Token | . |
Token ID | 13 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
anna | +0.066 |
annah | +0.059 |
uster | +0.059 |
ivering | +0.059 |
ittens | +0.058 |
Neg logit contributions | |
da | -0.026 |
pe | -0.019 |
Sof | -0.018 |
an | -0.018 |
aw | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
da | +0.028 |
pe | +0.023 |
cr | +0.021 |
aw | +0.021 |
Sof | +0.021 |
Neg logit contributions | |
anna | -0.042 |
ittens | -0.038 |
annah | -0.038 |
uster | -0.038 |
amas | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
da | +0.003 |
pe | +0.002 |
cr | +0.002 |
cr | +0.002 |
Sof | +0.002 |
Neg logit contributions | |
anna | -0.004 |
ittens | -0.004 |
annah | -0.004 |
agons | -0.004 |
uster | -0.004 |
Token | Dad |
Token ID | 46270 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
anna | +0.016 |
annah | +0.014 |
agons | +0.014 |
ittens | +0.014 |
ivering | +0.014 |
Neg logit contributions | |
da | -0.017 |
pe | -0.015 |
Sof | -0.014 |
cr | -0.014 |
cr | -0.014 |
Token | came |
Token ID | 1625 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
da | +0.101 |
Sof | +0.092 |
an | +0.084 |
high | +0.083 |
ho | +0.080 |
Neg logit contributions | |
anna | -0.114 |
ivering | -0.102 |
annah | -0.101 |
ider | -0.099 |
amas | -0.099 |
Token | over |
Token ID | 625 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
da | +0.057 |
aw | +0.045 |
Sof | +0.044 |
are | +0.042 |
ho | +0.041 |
Neg logit contributions | |
anna | -0.112 |
uster | -0.101 |
ivering | -0.099 |
annah | -0.097 |
amas | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
da | +0.127 |
Sof | +0.098 |
aw | +0.097 |
cr | +0.096 |
pe | +0.096 |
Neg logit contributions | |
anna | -0.226 |
ivering | -0.210 |
uster | -0.208 |
annah | -0.206 |
ittens | -0.201 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
da | +0.041 |
Sof | +0.039 |
aw | +0.038 |
cr | +0.037 |
ho | +0.036 |
Neg logit contributions | |
anna | -0.055 |
annah | -0.049 |
ital | -0.047 |
belt | -0.046 |
pron | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
da | +0.025 |
Sof | +0.020 |
pe | +0.019 |
cr | +0.018 |
an | +0.018 |
Neg logit contributions | |
anna | -0.053 |
ivering | -0.050 |
uster | -0.048 |
ivery | -0.047 |
agons | -0.046 |
Token | He |
Token ID | 679 |
Feature activation | +4.48e-03 |
Pos logit contributions | |
da | +0.063 |
pe | +0.056 |
an | +0.054 |
Sof | +0.054 |
cr | +0.054 |
Neg logit contributions | |
anna | -0.042 |
uster | -0.036 |
annah | -0.036 |
belt | -0.035 |
agons | -0.035 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
da | +0.006 |
Sof | +0.005 |
an | +0.005 |
cr | +0.005 |
ho | +0.005 |
Neg logit contributions | |
anna | -0.008 |
annah | -0.007 |
ivering | -0.007 |
belt | -0.007 |
ital | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -5.08e-03 |
Pos logit contributions | |
da | +0.007 |
a | +0.006 |
an | +0.006 |
pe | +0.006 |
the | +0.006 |
Neg logit contributions | |
anna | -0.018 |
ivering | -0.017 |
agons | -0.017 |
ivery | -0.017 |
uster | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
anna | +0.014 |
ivering | +0.013 |
uster | +0.013 |
belt | +0.013 |
agons | +0.013 |
Neg logit contributions | |
da | -0.004 |
a | -0.003 |
an | -0.003 |
pe | -0.003 |
Sof | -0.003 |
Token | Her |
Token ID | 9360 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
anna | +0.031 |
ivering | +0.027 |
uster | +0.027 |
agons | +0.027 |
belt | +0.027 |
Neg logit contributions | |
da | -0.014 |
a | -0.013 |
an | -0.012 |
pe | -0.012 |
Sof | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
anna | +0.088 |
ivering | +0.080 |
ivery | +0.079 |
uster | +0.078 |
annah | +0.078 |
Neg logit contributions | |
da | -0.055 |
pe | -0.047 |
a | -0.046 |
an | -0.045 |
cr | -0.045 |
Token | came |
Token ID | 1625 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
da | +0.041 |
an | +0.032 |
pe | +0.032 |
Sof | +0.031 |
a | +0.031 |
Neg logit contributions | |
anna | -0.100 |
ivering | -0.089 |
annah | -0.089 |
uster | -0.088 |
belt | -0.086 |
Token | over |
Token ID | 625 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
da | +0.057 |
pe | +0.044 |
an | +0.043 |
Sof | +0.042 |
cr | +0.042 |
Neg logit contributions | |
anna | -0.127 |
ivering | -0.114 |
uster | -0.114 |
annah | -0.113 |
agons | -0.111 |
Token | to |
Token ID | 284 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
da | +0.117 |
aw | +0.087 |
pe | +0.086 |
Sof | +0.085 |
cr | +0.083 |
Neg logit contributions | |
anna | -0.241 |
annah | -0.219 |
ivering | -0.218 |
uster | -0.215 |
amas | -0.211 |
Token | see |
Token ID | 766 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
da | +0.038 |
pe | +0.029 |
a | +0.028 |
an | +0.027 |
cr | +0.025 |
Neg logit contributions | |
anna | -0.133 |
ivering | -0.121 |
uster | -0.120 |
annah | -0.120 |
agons | -0.119 |
Token | what |
Token ID | 644 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
da | +0.075 |
Sof | +0.059 |
pe | +0.057 |
ho | +0.056 |
cr | +0.055 |
Neg logit contributions | |
anna | -0.164 |
annah | -0.145 |
ivering | -0.143 |
uster | -0.142 |
ittens | -0.137 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
da | +0.092 |
cr | +0.075 |
pe | +0.075 |
ho | +0.072 |
Sof | +0.070 |
Neg logit contributions | |
anna | -0.140 |
annah | -0.121 |
belt | -0.120 |
ital | -0.119 |
ittens | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
anna | +0.003 |
uster | +0.003 |
agons | +0.003 |
ivering | +0.003 |
annah | +0.003 |
Neg logit contributions | |
da | -0.001 |
a | -0.001 |
an | -0.001 |
pe | -0.000 |
to | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
da | +0.014 |
a | +0.011 |
pe | +0.011 |
an | +0.011 |
cr | +0.010 |
Neg logit contributions | |
anna | -0.042 |
ivering | -0.038 |
uster | -0.038 |
agons | -0.038 |
annah | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
anna | +0.014 |
ivering | +0.013 |
uster | +0.013 |
annah | +0.013 |
agons | +0.013 |
Neg logit contributions | |
da | -0.005 |
pe | -0.004 |
a | -0.004 |
an | -0.004 |
cr | -0.003 |
Token | Mom |
Token ID | 29252 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
anna | +0.040 |
uster | +0.036 |
agons | +0.034 |
ital | +0.034 |
rated | +0.034 |
Neg logit contributions | |
da | -0.021 |
a | -0.020 |
an | -0.019 |
the | -0.018 |
pe | -0.018 |
Token | my |
Token ID | 1820 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
da | +0.092 |
Sof | +0.081 |
an | +0.079 |
pe | +0.077 |
a | +0.075 |
Neg logit contributions | |
anna | -0.096 |
ivering | -0.085 |
uster | -0.082 |
annah | -0.080 |
amas | -0.079 |
Token | came |
Token ID | 1625 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
da | +0.041 |
Sof | +0.034 |
an | +0.032 |
cr | +0.031 |
pe | +0.030 |
Neg logit contributions | |
anna | -0.073 |
ivering | -0.066 |
annah | -0.063 |
uster | -0.063 |
amas | -0.062 |
Token | over |
Token ID | 625 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
da | +0.052 |
pe | +0.040 |
an | +0.039 |
Sof | +0.038 |
a | +0.038 |
Neg logit contributions | |
anna | -0.115 |
uster | -0.104 |
ivering | -0.104 |
annah | -0.102 |
agons | -0.101 |
Token | and |
Token ID | 290 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
da | +0.108 |
pe | +0.081 |
Sof | +0.078 |
aw | +0.077 |
an | +0.076 |
Neg logit contributions | |
anna | -0.252 |
ivering | -0.232 |
uster | -0.231 |
annah | -0.230 |
amas | -0.225 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
da | +0.044 |
Sof | +0.039 |
aw | +0.037 |
cr | +0.036 |
hex | +0.035 |
Neg logit contributions | |
anna | -0.072 |
annah | -0.064 |
ivering | -0.062 |
uster | -0.061 |
belt | -0.061 |
Token | at |
Token ID | 379 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
da | +0.030 |
Sof | +0.025 |
cr | +0.024 |
ho | +0.022 |
pe | +0.022 |
Neg logit contributions | |
anna | -0.062 |
ivering | -0.056 |
annah | -0.056 |
uster | -0.054 |
agons | -0.054 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
da | +0.040 |
a | +0.033 |
an | +0.031 |
pe | +0.030 |
the | +0.027 |
Neg logit contributions | |
anna | -0.164 |
ivering | -0.149 |
annah | -0.146 |
agons | -0.146 |
belt | -0.146 |
Token | 's |
Token ID | 338 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
da | +0.022 |
pe | +0.018 |
a | +0.017 |
an | +0.016 |
cr | +0.014 |
Neg logit contributions | |
anna | -0.101 |
uster | -0.094 |
agons | -0.093 |
belt | -0.092 |
ivering | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | +6.21e-03 |
Pos logit contributions | |
da | +0.022 |
pe | +0.018 |
a | +0.018 |
an | +0.018 |
Sof | +0.017 |
Neg logit contributions | |
anna | -0.050 |
ivering | -0.045 |
uster | -0.045 |
annah | -0.044 |
agons | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -6.09e-03 |
Pos logit contributions | |
da | +0.005 |
pe | +0.004 |
a | +0.004 |
an | +0.004 |
Sof | +0.004 |
Neg logit contributions | |
anna | -0.017 |
ivering | -0.015 |
uster | -0.015 |
annah | -0.015 |
agons | -0.015 |
Token | M |
Token ID | 44 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
anna | +0.014 |
ivering | +0.013 |
uster | +0.013 |
agons | +0.012 |
annah | +0.012 |
Neg logit contributions | |
da | -0.008 |
pe | -0.006 |
a | -0.006 |
an | -0.006 |
Sof | -0.006 |
Token | um |
Token ID | 388 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
anna | +0.006 |
uster | +0.005 |
ivering | +0.005 |
ital | +0.005 |
ivery | +0.005 |
Neg logit contributions | |
da | -0.005 |
pe | -0.005 |
Sof | -0.004 |
a | -0.004 |
an | -0.004 |
Token | walked |
Token ID | 6807 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
da | +0.053 |
an | +0.045 |
Sof | +0.042 |
high | +0.041 |
a | +0.040 |
Neg logit contributions | |
anna | -0.115 |
