ophone | +0.018 |
Neg logit contributions | |
excitement | -0.009 |
sudden | -0.009 |
delight | -0.009 |
it | -0.009 |
Mill | -0.009 |
Token | policeman |
Token ID | 32166 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
excitement | +0.020 |
Mill | +0.020 |
it | +0.020 |
delight | +0.019 |
Frankie | +0.019 |
Neg logit contributions | |
ems | -0.039 |
ppy | -0.037 |
ophone | -0.036 |
arl | -0.036 |
oke | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
it | +0.023 |
excitement | +0.023 |
sudden | +0.022 |
Mill | +0.021 |
delight | +0.021 |
Neg logit contributions | |
ems | -0.040 |
ppy | -0.038 |
arl | -0.038 |
ophone | -0.036 |
wy | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
ems | +0.007 |
ppy | +0.007 |
oke | +0.006 |
ophone | +0.006 |
arl | +0.006 |
Neg logit contributions | |
excitement | -0.004 |
sudden | -0.004 |
delight | -0.004 |
sight | -0.004 |
Mill | -0.004 |
Token | proud |
Token ID | 6613 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
ems | +0.016 |
ppy | +0.015 |
ophone | +0.014 |
arl | +0.014 |
oke | +0.014 |
Neg logit contributions | |
excitement | -0.008 |
it | -0.008 |
Mill | -0.007 |
delight | -0.007 |
sudden | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
ems | +0.081 |
ppy | +0.076 |
oke | +0.074 |
arl | +0.073 |
ophone | +0.073 |
Neg logit contributions | |
excitement | -0.038 |
Mill | -0.037 |
Frankie | -0.037 |
sudden | -0.035 |
delight | -0.035 |
Token | see |
Token ID | 766 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
sudden | +0.028 |
excitement | +0.027 |
Mill | +0.026 |
it | +0.026 |
Frankie | +0.026 |
Neg logit contributions | |
ems | -0.050 |
ppy | -0.048 |
ophone | -0.046 |
arl | -0.045 |
oke | -0.044 |
Token | it |
Token ID | 340 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
excitement | +0.019 |
sudden | +0.017 |
Mill | +0.017 |
delight | +0.017 |
it | +0.016 |
Neg logit contributions | |
ems | -0.072 |
ppy | -0.069 |
ophone | -0.067 |
arl | -0.066 |
oke | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
excitement | +0.037 |
Mill | +0.036 |
sudden | +0.035 |
delight | +0.034 |
Frankie | +0.034 |
Neg logit contributions | |
ems | -0.081 |
ppy | -0.077 |
ophone | -0.075 |
oke | -0.072 |
ets | -0.072 |
Token | John |
Token ID | 1757 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ems | +0.005 |
ppy | +0.004 |
ophone | +0.004 |
oke | +0.004 |
arl | +0.004 |
Neg logit contributions | |
excitement | -0.002 |
sudden | -0.002 |
delight | -0.002 |
it | -0.002 |
Mill | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
excitement | +0.137 |
it | +0.133 |
Mill | +0.130 |
delight | +0.129 |
sudden | +0.125 |
Neg logit contributions | |
ems | -0.242 |
ppy | -0.231 |
ophone | -0.221 |
arl | -0.218 |
oke | -0.213 |
Token | proud |
Token ID | 6613 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Mill | +0.012 |
sudden | +0.012 |
Frankie | +0.012 |
excitement | +0.012 |
it | +0.011 |
Neg logit contributions | |
ems | -0.039 |
ophone | -0.039 |
ppy | -0.039 |
oke | -0.037 |
wy | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ems | +0.078 |
ppy | +0.074 |
oke | +0.073 |
ets | +0.070 |
arl | +0.070 |
Neg logit contributions | |
Frankie | -0.044 |
Mill | -0.044 |
excitement | -0.043 |
sudden | -0.041 |
delight | -0.040 |
Token | his |
Token ID | 465 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