ivering | -0.103 |
annah | -0.101 |
ascal | -0.096 |
agons | -0.096 |
Token | over |
Token ID | 625 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
anna | +0.024 |
annah | +0.021 |
belt | +0.021 |
uster | +0.021 |
ivering | +0.020 |
Neg logit contributions | |
da | -0.013 |
are | -0.010 |
cr | -0.010 |
aw | -0.010 |
Sof | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
da | +0.113 |
aw | +0.091 |
Sof | +0.082 |
gl | +0.081 |
cr | +0.080 |
Neg logit contributions | |
anna | -0.217 |
uster | -0.194 |
annah | -0.193 |
lifestyle | -0.185 |
amas | -0.183 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
da | +0.033 |
aw | +0.028 |
are | +0.027 |
hex | +0.027 |
an | +0.027 |
Neg logit contributions | |
anna | -0.058 |
annah | -0.052 |
uster | -0.049 |
belt | -0.049 |
ivering | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
da | +0.041 |
ho | +0.034 |
cr | +0.033 |
high | +0.032 |
cr | +0.031 |
Neg logit contributions | |
anna | -0.128 |
annah | -0.119 |
uster | -0.118 |
ittens | -0.114 |
ascal | -0.111 |
Token | broken |
Token ID | 5445 |
Feature activation | -7.83e-03 |
Pos logit contributions | |
da | +0.042 |
pe | +0.035 |
a | +0.034 |
an | +0.033 |
cr | +0.032 |
Neg logit contributions | |
anna | -0.094 |
ivering | -0.085 |
uster | -0.085 |
annah | -0.084 |
agons | -0.084 |
Token | branch |
Token ID | 8478 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
anna | +0.018 |
ivering | +0.016 |
belt | +0.016 |
annah | +0.016 |
agons | +0.016 |
Neg logit contributions | |
da | -0.009 |
an | -0.007 |
Sof | -0.007 |
pe | -0.007 |
a | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -8.53e-03 |
Pos logit contributions | |
da | +0.010 |
pe | +0.008 |
cr | +0.007 |
an | +0.007 |
a | +0.007 |
Neg logit contributions | |
anna | -0.022 |
annah | -0.020 |
uster | -0.020 |
ivering | -0.020 |
amas | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
anna | +0.022 |
ivering | +0.020 |
uster | +0.020 |
annah | +0.020 |
agons | +0.020 |
Neg logit contributions | |
da | -0.008 |
pe | -0.006 |
a | -0.006 |
an | -0.006 |
cr | -0.006 |
Token | Mom |
Token ID | 29252 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
anna | +0.047 |
uster | +0.042 |
ivering | +0.042 |
belt | +0.042 |
agons | +0.041 |
Neg logit contributions | |
da | -0.021 |
a | -0.019 |
an | -0.018 |
pe | -0.017 |
cr | -0.017 |
Token | my |
Token ID | 1820 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
da | +0.072 |
an | +0.063 |
Sof | +0.061 |
pe | +0.058 |
high | +0.057 |
Neg logit contributions | |
anna | -0.111 |
ivering | -0.099 |
annah | -0.097 |
uster | -0.097 |
amas | -0.093 |
Token | came |
Token ID | 1625 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
da | +0.036 |
Sof | +0.030 |
an | +0.030 |
pe | +0.028 |
a | +0.028 |
Neg logit contributions | |
anna | -0.073 |
ivering | -0.065 |
annah | -0.065 |
uster | -0.063 |
amas | -0.062 |
Token | over |
Token ID | 625 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
da | +0.048 |
pe | +0.037 |
an | +0.036 |
a | +0.035 |
Sof | +0.035 |
Neg logit contributions | |
anna | -0.121 |
uster | -0.110 |
ivering | -0.110 |
annah | -0.109 |
agons | -0.107 |
Token | and |
Token ID | 290 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
da | +0.105 |
pe | +0.080 |
Sof | +0.076 |
an | +0.075 |
aw | +0.074 |
Neg logit contributions | |
anna | -0.253 |
annah | -0.231 |
uster | -0.231 |
ivering | -0.230 |
amas | -0.225 |
Token | got |
Token ID | 1392 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
da | +0.043 |
Sof | +0.037 |
aw | +0.036 |
an | +0.034 |
cr | +0.034 |
Neg logit contributions | |
anna | -0.076 |
annah | -0.069 |
uster | -0.066 |
belt | -0.066 |
ivering | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
da | +0.054 |
aw | +0.041 |
Sof | +0.038 |
ho | +0.036 |
cr | +0.035 |
Neg logit contributions | |
anna | -0.130 |
annah | -0.121 |
uster | -0.118 |
belt | -0.117 |
amas | -0.117 |
Token | ball |
Token ID | 2613 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
da | +0.044 |
a | +0.037 |
pe | +0.036 |
an | +0.036 |
cr | +0.035 |
Neg logit contributions | |
anna | -0.091 |
ivering | -0.081 |
annah | -0.080 |
uster | -0.079 |
ivery | -0.079 |
Token | for |
Token ID | 329 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
da | +0.024 |
pe | +0.018 |
Sof | +0.018 |
an | +0.017 |
aw | +0.017 |
Neg logit contributions | |
anna | -0.056 |
ivering | -0.052 |
uster | -0.052 |
annah | -0.051 |
belt | -0.051 |
Token | His |
Token ID | 6653 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
anna | +0.055 |
ancer | +0.053 |
uster | +0.053 |
agons | +0.051 |
spine | +0.051 |
Neg logit contributions | |
a | -0.023 |
M | -0.021 |
an | -0.020 |
da | -0.020 |
pe | -0.020 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
anna | +0.134 |
annah | +0.120 |
uster | +0.120 |
ivering | +0.119 |
ivery | +0.119 |
Neg logit contributions | |
da | -0.061 |
a | -0.055 |
pe | -0.054 |
cr | -0.053 |
an | -0.050 |
Token | my |
Token ID | 1820 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
da | +0.057 |
pe | +0.047 |
an | +0.047 |
a | +0.046 |
Sof | +0.045 |
Neg logit contributions | |
anna | -0.104 |
ivering | -0.093 |
uster | -0.092 |
annah | -0.092 |
agons | -0.091 |
Token | came |
Token ID | 1625 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
da | +0.031 |
pe | +0.025 |
an | +0.024 |
a | +0.024 |
Sof | +0.024 |
Neg logit contributions | |
anna | -0.068 |
ivering | -0.061 |
uster | -0.060 |
annah | -0.060 |
agons | -0.059 |
Token | running |
Token ID | 2491 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
da | +0.050 |
pe | +0.042 |
a | +0.040 |
an | +0.040 |
cr | +0.038 |
Neg logit contributions | |
anna | -0.113 |
ivering | -0.102 |
uster | -0.101 |
annah | -0.101 |
agons | -0.100 |
Token | over |
Token ID | 625 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
da | +0.017 |
pe | +0.012 |
Sof | +0.012 |
cr | +0.012 |
aw | +0.011 |
Neg logit contributions | |
anna | -0.040 |
uster | -0.037 |
annah | -0.036 |
ivering | -0.036 |
belt | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
da | +0.095 |
pe | +0.069 |
Sof | +0.066 |
an | +0.065 |
aw | +0.064 |
Neg logit contributions | |
anna | -0.263 |
ivering | -0.241 |
uster | -0.240 |
annah | -0.238 |
agons | -0.235 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
da | +0.047 |
Sof | +0.038 |
an | +0.038 |
aw | +0.037 |
pe | +0.036 |
Neg logit contributions | |
anna | -0.097 |
ivering | -0.087 |
annah | -0.086 |
uster | -0.085 |
belt | -0.084 |
Token | his |
Token ID | 465 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
da | +0.080 |
Sof | +0.066 |
ho | +0.063 |
cr | +0.062 |
pe | +0.060 |
Neg logit contributions | |
anna | -0.132 |
uster | -0.126 |
agons | -0.124 |
ivering | -0.123 |
ittens | -0.122 |
Token | wide |
Token ID | 3094 |
Feature activation | -5.51e-03 |
Pos logit contributions | |
anna | +0.041 |
uster | +0.035 |
ital | +0.035 |
annah | +0.034 |
agons | +0.034 |
Neg logit contributions | |
da | -0.031 |
a | -0.030 |
pe | -0.029 |
an | -0.028 |
cr | -0.027 |
Token | scrape |
Token ID | 42778 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
anna | +0.011 |
agons | +0.010 |
uster | +0.009 |
ital | +0.009 |
annah | +0.009 |
Neg logit contributions | |
da | -0.009 |
pe | -0.008 |
a | -0.008 |
cr | -0.008 |
an | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -6.71e-03 |
Pos logit contributions | |
da | +0.015 |
pe | +0.012 |
cr | +0.012 |
an | +0.011 |
a | +0.011 |
Neg logit contributions | |
anna | -0.030 |
annah | -0.027 |
uster | -0.026 |
ittens | -0.026 |
ivering | -0.026 |
Token | Mom |
Token ID | 29252 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
anna | +0.016 |
uster | +0.014 |
ivering | +0.014 |
agons | +0.014 |
annah | +0.014 |
Neg logit contributions | |
da | -0.008 |
pe | -0.007 |
a | -0.007 |
an | -0.007 |
Sof | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -6.79e-03 |
Pos logit contributions | |
da | +0.050 |
pe | +0.040 |
a | +0.038 |
an | +0.037 |
cr | +0.035 |
Neg logit contributions | |
anna | -0.145 |
ivering | -0.132 |
uster | -0.131 |
annah | -0.131 |
agons | -0.131 |
Token | Dad |
Token ID | 17415 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
anna | +0.014 |
uster | +0.012 |
annah | +0.012 |
ivering | +0.012 |
belt | +0.012 |
Neg logit contributions | |
da | -0.010 |
pe | -0.008 |
an | -0.008 |
Sof | -0.008 |
a | -0.008 |
Token | came |
Token ID | 1625 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
da | +0.071 |
Sof | +0.061 |
an | +0.058 |
high | +0.054 |
hex | +0.053 |
Neg logit contributions | |
anna | -0.137 |
ivering | -0.123 |
uster | -0.123 |
annah | -0.118 |
ivery | -0.116 |
Token | over |
Token ID | 625 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
da | +0.056 |
aw | +0.043 |
Sof | +0.043 |
cr | +0.042 |
pe | +0.041 |
Neg logit contributions | |
anna | -0.112 |
uster | -0.101 |
ivering | -0.099 |
annah | -0.098 |
agons | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
da | +0.115 |
aw | +0.088 |
Sof | +0.088 |
pe | +0.087 |
cr | +0.086 |
Neg logit contributions | |
anna | -0.223 |
annah | -0.203 |
ivering | -0.203 |
uster | -0.201 |
ittens | -0.196 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
da | +0.043 |
aw | +0.042 |
Sof | +0.040 |
an | +0.037 |
hex | +0.036 |
Neg logit contributions | |
anna | -0.062 |
uster | -0.051 |
annah | -0.051 |
ital | -0.051 |
ivering | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
da | +0.061 |
cr | +0.059 |
ho | +0.053 |
gl | +0.052 |
hex | +0.049 |
Neg logit contributions | |
anna | -0.126 |
annah | -0.121 |
uster | -0.113 |
ittens | -0.112 |
agons | -0.106 |
Token | shell |
Token ID | 7582 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
da | +0.045 |
pe | +0.039 |
an | +0.038 |
a | +0.038 |
Sof | +0.036 |
Neg logit contributions | |
anna | -0.074 |
ivering | -0.065 |
uster | -0.065 |
annah | -0.065 |
agons | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
da | +0.008 |
pe | +0.006 |
an | +0.006 |
a | +0.006 |
Sof | +0.006 |
Neg logit contributions | |
anna | -0.021 |
ivering | -0.019 |
annah | -0.019 |
agons | -0.019 |
uster | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
da | +0.043 |
Sof | +0.035 |
pe | +0.034 |
cr | +0.034 |
cr | +0.033 |
Neg logit contributions | |
anna | -0.072 |
ivering | -0.063 |
uster | -0.061 |
belt | -0.060 |
annah | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
da | +0.018 |
a | +0.017 |
an | +0.016 |
the | +0.015 |
Sof | +0.014 |
Neg logit contributions | |
anna | -0.045 |
ivering | -0.041 |
ivery | -0.040 |
ital | -0.040 |
annah | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-04 |
Pos logit contributions | |
da | +0.019 |
pe | +0.015 |
cr | +0.014 |
an | +0.014 |
Sof | +0.014 |
Neg logit contributions | |
anna | -0.041 |
annah | -0.036 |
uster | -0.036 |
ivering | -0.036 |
agons | -0.036 |
Token | Mom |
Token ID | 29252 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
anna | +0.000 |
ivering | +0.000 |
uster | +0.000 |
annah | +0.000 |
agons | +0.000 |
Neg logit contributions | |
da | -0.000 |
pe | -0.000 |
a | -0.000 |
an | -0.000 |
Sof | -0.000 |
Token | came |
Token ID | 1625 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
da | +0.072 |
an | +0.063 |
Sof | +0.062 |
high | +0.057 |
a | +0.056 |
Neg logit contributions | |
anna | -0.137 |
ivering | -0.122 |
uster | -0.121 |
annah | -0.119 |
amas | -0.116 |
Token | over |
Token ID | 625 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
da | +0.050 |
Sof | +0.037 |
aw | +0.037 |
cr | +0.037 |
an | +0.037 |
Neg logit contributions | |
anna | -0.111 |
uster | -0.100 |
ivering | -0.099 |
annah | -0.098 |
amas | -0.095 |
Token | and |
Token ID | 290 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
da | +0.112 |
pe | +0.087 |
Sof | +0.085 |
aw | +0.083 |
an | +0.083 |
Neg logit contributions | |
anna | -0.234 |
uster | -0.213 |
ivering | -0.213 |
annah | -0.212 |
ittens | -0.206 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
da | +0.041 |
Sof | +0.038 |
aw | +0.038 |
an | +0.037 |
are | +0.036 |
Neg logit contributions | |
anna | -0.065 |
annah | -0.056 |
uster | -0.054 |
ivering | -0.053 |
belt | -0.053 |
Token | what |
Token ID | 644 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
da | +0.067 |
pe | +0.055 |
cr | +0.054 |
ho | +0.053 |
cr | +0.052 |
Neg logit contributions | |
anna | -0.143 |
uster | -0.135 |
annah | -0.133 |
agons | -0.131 |
ittens | -0.129 |
Token | was |
Token ID | 373 |
Feature activation | -3.39e-03 |
Pos logit contributions | |
da | +0.087 |
pe | +0.072 |
Sof | +0.067 |
cr | +0.066 |
ho | +0.066 |
Neg logit contributions | |
anna | -0.123 |
annah | -0.112 |
belt | -0.110 |
ital | -0.110 |
ittens | -0.110 |
Token | happening |
Token ID | 5836 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
anna | +0.007 |
agons | +0.006 |
annah | +0.006 |
ivering | +0.006 |
belt | +0.006 |
Neg logit contributions | |
da | -0.005 |
pe | -0.004 |
Sof | -0.004 |
cr | -0.004 |
an | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.41e-03 |
Pos logit contributions | |
da | +0.010 |
a | +0.008 |
an | +0.008 |
pe | +0.007 |
Sof | +0.007 |
Neg logit contributions | |
anna | -0.033 |
ivering | -0.031 |
uster | -0.030 |
agons | -0.030 |
belt | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
anna | +0.015 |
ivering | +0.013 |
agons | +0.013 |
uster | +0.013 |
belt | +0.013 |
Neg logit contributions | |
da | -0.004 |
a | -0.004 |
pe | -0.003 |
an | -0.003 |
Sof | -0.003 |
Token | Her |
Token ID | 9360 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
anna | +0.035 |
agons | +0.033 |
uster | +0.033 |
immers | +0.032 |
rated | +0.032 |
Neg logit contributions | |
da | -0.015 |
a | -0.014 |
an | -0.013 |
pe | -0.013 |
cr | -0.012 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
anna | +0.098 |
ivering | +0.088 |
uster | +0.087 |
annah | +0.086 |
agons | +0.086 |
Neg logit contributions | |
da | -0.056 |
pe | -0.048 |
a | -0.047 |
an | -0.046 |
cr | -0.045 |
Token | came |
Token ID | 1625 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
da | +0.055 |
Sof | +0.045 |
an | +0.045 |
high | +0.042 |
pe | +0.042 |
Neg logit contributions | |
anna | -0.089 |
ivering | -0.079 |
annah | -0.077 |
uster | -0.075 |
belt | -0.074 |
Token | over |
Token ID | 625 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
da | +0.048 |
pe | +0.038 |
an | +0.037 |
a | +0.037 |
Sof | +0.035 |
Neg logit contributions | |
anna | -0.117 |
ivering | -0.106 |
uster | -0.105 |
annah | -0.105 |
agons | -0.104 |
Token | and |
Token ID | 290 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
da | +0.110 |
pe | +0.084 |
Sof | +0.082 |
aw | +0.081 |
an | +0.081 |
Neg logit contributions | |
anna | -0.239 |
annah | -0.218 |
ivering | -0.217 |
uster | -0.217 |
amas | -0.211 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
da | +0.042 |
Sof | +0.036 |
aw | +0.035 |
cr | +0.034 |
an | +0.034 |
Neg logit contributions | |
anna | -0.079 |
annah | -0.071 |
ivering | -0.067 |
uster | -0.067 |
belt | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
da | +0.056 |
pe | +0.045 |
cr | +0.043 |
Sof | +0.042 |
ho | +0.042 |
Neg logit contributions | |
anna | -0.149 |
annah | -0.138 |
uster | -0.136 |
ivering | -0.133 |
ittens | -0.132 |
Token | whale |
Token ID | 22206 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
da | +0.053 |
Sof | +0.050 |
an | +0.047 |
aw | +0.045 |
pe | +0.044 |
Neg logit contributions | |
anna | -0.082 |
ivering | -0.074 |
agons | -0.073 |
annah | -0.071 |
uster | -0.071 |
Token | too |
Token ID | 1165 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
da | +0.035 |
pe | +0.028 |
a | +0.027 |
an | +0.026 |
cr | +0.025 |
Neg logit contributions | |
anna | -0.095 |
uster | -0.086 |
annah | -0.086 |
ivering | -0.086 |
agons | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
anna | +0.017 |
ivering | +0.015 |
uster | +0.015 |
annah | +0.015 |
agons | +0.015 |
Neg logit contributions | |
da | -0.006 |
pe | -0.005 |
an | -0.005 |
a | -0.005 |
cr | -0.004 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
anna | +0.053 |
uster | +0.051 |
agons | +0.050 |
ancer | +0.049 |
immers | +0.049 |
Neg logit contributions | |
da | -0.021 |
a | -0.021 |
an | -0.019 |
pe | -0.018 |
the | -0.018 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
anna | +0.113 |
ivering | +0.100 |
uster | +0.100 |
annah | +0.100 |
agons | +0.099 |
Neg logit contributions | |
da | -0.072 |
pe | -0.062 |
a | -0.061 |
an | -0.061 |
cr | -0.059 |
Token | my |
Token ID | 1820 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
da | +0.054 |
pe | +0.047 |
a | +0.046 |
an | +0.046 |
cr | +0.044 |
Neg logit contributions | |
anna | -0.074 |
ivering | -0.065 |
uster | -0.065 |
annah | -0.065 |
agons | -0.064 |
Token | came |
Token ID | 1625 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
da | +0.020 |
pe | +0.016 |
an | +0.016 |
a | +0.016 |
Sof | +0.015 |
Neg logit contributions | |
anna | -0.042 |
ivering | -0.038 |
uster | -0.038 |
annah | -0.037 |
agons | -0.037 |
Token | over |
Token ID | 625 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
da | +0.048 |
pe | +0.039 |
an | +0.038 |
a | +0.038 |
Sof | +0.037 |
Neg logit contributions | |
anna | -0.096 |
ivering | -0.086 |
uster | -0.086 |
annah | -0.085 |
agons | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
da | +0.101 |
pe | +0.078 |
an | +0.075 |
Sof | +0.074 |
a | +0.073 |
Neg logit contributions | |
anna | -0.251 |
ivering | -0.230 |
uster | -0.228 |
annah | -0.227 |
agons | -0.223 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
da | +0.038 |
Sof | +0.033 |
aw | +0.032 |
an | +0.031 |
cr | +0.030 |
Neg logit contributions | |
anna | -0.071 |
annah | -0.063 |
ivering | -0.063 |
uster | -0.061 |
ital | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
da | +0.063 |
cr | +0.050 |
Sof | +0.050 |
pe | +0.050 |
ho | +0.049 |
Neg logit contributions | |
anna | -0.153 |
annah | -0.140 |
ivering | -0.139 |
uster | -0.138 |
agons | -0.135 |
Token | coin |
Token ID | 10752 |
Feature activation | +8.12e-03 |
Pos logit contributions | |
da | +0.057 |
Sof | +0.047 |
an | +0.047 |
pe | +0.047 |
a | +0.046 |
Neg logit contributions | |
anna | -0.084 |
ivering | -0.075 |
annah | -0.074 |
uster | -0.074 |
belt | -0.073 |
Token | on |
Token ID | 319 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
da | +0.008 |
pe | +0.006 |
an | +0.006 |
a | +0.006 |
Sof | +0.006 |
Neg logit contributions | |
anna | -0.020 |
ivering | -0.019 |
annah | -0.018 |
uster | -0.018 |
agons | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
agons | +0.012 |
anna | +0.012 |
uster | +0.011 |
ivering | +0.011 |
ital | +0.011 |
Neg logit contributions | |
a | -0.004 |
an | -0.004 |
da | -0.003 |
Sof | -0.003 |
the | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
anna | +0.004 |
ivering | +0.004 |
uster | +0.004 |
belt | +0.004 |
agons | +0.004 |
Neg logit contributions | |
da | -0.001 |
a | -0.001 |
an | -0.001 |
pe | -0.001 |
the | -0.001 |
Token | Her |
Token ID | 9360 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
anna | +0.036 |
amas | +0.034 |
uster | +0.034 |
agons | +0.034 |
rated | +0.034 |
Neg logit contributions | |
a | -0.014 |
da | -0.013 |