sudden | +0.008 |
excitement | +0.007 |
Mill | +0.007 |
Frankie | +0.007 |
delight | +0.007 |
Neg logit contributions | |
ems | -0.026 |
ppy | -0.025 |
arl | -0.025 |
ophone | -0.025 |
oke | -0.024 |
Token | work |
Token ID | 670 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
ems | +0.056 |
ophone | +0.055 |
oke | +0.053 |
ppy | +0.053 |
ider | +0.052 |
Neg logit contributions | |
Mill | -0.035 |
Frankie | -0.034 |
Mill | -0.033 |
Samantha | -0.031 |
Its | -0.031 |
Token | that |
Token ID | 326 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
ems | +0.014 |
ppy | +0.013 |
ophone | +0.012 |
arl | +0.012 |
oke | +0.012 |
Neg logit contributions | |
excitement | -0.008 |
Mill | -0.007 |
it | -0.007 |
delight | -0.007 |
sudden | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
excitement | +0.003 |
Mill | +0.003 |
delight | +0.003 |
sudden | +0.003 |
Frankie | +0.003 |
Neg logit contributions | |
ems | -0.009 |
ppy | -0.008 |
ophone | -0.008 |
oke | -0.008 |
wy | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
it | +0.046 |
excitement | +0.044 |
Mill | +0.043 |
an | +0.042 |
delight | +0.041 |
Neg logit contributions | |
ems | -0.088 |
arl | -0.085 |
ppy | -0.084 |
ophone | -0.080 |
oke | -0.077 |
Token | special |
Token ID | 2041 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
excitement | +0.014 |
Mill | +0.014 |
sudden | +0.014 |
delight | +0.013 |
Frankie | +0.013 |
Neg logit contributions | |
ems | -0.031 |
ppy | -0.030 |
ophone | -0.029 |
wy | -0.028 |
arl | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ems | +0.009 |
ppy | +0.008 |
ophone | +0.008 |
arl | +0.008 |
oke | +0.008 |
Neg logit contributions | |
excitement | -0.003 |
Mill | -0.003 |
sudden | -0.003 |
delight | -0.003 |
Frankie | -0.003 |
Token | him |
Token ID | 683 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
it | +0.011 |
excitement | +0.010 |
Mill | +0.009 |
an | +0.009 |
delight | +0.009 |
Neg logit contributions | |
ems | -0.052 |
ppy | -0.050 |
ophone | -0.049 |
arl | -0.048 |
oke | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
excitement | +0.110 |
Mill | +0.103 |
delight | +0.102 |
it | +0.101 |
sudden | +0.099 |
Neg logit contributions | |
ems | -0.261 |
ppy | -0.251 |
ophone | -0.242 |
arl | -0.236 |
oke | -0.232 |
Token | He |
Token ID | 679 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
excitement | +0.009 |
sudden | +0.009 |
delight | +0.008 |
Mill | +0.008 |
it | +0.008 |
Neg logit contributions | |
ems | -0.019 |
ppy | -0.018 |
ophone | -0.018 |
oke | -0.018 |
arl | -0.018 |
Token | decided |
Token ID | 3066 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
ems | +0.038 |
ppy | +0.035 |
arl | +0.035 |
ophone | +0.034 |
oke | +0.032 |
Neg logit contributions | |
excitement | -0.026 |
it | -0.026 |
delight | -0.025 |
Mill | -0.024 |
an | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
excitement | +0.040 |
Mill | +0.037 |
delight | +0.037 |
sudden | +0.036 |
Frankie | +0.034 |
Neg logit contributions | |
ems | -0.117 |
ophone | -0.109 |
ppy | -0.109 |
arl | -0.105 |
oke | -0.104 |
Token | be |
Token ID | 307 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
excitement | +0.017 |
sudden | +0.017 |
it | +0.017 |
Mill | +0.017 |
delight | +0.016 |
Neg logit contributions | |
ems | -0.029 |
ppy | -0.028 |
ophone | -0.026 |
arl | -0.026 |
wy | -0.025 |