an | -0.013 |
the | -0.012 |
aw | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
anna | +0.116 |
ivering | +0.106 |
ivery | +0.105 |
uster | +0.104 |
ital | +0.104 |
Neg logit contributions | |
da | -0.057 |
a | -0.051 |
pe | -0.049 |
an | -0.047 |
cr | -0.047 |
Token | came |
Token ID | 1625 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
da | +0.041 |
pe | +0.033 |
a | +0.032 |
an | +0.031 |
cr | +0.030 |
Neg logit contributions | |
anna | -0.116 |
agons | -0.106 |
uster | -0.106 |
ivering | -0.105 |
annah | -0.105 |
Token | over |
Token ID | 625 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
da | +0.041 |
pe | +0.033 |
a | +0.033 |
an | +0.032 |
cr | +0.028 |
Neg logit contributions | |
anna | -0.132 |
ivering | -0.120 |
agons | -0.119 |
annah | -0.119 |
uster | -0.119 |
Token | and |
Token ID | 290 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
da | +0.100 |
pe | +0.076 |
an | +0.073 |
Sof | +0.072 |
a | +0.070 |
Neg logit contributions | |
anna | -0.252 |
ivering | -0.229 |
annah | -0.229 |
uster | -0.228 |
agons | -0.223 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
da | +0.048 |
Sof | +0.041 |
aw | +0.040 |
cr | +0.038 |
hex | +0.038 |
Neg logit contributions | |
anna | -0.080 |
annah | -0.071 |
ivering | -0.070 |
uster | -0.068 |
belt | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
da | +0.010 |
pe | +0.007 |
an | +0.007 |
Sof | +0.007 |
cr | +0.007 |
Neg logit contributions | |
anna | -0.026 |
annah | -0.024 |
ivering | -0.023 |
uster | -0.023 |
belt | -0.023 |
Token | " |
Token ID | 366 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
da | +0.033 |
a | +0.032 |
pe | +0.030 |
an | +0.029 |
the | +0.026 |
Neg logit contributions | |
anna | -0.134 |
agons | -0.128 |
ital | -0.125 |
ivering | -0.123 |
ivery | -0.123 |
Token | What |
Token ID | 2061 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
da | +0.058 |
pe | +0.052 |
a | +0.051 |
an | +0.050 |
cr | +0.048 |
Neg logit contributions | |
anna | -0.083 |
agons | -0.074 |
uster | -0.073 |
annah | -0.073 |
belt | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
anna | +0.010 |
ivering | +0.009 |
uster | +0.009 |
agons | +0.009 |
annah | +0.009 |
Neg logit contributions | |
da | -0.003 |
a | -0.002 |
pe | -0.002 |
an | -0.002 |
Sof | -0.002 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
anna | +0.046 |
agons | +0.044 |
uster | +0.043 |
immers | +0.042 |
ascal | +0.042 |
Neg logit contributions | |
da | -0.017 |
a | -0.016 |
an | -0.015 |
pe | -0.015 |
high | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
anna | +0.114 |
ivering | +0.101 |
uster | +0.101 |
annah | +0.100 |
agons | +0.099 |
Neg logit contributions | |
da | -0.075 |
pe | -0.065 |
a | -0.064 |
an | -0.064 |
cr | -0.061 |
Token | my |
Token ID | 1820 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
da | +0.057 |
Sof | +0.049 |
an | +0.049 |
pe | +0.047 |
a | +0.047 |
Neg logit contributions | |
anna | -0.060 |
ivering | -0.053 |
annah | -0.050 |
uster | -0.050 |
ivery | -0.049 |
Token | came |
Token ID | 1625 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
da | +0.018 |
Sof | +0.015 |
an | +0.014 |
high | +0.014 |
are | +0.014 |
Neg logit contributions | |
anna | -0.034 |
ivering | -0.031 |
annah | -0.030 |
uster | -0.029 |
amas | -0.029 |
Token | over |
Token ID | 625 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
da | +0.047 |
pe | +0.037 |
an | +0.037 |
Sof | +0.036 |
cr | +0.036 |
Neg logit contributions | |
anna | -0.090 |
ivering | -0.081 |
uster | -0.081 |
annah | -0.080 |
agons | -0.078 |
Token | to |
Token ID | 284 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
da | +0.114 |
aw | +0.090 |
Sof | +0.087 |
pe | +0.084 |
cr | +0.082 |
Neg logit contributions | |
anna | -0.229 |
uster | -0.209 |
ivering | -0.209 |
annah | -0.208 |
amas | -0.202 |
Token | see |
Token ID | 766 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
da | +0.052 |
pe | +0.043 |
an | +0.042 |
a | +0.041 |
Sof | +0.040 |
Neg logit contributions | |
anna | -0.108 |
ivering | -0.097 |
annah | -0.096 |
uster | -0.096 |
agons | -0.095 |
Token | what |
Token ID | 644 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
da | +0.068 |
pe | +0.054 |
Sof | +0.054 |
an | +0.049 |
aw | +0.049 |
Neg logit contributions | |
anna | -0.162 |
ivering | -0.145 |
annah | -0.145 |
uster | -0.144 |
agons | -0.141 |
Token | she |
Token ID | 673 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
da | +0.081 |
pe | +0.066 |
Sof | +0.064 |
aw | +0.063 |
ho | +0.063 |
Neg logit contributions | |
anna | -0.141 |
annah | -0.125 |
ital | -0.125 |
ittens | -0.124 |
belt | -0.124 |
Token | had |
Token ID | 550 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
anna | +0.114 |
ivering | +0.103 |
uster | +0.102 |
annah | +0.102 |
agons | +0.102 |
Neg logit contributions | |
da | -0.045 |
pe | -0.036 |
an | -0.035 |
a | -0.034 |
Sof | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
anna | +0.033 |
ivering | +0.030 |
annah | +0.030 |
uster | +0.029 |
ivery | +0.029 |
Neg logit contributions | |
da | -0.011 |
pe | -0.008 |
an | -0.007 |
cr | -0.007 |
Sof | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +5.16e-03 |
Pos logit contributions | |
da | +0.008 |
a | +0.007 |
pe | +0.007 |
an | +0.006 |
Sof | +0.006 |
Neg logit contributions | |
anna | -0.030 |
ivering | -0.027 |
agons | -0.027 |
uster | -0.027 |
ital | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
da | +0.005 |
pe | +0.004 |
an | +0.004 |
a | +0.004 |
cr | +0.004 |
Neg logit contributions | |
anna | -0.013 |
ivering | -0.012 |
annah | -0.012 |
uster | -0.012 |
agons | -0.012 |
Token | Mom |
Token ID | 29252 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
anna | +0.040 |
agons | +0.037 |
uster | +0.037 |
amas | +0.036 |
ivering | +0.036 |
Neg logit contributions | |
da | -0.011 |
a | -0.010 |
pe | -0.009 |
an | -0.009 |
aw | -0.008 |
Token | came |
Token ID | 1625 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
da | +0.076 |
Sof | +0.063 |
an | +0.060 |
high | +0.056 |
cr | +0.055 |
Neg logit contributions | |
anna | -0.116 |
ivering | -0.107 |
uster | -0.103 |
annah | -0.101 |
amas | -0.100 |
Token | over |
Token ID | 625 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
da | +0.045 |
pe | +0.035 |
an | +0.034 |
Sof | +0.033 |
cr | +0.033 |
Neg logit contributions | |
anna | -0.099 |
uster | -0.088 |
ivering | -0.088 |
annah | -0.088 |
agons | -0.086 |
Token | and |
Token ID | 290 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
da | +0.102 |
pe | +0.077 |
an | +0.073 |
aw | +0.072 |
Sof | +0.071 |
Neg logit contributions | |
anna | -0.248 |
annah | -0.226 |
ivering | -0.225 |
uster | -0.225 |
ittens | -0.219 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
da | +0.033 |
Sof | +0.029 |
cr | +0.028 |
aw | +0.028 |
hex | +0.027 |
Neg logit contributions | |
anna | -0.051 |
annah | -0.047 |
ivering | -0.044 |
belt | -0.043 |
uster | -0.043 |
Token | them |
Token ID | 606 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
da | +0.070 |
cr | +0.063 |
cr | +0.062 |
gl | +0.057 |
ho | +0.057 |
Neg logit contributions | |
anna | -0.118 |
annah | -0.109 |
uster | -0.105 |
ittens | -0.102 |
ascal | -0.101 |
Token | fighting |
Token ID | 4330 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
da | +0.029 |
pe | +0.023 |
a | +0.022 |
an | +0.022 |
cr | +0.021 |
Neg logit contributions | |
anna | -0.077 |
ivering | -0.069 |
uster | -0.069 |
annah | -0.069 |
agons | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
da | +0.054 |
Sof | +0.039 |
pe | +0.039 |
aw | +0.036 |
ho | +0.035 |
Neg logit contributions | |
anna | -0.094 |
ivering | -0.087 |
ivery | -0.085 |
annah | -0.085 |
amas | -0.085 |
Token | His |
Token ID | 6653 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
anna | +0.031 |
uster | +0.029 |
belt | +0.028 |
agons | +0.028 |
ancer | +0.028 |
Neg logit contributions | |
a | -0.018 |
an | -0.018 |
da | -0.016 |
the | -0.016 |
many | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
anna | +0.163 |
uster | +0.149 |
ivering | +0.147 |
ivery | +0.143 |
annah | +0.140 |
Neg logit contributions | |
da | -0.107 |
pe | -0.100 |
a | -0.100 |
an | -0.096 |
cr | -0.094 |
Token | and |
Token ID | 290 |
Feature activation | -7.80e-03 |
Pos logit contributions | |
da | +0.034 |
pe | +0.029 |
a | +0.028 |
an | +0.026 |
cr | +0.025 |
Neg logit contributions | |
anna | -0.103 |
agons | -0.095 |
uster | -0.094 |
annah | -0.093 |
belt | -0.093 |
Token | dad |
Token ID | 9955 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
anna | +0.015 |
uster | +0.014 |
ivering | +0.014 |
annah | +0.014 |
agons | +0.013 |
Neg logit contributions | |
da | -0.012 |
pe | -0.010 |
an | -0.010 |
a | -0.010 |
Sof | -0.010 |
Token | ran |
Token ID | 4966 |
Feature activation | +4.19e-03 |
Pos logit contributions | |
da | +0.050 |
Sof | +0.038 |
an | +0.037 |
pe | +0.037 |
a | +0.036 |
Neg logit contributions | |
anna | -0.109 |
ivering | -0.099 |
uster | -0.098 |
annah | -0.096 |
ivery | -0.096 |
Token | over |
Token ID | 625 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
da | +0.003 |
pe | +0.002 |
an | +0.002 |
a | +0.002 |
cr | +0.002 |
Neg logit contributions | |
anna | -0.011 |
uster | -0.010 |
annah | -0.010 |
ivering | -0.010 |
agons | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
da | +0.091 |
pe | +0.066 |
Sof | +0.065 |
aw | +0.062 |
an | +0.059 |
Neg logit contributions | |
anna | -0.253 |
uster | -0.233 |
annah | -0.232 |
ivering | -0.229 |
agons | -0.226 |
Token | him |
Token ID | 683 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
da | +0.042 |
a | +0.036 |
pe | +0.036 |
an | +0.035 |
cr | +0.032 |
Neg logit contributions | |
anna | -0.107 |
ivering | -0.097 |
uster | -0.096 |
belt | -0.096 |
agons | -0.096 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
da | +0.010 |
a | +0.009 |
pe | +0.008 |
an | +0.008 |
the | +0.007 |
Neg logit contributions | |
anna | -0.046 |
agons | -0.043 |
ivery | -0.043 |
uster | -0.042 |
ivering | -0.042 |
Token | looking |
Token ID | 2045 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
da | +0.022 |
pe | +0.019 |
a | +0.019 |
an | +0.018 |
the | +0.016 |
Neg logit contributions | |
anna | -0.053 |
agons | -0.049 |
uster | -0.048 |
ivery | -0.048 |
ital | -0.048 |
Token | worried |
Token ID | 7960 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
da | +0.007 |
pe | +0.006 |
Sof | +0.005 |
an | +0.005 |
a | +0.005 |
Neg logit contributions | |
anna | -0.018 |
ivering | -0.016 |
uster | -0.016 |
annah | -0.016 |
agons | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
anna | +0.028 |
ivering | +0.026 |
uster | +0.025 |
annah | +0.025 |
agons | +0.025 |
Neg logit contributions | |
da | -0.010 |
pe | -0.008 |
a | -0.008 |
an | -0.008 |
cr | -0.007 |
Token | His |
Token ID | 6653 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
anna | +0.060 |
uster | +0.057 |
agons | +0.055 |
ancer | +0.054 |
ivery | +0.054 |
Neg logit contributions | |
da | -0.028 |
a | -0.027 |
pe | -0.026 |
an | -0.025 |
the | -0.024 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
anna | +0.134 |
annah | +0.119 |
uster | +0.119 |
ivering | +0.118 |
ivery | +0.116 |
Neg logit contributions | |
da | -0.070 |
a | -0.062 |
pe | -0.062 |
an | -0.059 |
cr | -0.059 |
Token | came |
Token ID | 1625 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
da | +0.049 |
pe | +0.041 |
an | +0.041 |
a | +0.040 |
Sof | +0.040 |
Neg logit contributions | |
anna | -0.086 |
ivering | -0.077 |
uster | -0.076 |
annah | -0.075 |
agons | -0.074 |
Token | running |
Token ID | 2491 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
da | +0.045 |
pe | +0.038 |
a | +0.037 |
an | +0.036 |
cr | +0.034 |
Neg logit contributions | |
anna | -0.093 |
ivering | -0.083 |
uster | -0.083 |
annah | -0.082 |
agons | -0.082 |
Token | over |
Token ID | 625 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
da | +0.012 |
Sof | +0.009 |
aw | +0.009 |
pe | +0.009 |
cr | +0.009 |
Neg logit contributions | |
anna | -0.027 |
uster | -0.025 |
ivering | -0.025 |
annah | -0.024 |
belt | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
da | +0.093 |
pe | +0.067 |
Sof | +0.066 |
an | +0.064 |
aw | +0.063 |
Neg logit contributions | |
anna | -0.255 |
ivering | -0.233 |
uster | -0.233 |
annah | -0.231 |
agons | -0.228 |
Token | picked |
Token ID | 6497 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
da | +0.044 |
Sof | +0.036 |
an | +0.035 |
aw | +0.035 |
pe | +0.033 |
Neg logit contributions | |
anna | -0.091 |
ivering | -0.081 |
annah | -0.081 |
uster | -0.079 |
belt | -0.077 |
Token | him |
Token ID | 683 |
Feature activation | +7.56e-03 |
Pos logit contributions | |
da | +0.034 |
Sof | +0.028 |
cr | +0.028 |
ho | +0.027 |
cr | +0.026 |
Neg logit contributions | |
anna | -0.045 |
uster | -0.041 |
annah | -0.040 |
amas | -0.038 |
agons | -0.038 |
Token | up |
Token ID | 510 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
da | +0.011 |
Sof | +0.009 |
cr | +0.008 |
aw | +0.008 |
ho | +0.008 |
Neg logit contributions | |
anna | -0.016 |
ivering | -0.014 |
annah | -0.014 |
ivery | -0.014 |
uster | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
da | +0.021 |
pe | +0.015 |
Sof | +0.014 |
an | +0.014 |
a | +0.014 |
Neg logit contributions | |
anna | -0.060 |
ivering | -0.055 |
annah | -0.055 |
uster | -0.054 |
belt | -0.054 |
Token | calling |
Token ID | 4585 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
da | +0.003 |
pe | +0.002 |
an | +0.002 |
a | +0.002 |
Sof | +0.002 |
Neg logit contributions | |
anna | -0.008 |
ivering | -0.008 |
uster | -0.008 |
annah | -0.008 |
agons | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
da | +0.015 |
pe | +0.012 |
Sof | +0.011 |
an | +0.011 |
cr | +0.011 |
Neg logit contributions | |
anna | -0.036 |
uster | -0.033 |
annah | -0.033 |
ivering | -0.033 |
agons | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
da | +0.011 |
a | +0.009 |
an | +0.008 |
pe | +0.008 |
Sof | +0.007 |
Neg logit contributions | |
anna | -0.046 |
ivering | -0.043 |
annah | -0.042 |
uster | -0.042 |
ivery | -0.042 |
Token | Mum |
Token ID | 38367 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
da | +0.012 |
a | +0.012 |
an | +0.012 |
pe | +0.011 |
Sof | +0.010 |
Neg logit contributions | |
anna | -0.028 |
agons | -0.026 |
ital | -0.026 |
ivering | -0.026 |
uster | -0.026 |
Token | ran |
Token ID | 4966 |
Feature activation | +8.54e-03 |
Pos logit contributions | |
da | +0.065 |
pe | +0.054 |
a | +0.052 |
an | +0.052 |
cr | +0.049 |
Neg logit contributions | |
anna | -0.148 |
ivering | -0.133 |
uster | -0.133 |
annah | -0.132 |
agons | -0.132 |
Token | over |
Token ID | 625 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
da | +0.008 |
pe | +0.005 |
cr | +0.005 |
an | +0.005 |
Sof | +0.005 |
Neg logit contributions | |
anna | -0.023 |
uster | -0.021 |
annah | -0.021 |
ivering | -0.020 |
belt | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
da | +0.098 |
aw | +0.072 |
Sof | +0.069 |
pe | +0.066 |
cr | +0.064 |
Neg logit contributions | |
anna | -0.240 |
uster | -0.225 |
annah | -0.220 |
ivering | -0.215 |
belt | -0.213 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
da | +0.038 |
aw | +0.031 |
Sof | +0.030 |
an | +0.029 |
cr | +0.029 |
Neg logit contributions | |
anna | -0.072 |
annah | -0.065 |
uster | -0.064 |
ivering | -0.063 |
belt | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
da | +0.081 |
Sof | +0.065 |
ho | +0.063 |
cr | +0.063 |
aw | +0.063 |
Neg logit contributions | |
anna | -0.112 |
uster | -0.105 |
annah | -0.102 |
ittens | -0.102 |
agons | -0.102 |
Token | problem |
Token ID | 1917 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
da | +0.044 |
pe | +0.038 |
a | +0.037 |
an | +0.037 |
cr | +0.036 |
Neg logit contributions | |
anna | -0.064 |
ivering | -0.057 |
uster | -0.057 |
annah | -0.056 |
agons | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
da | +0.019 |
pe | +0.015 |
a | +0.014 |
an | +0.014 |
cr | +0.013 |
Neg logit contributions | |
anna | -0.062 |
ivering | -0.057 |
uster | -0.056 |
annah | -0.056 |
agons | -0.056 |
Token | spider |
Token ID | 19230 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
da | +0.041 |
pe | +0.035 |
a | +0.034 |
an | +0.033 |
cr | +0.032 |
Neg logit contributions | |
anna | -0.072 |
annah | -0.064 |
uster | -0.063 |
ivering | -0.063 |
ivery | -0.062 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
da | +0.014 |
pe | +0.011 |
a | +0.011 |
an | +0.010 |
cr | +0.010 |
Neg logit contributions | |
anna | -0.037 |
uster | -0.035 |
annah | -0.034 |
agons | -0.034 |
ittens | -0.034 |
Token | Her |
Token ID | 2332 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
da | +0.012 |
a | +0.011 |
an | +0.010 |
pe | +0.010 |
the | +0.010 |
Neg logit contributions | |
anna | -0.028 |
agons | -0.027 |
ivering | -0.026 |
ivery | -0.026 |
ital | -0.026 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
anna | +0.099 |
ivering | +0.090 |
uster | +0.088 |
ital | +0.088 |
ivery | +0.088 |
Neg logit contributions | |
da | -0.046 |
a | -0.042 |
pe | -0.040 |
an | -0.039 |
cr | -0.038 |
Token | came |
Token ID | 1625 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
da | +0.059 |
an | +0.050 |
Sof | +0.050 |
pe | +0.049 |
a | +0.048 |
Neg logit contributions | |
anna | -0.076 |
ivering | -0.066 |
annah | -0.064 |
uster | -0.063 |
ivery | -0.062 |
Token | over |
Token ID | 625 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
da | +0.045 |
pe | +0.036 |
a | +0.035 |
an | +0.035 |
cr | +0.033 |
Neg logit contributions | |
anna | -0.115 |
ivering | -0.104 |
uster | -0.103 |
annah | -0.103 |
agons | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
da | +0.112 |
Sof | +0.086 |
aw | +0.085 |
pe | +0.083 |
an | +0.079 |
Neg logit contributions | |
anna | -0.231 |
ivering | -0.211 |
annah | -0.210 |
uster | -0.210 |
amas | -0.205 |
Token | said |
Token ID | 531 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
da | +0.040 |
Sof | +0.035 |
aw | +0.034 |
an | +0.032 |
are | +0.031 |
Neg logit contributions | |
anna | -0.072 |
annah | -0.063 |
ivering | -0.061 |
uster | -0.060 |
belt | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
da | +0.019 |
pe | +0.014 |
Sof | +0.014 |
aw | +0.014 |
cr | +0.014 |
Neg logit contributions | |
anna | -0.040 |
annah | -0.035 |
belt | -0.033 |
ivering | -0.033 |
ider | -0.033 |
Token | " |
Token ID | 366 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
da | +0.029 |
a | +0.026 |
pe | +0.024 |
an | +0.024 |
the | +0.021 |
Neg logit contributions | |
anna | -0.101 |
agons | -0.094 |
ital | -0.093 |
ivering | -0.093 |
ivery | -0.092 |
Token | Don |
Token ID | 3987 |
Feature activation | -1.70e-03 |
Pos logit contributions | |
da | +0.042 |
pe | +0.036 |
a | +0.035 |
an | +0.034 |
Sof | +0.033 |
Neg logit contributions | |
anna | -0.084 |
agons | -0.077 |
annah | -0.076 |
ivering | -0.075 |
uster | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +5.37e-03 |
Pos logit contributions | |
da | +0.004 |
pe | +0.003 |
Sof | +0.003 |
cr | +0.002 |
ho | +0.002 |
Neg logit contributions | |
anna | -0.015 |
ivering | -0.014 |
uster | -0.014 |
ivery | -0.014 |
annah | -0.013 |
Token | Her |
Token ID | 2332 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
da | +0.005 |
a | +0.005 |
an | +0.005 |
pe | +0.005 |
Sof | +0.005 |
Neg logit contributions | |
anna | -0.013 |
agons | -0.013 |
uster | -0.013 |
ivering | -0.013 |
ivery | -0.012 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
anna | +0.139 |
uster | +0.124 |
annah | +0.123 |
ivering | +0.121 |
ital | +0.120 |
Neg logit contributions | |
da | -0.070 |
a | -0.062 |
pe | -0.061 |
an | -0.059 |
cr | -0.058 |
Token | came |
Token ID | 1625 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
da | +0.045 |
pe | +0.037 |
an | +0.037 |
a | +0.036 |
Sof | +0.035 |
Neg logit contributions | |
anna | -0.092 |
ivering | -0.083 |
uster | -0.082 |
annah | -0.082 |
agons | -0.081 |
Token | running |
Token ID | 2491 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
da | +0.040 |
pe | +0.034 |
a | +0.034 |
an | +0.032 |
cr | +0.029 |
Neg logit contributions | |
anna | -0.111 |
belt | -0.101 |
annah | -0.101 |
ivering | -0.101 |
agons | -0.101 |
Token | over |
Token ID | 625 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
da | +0.022 |
pe | +0.017 |
Sof | +0.017 |
cr | +0.017 |
aw | +0.016 |
Neg logit contributions | |
anna | -0.042 |
uster | -0.038 |
ivering | -0.038 |
annah | -0.038 |
belt | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
da | +0.100 |
pe | +0.076 |
Sof | +0.074 |
aw | +0.072 |
an | +0.072 |
Neg logit contributions | |
anna | -0.243 |
annah | -0.220 |
uster | -0.220 |
ivering | -0.220 |
ittens | -0.214 |
Token | see |
Token ID | 766 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
da | +0.057 |
pe | +0.047 |
an | +0.046 |
a | +0.046 |
Sof | +0.044 |
Neg logit contributions | |
anna | -0.106 |
ivering | -0.094 |
annah | -0.094 |
uster | -0.094 |
agons | -0.092 |
Token | what |
Token ID | 644 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
da | +0.067 |
Sof | +0.054 |
pe | +0.053 |
aw | +0.049 |
an | +0.049 |
Neg logit contributions | |
anna | -0.149 |
ivering | -0.135 |
annah | -0.133 |
uster | -0.131 |
ivery | -0.130 |
Token | happened |
Token ID | 3022 |
Feature activation | +2.80e-03 |
Pos logit contributions | |
da | +0.083 |
pe | +0.069 |
Sof | +0.068 |
cr | +0.064 |
aw | +0.063 |
Neg logit contributions | |
anna | -0.124 |
ital | -0.109 |
ivering | -0.108 |
ittens | -0.108 |
annah | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
da | +0.003 |
pe | +0.002 |
an | +0.002 |
a | +0.002 |
Sof | +0.002 |
Neg logit contributions | |
anna | -0.007 |
ivering | -0.007 |
annah | -0.007 |
uster | -0.007 |
belt | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
da | +0.002 |
a | +0.002 |
an | +0.002 |
pe | +0.002 |
Sof | +0.002 |
Neg logit contributions | |
anna | -0.003 |
ivering | -0.002 |
uster | -0.002 |
agons | -0.002 |
annah | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
da | +0.009 |
pe | +0.007 |
cr | +0.007 |
aw | +0.006 |
Sof | +0.006 |
Neg logit contributions | |
anna | -0.014 |
ittens | -0.013 |
annah | -0.013 |
agons | -0.013 |
uster | -0.013 |
Token | His |
Token ID | 6653 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
anna | +0.025 |
ivering | +0.022 |
uster | +0.022 |
annah | +0.022 |
agons | +0.022 |
Neg logit contributions | |
da | -0.018 |
pe | -0.016 |
a | -0.015 |
an | -0.015 |
cr | -0.015 |
Token | dad |
Token ID | 9955 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
anna | +0.131 |
ivering | +0.116 |
uster | +0.115 |
annah | +0.115 |
agons | +0.114 |
Neg logit contributions | |
da | -0.079 |
pe | -0.068 |
a | -0.067 |
an | -0.066 |
cr | -0.064 |
Token | came |
Token ID | 1625 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
da | +0.062 |
Sof | +0.053 |
an | +0.051 |
cr | +0.048 |
high | +0.047 |
Neg logit contributions | |
anna | -0.109 |
ivering | -0.099 |
uster | -0.096 |
annah | -0.096 |
belt | -0.093 |
Token | over |
Token ID | 625 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
da | +0.049 |
aw | +0.036 |
Sof | +0.035 |
pe | +0.034 |
cr | +0.034 |
Neg logit contributions | |
anna | -0.121 |
uster | -0.110 |
ivering | -0.109 |
annah | -0.108 |
agons | -0.107 |
Token | and |
Token ID | 290 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
da | +0.099 |
pe | +0.075 |
an | +0.073 |
Sof | +0.072 |
a | +0.069 |
Neg logit contributions | |
anna | -0.248 |
ivering | -0.228 |
uster | -0.226 |
annah | -0.225 |
agons | -0.222 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
da | +0.035 |
Sof | +0.032 |
aw | +0.031 |
cr | +0.031 |
an | +0.029 |
Neg logit contributions | |
anna | -0.052 |
annah | -0.047 |
ivering | -0.045 |
uster | -0.045 |
belt | -0.044 |
Token | what |
Token ID | 644 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
da | +0.048 |
ho | +0.035 |
cr | +0.034 |
Sof | +0.033 |
pe | +0.033 |
Neg logit contributions | |
anna | -0.145 |
uster | -0.139 |
annah | -0.138 |
agons | -0.137 |
ascal | -0.134 |
Token | happened |
Token ID | 3022 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
da | +0.073 |
pe | +0.057 |
Sof | +0.056 |
aw | +0.055 |
ho | +0.052 |
Neg logit contributions | |
anna | -0.108 |
annah | -0.099 |
ital | -0.098 |
agons | -0.097 |
belt | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
da | +0.001 |
pe | +0.001 |
Sof | +0.001 |
an | +0.001 |
cr | +0.001 |
Neg logit contributions | |
anna | -0.004 |
ivering | -0.003 |
annah | -0.003 |
belt | -0.003 |
agons | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
anna | +0.008 |
ivering | +0.007 |
uster | +0.007 |
annah | +0.007 |
ivery | +0.007 |
Neg logit contributions | |
da | -0.003 |
pe | -0.002 |
cr | -0.002 |
Sof | -0.002 |
an | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +7.75e-04 |
Pos logit contributions | |
da | +0.014 |
pe | +0.012 |
an | +0.011 |
cr | +0.011 |
a | +0.011 |
Neg logit contributions | |
anna | -0.024 |
annah | -0.021 |
uster | -0.021 |
amas | -0.021 |
ivering | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
da | +0.001 |
pe | +0.001 |
an | +0.001 |
cr | +0.001 |
a | +0.001 |
Neg logit contributions | |
anna | -0.002 |
annah | -0.002 |
uster | -0.002 |
ivering | -0.002 |
agons | -0.002 |
Token | Mom |
Token ID | 29252 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
anna | +0.030 |
uster | +0.027 |
ivering | +0.027 |
agons | +0.027 |
annah | +0.026 |
Neg logit contributions | |
da | -0.019 |
a | -0.017 |
pe | -0.016 |
an | -0.016 |
cr | -0.015 |
Token | came |
Token ID | 1625 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
da | +0.072 |
Sof | +0.062 |
an | +0.060 |
high | +0.056 |
many | +0.053 |
Neg logit contributions | |
anna | -0.117 |
ivering | -0.107 |
uster | -0.104 |
annah | -0.099 |
amas | -0.099 |
Token | over |
Token ID | 625 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
da | +0.051 |
aw | +0.039 |
cr | +0.039 |
are | +0.039 |
Sof | +0.038 |
Neg logit contributions | |
anna | -0.094 |
uster | -0.084 |
ivering | -0.084 |
annah | -0.081 |
amas | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
da | +0.116 |
pe | +0.088 |
Sof | +0.087 |
aw | +0.086 |
cr | +0.084 |
Neg logit contributions | |
anna | -0.219 |
ivering | -0.202 |
uster | -0.201 |
annah | -0.199 |
ittens | -0.194 |
Token | gazed |
Token ID | 50255 |
Feature activation | -5.74e-04 |
Pos logit contributions | |
da | +0.034 |
aw | +0.031 |
Sof | +0.031 |
are | +0.030 |
an | +0.030 |
Neg logit contributions | |
anna | -0.059 |
annah | -0.051 |
ivering | -0.049 |
belt | -0.048 |
uster | -0.048 |
Token | at |
Token ID | 379 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
anna | +0.001 |
uster | +0.001 |
ivering | +0.001 |
annah | +0.001 |
agons | +0.001 |
Neg logit contributions | |
da | -0.001 |
pe | -0.000 |
cr | -0.000 |
Sof | -0.000 |
an | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
da | +0.028 |
pe | +0.020 |
cr | +0.016 |
cr | +0.016 |
Sof | +0.015 |
Neg logit contributions | |
anna | -0.122 |
annah | -0.113 |
uster | -0.112 |
belt | -0.110 |
ivering | -0.110 |
Token | baby |
Token ID | 5156 |
Feature activation | -5.70e-03 |
Pos logit contributions | |
da | +0.050 |
pe | +0.042 |
a | +0.040 |
an | +0.040 |
cr | +0.038 |
Neg logit contributions | |
anna | -0.108 |
ivering | -0.097 |
uster | -0.096 |
annah | -0.096 |
agons | -0.095 |
Token | the |
Token ID | 262 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
anna | +0.022 |
ivering | +0.021 |
ivery | +0.020 |
uster | +0.020 |
amas | +0.020 |
Neg logit contributions | |
da | -0.002 |
a | -0.002 |
an | -0.001 |
pe | -0.001 |
the | -0.001 |
Token | kids |
Token ID | 3988 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
da | +0.038 |
a | +0.035 |
cr | +0.034 |
pe | +0.033 |
high | +0.032 |
Neg logit contributions | |
anna | -0.054 |
uster | -0.053 |
ivery | -0.048 |
ivering | -0.048 |
ittens | -0.048 |
Token | had |
Token ID | 550 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
da | +0.011 |
pe | +0.010 |
a | +0.010 |
to | +0.009 |
the | +0.009 |
Neg logit contributions | |
anna | -0.029 |
agons | -0.028 |
uster | -0.028 |
ivering | -0.028 |
ivery | -0.028 |
Token | their |
Token ID | 511 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
da | +0.019 |
pe | +0.014 |
a | +0.013 |
an | +0.013 |
cr | +0.012 |
Neg logit contributions | |
anna | -0.065 |
ivering | -0.059 |
uster | -0.059 |
annah | -0.059 |
agons | -0.058 |
Token | t |
Token ID | 256 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
anna | +0.091 |
ivering | +0.088 |
uster | +0.086 |
ivery | +0.085 |
amas | +0.083 |
Neg logit contributions | |
da | -0.067 |
a | -0.061 |
pe | -0.059 |
an | -0.058 |
cr | -0.057 |
Token | amb |
Token ID | 4131 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
anna | +0.102 |
annah | +0.089 |
ivering | +0.087 |
ivery | +0.086 |
uster | +0.084 |
Neg logit contributions | |
da | -0.110 |
pe | -0.098 |
cr | -0.096 |
a | -0.094 |
aw | -0.094 |
Token | our |
Token ID | 454 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
ivering | +0.199 |
ivery | +0.192 |
amas | +0.189 |
lifestyle | +0.185 |
uster | +0.184 |
Neg logit contributions | |
da | -0.214 |
are | -0.207 |
pe | -0.202 |
an | -0.190 |
a | -0.190 |
Token | ines |
Token ID | 1127 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
anna | +0.118 |
ivering | +0.116 |
ivery | +0.115 |
uster | +0.113 |
amas | +0.112 |
Neg logit contributions | |
da | -0.058 |
a | -0.055 |
an | -0.050 |
pe | -0.049 |
to | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
anna | +0.038 |
uster | +0.035 |
ivering | +0.035 |
agons | +0.035 |
ivery | +0.035 |
Neg logit contributions | |
da | -0.008 |
a | -0.007 |
an | -0.006 |
pe | -0.006 |
the | -0.006 |
Token | drums |
Token ID | 24730 |
Feature activation | +2.25e-03 |
Pos logit contributions | |
anna | +0.011 |
ivering | +0.010 |
uster | +0.010 |
ivery | +0.010 |
agons | +0.010 |
Neg logit contributions | |
da | -0.005 |
a | -0.005 |
an | -0.004 |
pe | -0.004 |
the | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
da | +0.002 |
a | +0.001 |
pe | +0.001 |
an | +0.001 |
cr | +0.001 |
Neg logit contributions | |
anna | -0.006 |
ivering | -0.006 |
annah | -0.006 |
uster | -0.006 |
agons | -0.006 |
Token | there |
Token ID | 612 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
anna | +0.016 |
ittens | +0.015 |
annah | +0.014 |
ivering | +0.014 |
ider | +0.014 |
Neg logit contributions | |
da | -0.009 |
aw | -0.007 |
pe | -0.007 |
cr | -0.006 |
l | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
anna | +0.040 |
ivering | +0.036 |
annah | +0.035 |
ivery | +0.035 |
belt | +0.035 |
Neg logit contributions | |
da | -0.020 |
pe | -0.014 |
aw | -0.014 |
cr | -0.014 |
an | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
anna | +0.048 |
ivering | +0.044 |
uster | +0.044 |
annah | +0.044 |
agons | +0.044 |
Neg logit contributions | |
da | -0.004 |
pe | -0.001 |
an | -0.001 |
a | -0.001 |
Sof | -0.000 |
Token | great |
Token ID | 1049 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
da | +0.017 |
pe | +0.015 |
a | +0.015 |
an | +0.014 |
cr | +0.014 |
Neg logit contributions | |
anna | -0.023 |
uster | -0.020 |
annah | -0.020 |
ivering | -0.020 |
agons | -0.020 |
Token | l |
Token ID | 300 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
anna | +0.087 |
ivering | +0.077 |
uster | +0.077 |
annah | +0.077 |
belt | +0.076 |
Neg logit contributions | |
da | -0.057 |
pe | -0.049 |
a | -0.048 |
an | -0.047 |
cr | -0.045 |
Token | oll |
Token ID | 692 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
anna | +0.057 |
ivering | +0.049 |
annah | +0.048 |
agons | +0.048 |
uster | +0.048 |
Neg logit contributions | |
da | -0.062 |
an | -0.056 |
pe | -0.056 |
a | -0.055 |
cr | -0.054 |
Token | ipop |
Token ID | 42800 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
anna | +0.206 |
uster | +0.195 |
ivery | +0.191 |
ivering | +0.191 |
amas | +0.186 |
Neg logit contributions | |
da | -0.217 |
pe | -0.196 |
cr | -0.191 |
a | -0.186 |
an | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
anna | +0.091 |
uster | +0.083 |
ivering | +0.083 |
annah | +0.082 |
agons | +0.082 |
Neg logit contributions | |
da | -0.028 |
pe | -0.021 |
a | -0.021 |
an | -0.020 |
cr | -0.019 |
Token | It |
Token ID | 632 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
anna | +0.087 |
ivering | +0.079 |
agons | +0.078 |
uster | +0.077 |
ivery | +0.077 |
Neg logit contributions | |
da | -0.046 |
a | -0.042 |
an | -0.041 |
pe | -0.040 |
Sof | -0.039 |
Token | was |
Token ID | 373 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
anna | +0.030 |
annah | +0.026 |
ivering | +0.026 |
belt | +0.026 |
ittens | +0.026 |
Neg logit contributions | |
da | -0.011 |
an | -0.008 |
Sof | -0.008 |
pe | -0.008 |
aw | -0.008 |
Token | pink |
Token ID | 11398 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
anna | +0.015 |
ivering | +0.013 |
annah | +0.013 |
uster | +0.013 |
agons | +0.013 |
Neg logit contributions | |
da | -0.003 |
pe | -0.002 |
an | -0.002 |
a | -0.002 |
Sof | -0.002 |
Token | about |
Token ID | 546 |
Feature activation | -7.32e-03 |
Pos logit contributions | |
da | +0.026 |
pe | +0.022 |
Sof | +0.021 |
an | +0.019 |
ho | +0.019 |
Neg logit contributions | |
anna | -0.051 |
annah | -0.045 |
belt | -0.045 |
uster | -0.045 |
ivering | -0.044 |
Token | you |
Token ID | 345 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
anna | +0.019 |
ivery | +0.019 |
ivering | +0.019 |
uster | +0.019 |
agons | +0.018 |
Neg logit contributions | |
da | -0.007 |
a | -0.007 |
an | -0.006 |
pe | -0.006 |
the | -0.006 |
Token | wear |
Token ID | 5806 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
anna | +0.063 |
agons | +0.057 |
uster | +0.057 |
belt | +0.056 |
amas | +0.055 |
Neg logit contributions | |
a | -0.029 |
da | -0.029 |
an | -0.028 |
pe | -0.027 |
the | -0.025 |
Token | this |
Token ID | 428 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
anna | +0.141 |
ivering | +0.134 |
ivery | +0.133 |
uster | +0.131 |
agons | +0.129 |
Neg logit contributions | |
a | -0.038 |
da | -0.038 |
an | -0.035 |
the | -0.033 |
pe | -0.030 |
Token | l |
Token ID | 300 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
anna | +0.078 |
uster | +0.071 |
ivering | +0.071 |
annah | +0.070 |
agons | +0.070 |
Neg logit contributions | |
da | -0.036 |
pe | -0.030 |
a | -0.029 |
an | -0.028 |
cr | -0.027 |
Token | oll |
Token ID | 692 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
anna | +0.068 |
ivery | +0.062 |
ivering | +0.061 |
uster | +0.058 |
amas | +0.058 |
Neg logit contributions | |
da | -0.075 |
pe | -0.067 |
a | -0.066 |
an | -0.065 |
Sof | -0.065 |
Token | ipop |
Token ID | 42800 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
anna | +0.213 |
ivery | +0.207 |
ivering | +0.206 |
uster | +0.198 |
urance | +0.191 |
Neg logit contributions | |
da | -0.202 |
pe | -0.190 |
cr | -0.185 |
a | -0.179 |
an | -0.171 |
Token | instead |
Token ID | 2427 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
anna | +0.104 |
uster | +0.095 |
agons | +0.093 |
ivering | +0.091 |
ivery | +0.090 |
Neg logit contributions | |
da | -0.049 |
a | -0.049 |
an | -0.046 |
to | -0.044 |
pe | -0.043 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
anna | +0.028 |
uster | +0.028 |
agons | +0.027 |
ascal | +0.026 |
immers | +0.026 |
Neg logit contributions | |
a | -0.012 |
the | -0.011 |
to | -0.011 |
! | -0.011 |
an | -0.010 |
Token | Jack |
Token ID | 3619 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
a | +0.003 |
an | +0.003 |
the | +0.002 |
da | +0.002 |
pe | +0.002 |
Neg logit contributions | |
anna | -0.006 |
belt | -0.006 |
agons | -0.006 |
uster | -0.006 |
ivering | -0.006 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
da | +0.022 |
pe | +0.019 |
a | +0.018 |
an | +0.018 |
cr | +0.017 |
Neg logit contributions | |
anna | -0.052 |
uster | -0.048 |
agons | -0.047 |
ivering | -0.047 |
annah | -0.047 |
Token | Can |
Token ID | 6090 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
da | +0.037 |
pe | +0.032 |
an | +0.031 |
a | +0.031 |
Sof | +0.030 |
Neg logit contributions | |
anna | -0.055 |
ivering | -0.049 |
uster | -0.048 |
annah | -0.048 |
agons | -0.048 |
Token | we |
Token ID | 356 |
Feature activation | -9.50e-04 |
Pos logit contributions | |
anna | +0.010 |
uster | +0.009 |
ivering | +0.009 |
agons | +0.009 |
ivery | +0.009 |
Neg logit contributions | |
da | -0.006 |
a | -0.006 |
pe | -0.006 |
an | -0.006 |
cr | -0.005 |
Token | have |
Token ID | 423 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
anna | +0.002 |
uster | +0.002 |
ivering | +0.002 |
belt | +0.002 |
annah | +0.002 |
Neg logit contributions | |
da | -0.001 |
pe | -0.001 |
a | -0.001 |
an | -0.001 |
cr | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -6.54e-03 |
Pos logit contributions | |
da | +0.023 |
ho | +0.022 |
Sof | +0.019 |
aw | +0.018 |
pe | +0.018 |
Neg logit contributions | |
anna | -0.060 |
ittens | -0.053 |
annah | -0.053 |
ital | -0.051 |
agons | -0.051 |
Token | l |
Token ID | 300 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
anna | +0.014 |
ivering | +0.013 |
uster | +0.013 |
annah | +0.013 |
agons | +0.013 |
Neg logit contributions | |
da | -0.009 |
pe | -0.008 |
an | -0.007 |
a | -0.007 |
Sof | -0.007 |
Token | oll |
Token ID | 692 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
anna | +0.047 |
ivering | +0.039 |
uster | +0.039 |
annah | +0.039 |
agons | +0.038 |
Neg logit contributions | |
da | -0.063 |
pe | -0.057 |
a | -0.056 |
an | -0.056 |
Sof | -0.054 |
Token | ipop |
Token ID | 42800 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
anna | +0.198 |
ivering | +0.183 |
ivery | +0.179 |
uster | +0.175 |
amas | +0.169 |
Neg logit contributions | |
da | -0.212 |
pe | -0.196 |
cr | -0.189 |
a | -0.188 |
an | -0.182 |
Token | , |
Token ID | 11 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
anna | +0.096 |
uster | +0.086 |
ivering | +0.086 |
annah | +0.085 |
agons | +0.085 |
Neg logit contributions | |
da | -0.051 |
pe | -0.043 |
a | -0.043 |
an | -0.042 |
cr | -0.040 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
anna | +0.005 |
ivering | +0.005 |
uster | +0.005 |
annah | +0.005 |
agons | +0.005 |
Neg logit contributions | |
da | -0.004 |
pe | -0.003 |
a | -0.003 |
an | -0.003 |
cr | -0.003 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
da | +0.019 |
a | +0.018 |
pe | +0.018 |
to | +0.017 |
the | +0.017 |
Neg logit contributions | |
anna | -0.035 |
uster | -0.035 |
agons | -0.034 |
ivery | -0.034 |
belt | -0.033 |
Token | Ben |
Token ID | 3932 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
da | +0.014 |
a | +0.013 |
an | +0.012 |
pe | +0.012 |
the | +0.012 |
Neg logit contributions | |
anna | -0.035 |
ivering | -0.033 |
agons | -0.033 |
uster | -0.033 |
ivery | -0.033 |
Token | j |
Token ID | 474 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
da | +0.023 |
pe | +0.020 |
an | +0.020 |
a | +0.020 |
Sof | +0.019 |
Neg logit contributions | |
anna | -0.028 |
ivering | -0.024 |
uster | -0.024 |
annah | -0.024 |
agons | -0.024 |
Token | olly |
Token ID | 5098 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
anna | +0.104 |
uster | +0.086 |
amas | +0.086 |
belt | +0.085 |
ivering | +0.085 |
Neg logit contributions | |
da | -0.154 |
pe | -0.138 |
high | -0.134 |
a | -0.134 |
Sof | -0.133 |
Token | deer |
Token ID | 20096 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
anna | +0.062 |
ivery | +0.057 |
uster | +0.056 |
ivering | +0.056 |
agons | +0.056 |
Neg logit contributions | |
da | -0.045 |
pe | -0.038 |
a | -0.037 |
cr | -0.035 |
an | -0.035 |
Token | named |
Token ID | 3706 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
anna | +0.053 |
ivering | +0.047 |
annah | +0.045 |
agons | +0.045 |
uster | +0.045 |
Neg logit contributions | |
da | -0.037 |
pe | -0.031 |
an | -0.031 |
Sof | -0.030 |
a | -0.030 |
Token | B |
Token ID | 347 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
anna | +0.072 |
ivering | +0.064 |
uster | +0.064 |
annah | +0.063 |
agons | +0.063 |
Neg logit contributions | |
da | -0.044 |
pe | -0.038 |
a | -0.037 |
an | -0.037 |
Sof | -0.036 |
Token | amb |
Token ID | 4131 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
anna | +0.073 |
ivering | +0.064 |
belt | +0.062 |
ivery | +0.062 |
ital | +0.062 |
Neg logit contributions | |
da | -0.093 |
pe | -0.083 |
a | -0.083 |
an | -0.081 |
Sof | -0.081 |
Token | i |
Token ID | 72 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
ivering | +0.216 |
amas | +0.214 |
ivery | +0.211 |
anna | +0.211 |
uster | +0.210 |
Neg logit contributions | |
da | -0.177 |
pe | -0.168 |
an | -0.150 |
a | -0.149 |
Sof | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
anna | +0.065 |
agons | +0.057 |
ivering | +0.056 |
ittens | +0.056 |
annah | +0.056 |
Neg logit contributions | |
da | -0.027 |
Sof | -0.022 |
pe | -0.021 |
an | -0.021 |
cr | -0.020 |
Token | B |
Token ID | 347 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
anna | +0.076 |
ivering | +0.067 |
ital | +0.067 |
annah | +0.067 |
belt | +0.065 |
Neg logit contributions | |
da | -0.041 |
a | -0.038 |
an | -0.037 |
pe | -0.036 |
the | -0.034 |
Token | amb |
Token ID | 4131 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
anna | +0.074 |
ivering | +0.067 |
belt | +0.066 |
ivery | +0.065 |
ital | +0.065 |
Neg logit contributions | |
da | -0.101 |
pe | -0.091 |
a | -0.088 |
Sof | -0.088 |
an | -0.087 |
Token | i |
Token ID | 72 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
ivering | +0.224 |
amas | +0.223 |
ivery | +0.223 |
uster | +0.215 |
ital | +0.210 |
Neg logit contributions | |
da | -0.159 |
pe | -0.155 |
ho | -0.134 |
Sof | -0.131 |
an | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
da | +0.000 |
an | +0.000 |
pe | +0.000 |
a | +0.000 |
Sof | +0.000 |
Neg logit contributions | |
anna | -0.001 |
ivering | -0.001 |
agons | -0.001 |
annah | -0.001 |
uster | -0.001 |
Token | green |
Token ID | 4077 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
anna | +0.122 |
uster | +0.111 |
ivery | +0.110 |
annah | +0.110 |
ivering | +0.110 |
Neg logit contributions | |
da | -0.037 |
pe | -0.030 |
a | -0.029 |
high | -0.027 |
an | -0.026 |
Token | field |
Token ID | 2214 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
anna | +0.043 |
ivering | +0.038 |
uster | +0.038 |
annah | +0.038 |
agons | +0.037 |
Neg logit contributions | |
da | -0.033 |
pe | -0.029 |
an | -0.028 |
a | -0.028 |
Sof | -0.027 |
Token | with |
Token ID | 351 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
anna | +0.029 |
ivering | +0.027 |
belt | +0.026 |
annah | +0.026 |
ider | +0.026 |
Neg logit contributions | |
da | -0.015 |
pe | -0.012 |
Sof | -0.012 |
an | -0.011 |
cr | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
da | +0.017 |
ho | +0.016 |
Sof | +0.014 |
aw | +0.013 |
pe | +0.013 |
Neg logit contributions | |
anna | -0.045 |
agons | -0.045 |
ittens | -0.043 |
uster | -0.040 |
lifestyle | -0.040 |
Token | z |
Token ID | 1976 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
anna | +0.093 |
agons | +0.085 |
ittens | +0.083 |
belt | +0.079 |
ivering | +0.079 |
Neg logit contributions | |
da | -0.098 |
pe | -0.087 |
an | -0.086 |
Sof | -0.086 |
aw | -0.085 |
Token | ebra |
Token ID | 37052 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
anna | +0.161 |
ivering | +0.131 |
annah | +0.130 |
uster | +0.130 |
ivery | +0.128 |
Neg logit contributions | |
da | -0.255 |
pe | -0.231 |
a | -0.225 |
an | -0.224 |
cr | -0.223 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
anna | +0.062 |
uster | +0.057 |
annah | +0.056 |
ivering | +0.056 |
ivery | +0.056 |
Neg logit contributions | |
da | -0.028 |
a | -0.023 |
pe | -0.023 |
an | -0.022 |
cr | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
anna | +0.040 |
agons | +0.037 |
ivering | +0.037 |
uster | +0.036 |
annah | +0.036 |
Neg logit contributions | |
da | -0.014 |
pe | -0.011 |
Sof | -0.010 |
an | -0.010 |
cr | -0.010 |
Token | One |
Token ID | 1881 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
anna | +0.041 |
ivering | +0.037 |
annah | +0.037 |
uster | +0.036 |
ivery | +0.036 |
Neg logit contributions | |
da | -0.028 |
a | -0.024 |
pe | -0.024 |
an | -0.024 |
Sof | -0.023 |
Token | day |
Token ID | 1110 |
Feature activation | -7.03e-03 |
Pos logit contributions | |
anna | +0.054 |
ivering | +0.043 |
agons | +0.042 |
ittens | +0.041 |
uster | +0.041 |
Neg logit contributions | |
da | -0.090 |
pe | -0.082 |
an | -0.081 |
Sof | -0.080 |
cr | -0.080 |
Token | had |
Token ID | 550 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
uster | +0.055 |
anna | +0.055 |
agons | +0.054 |
amas | +0.053 |
ivering | +0.053 |
Neg logit contributions | |
da | -0.020 |
pe | -0.020 |
a | -0.019 |
an | -0.017 |
cr | -0.016 |
Token | been |
Token ID | 587 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
da | +0.037 |
pe | +0.030 |
Sof | +0.029 |
a | +0.029 |
an | +0.028 |
Neg logit contributions | |
anna | -0.075 |
ivering | -0.066 |
annah | -0.066 |
uster | -0.066 |
belt | -0.065 |
Token | collecting |
Token ID | 13157 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
anna | +0.083 |
uster | +0.077 |
agons | +0.077 |
belt | +0.075 |
ittens | +0.075 |
Neg logit contributions | |
a | -0.046 |
da | -0.046 |
an | -0.045 |
pe | -0.044 |
the | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +4.45e-03 |
Pos logit contributions | |
anna | +0.078 |
ivering | +0.070 |
uster | +0.069 |
annah | +0.069 |
agons | +0.069 |
Neg logit contributions | |
da | -0.039 |
pe | -0.033 |
an | -0.032 |
a | -0.032 |
Sof | -0.031 |
Token | best |
Token ID | 1266 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
da | +0.006 |
pe | +0.005 |
a | +0.005 |
an | +0.005 |
cr | +0.004 |
Neg logit contributions | |
anna | -0.011 |
annah | -0.010 |
ivering | -0.010 |
uster | -0.009 |
ivery | -0.009 |
Token | tw |
Token ID | 665 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
anna | +0.128 |
ivering | +0.116 |
annah | +0.116 |
ivery | +0.115 |
uster | +0.113 |
Neg logit contributions | |
da | -0.078 |
pe | -0.069 |
a | -0.066 |
cr | -0.064 |
an | -0.064 |
Token | igs |
Token ID | 9235 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
anna | +0.152 |
uster | +0.132 |
ivering | +0.131 |
ivery | +0.130 |
amas | +0.124 |
Neg logit contributions | |
da | -0.254 |
pe | -0.232 |
an | -0.220 |
a | -0.219 |
cr | -0.216 |
Token | and |
Token ID | 290 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
anna | +0.141 |
ivering | +0.130 |
uster | +0.129 |
agons | +0.128 |
annah | +0.128 |
Neg logit contributions | |
da | -0.039 |
pe | -0.030 |
a | -0.029 |
an | -0.029 |
cr | -0.026 |
Token | leaves |
Token ID | 5667 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
anna | +0.048 |
ivering | +0.044 |
uster | +0.044 |
ivery | +0.043 |
annah | +0.043 |
Neg logit contributions | |
da | -0.020 |
pe | -0.017 |
a | -0.016 |
an | -0.016 |
cr | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
anna | +0.059 |
ivering | +0.054 |
uster | +0.054 |
annah | +0.054 |
agons | +0.053 |
Neg logit contributions | |
da | -0.019 |
pe | -0.014 |
an | -0.013 |
a | -0.013 |
Sof | -0.013 |
Token | make |
Token ID | 787 |
Feature activation | +1.65e-03 |
Pos logit contributions | |
anna | +0.071 |
ivering | +0.064 |
uster | +0.064 |
annah | +0.063 |
agons | +0.063 |
Neg logit contributions | |
da | -0.034 |
a | -0.029 |
pe | -0.029 |
an | -0.028 |
the | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
anna | +0.071 |
ivering | +0.068 |
ivery | +0.067 |
ittens | +0.065 |
ascal | +0.064 |
Neg logit contributions | |
a | -0.016 |
da | -0.015 |
an | -0.014 |
to | -0.014 |
the | -0.013 |
Token | be |
Token ID | 307 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
anna | +0.101 |
ivering | +0.089 |
uster | +0.088 |
ascal | +0.087 |
annah | +0.086 |
Neg logit contributions | |
a | -0.060 |
an | -0.058 |
da | -0.057 |
pe | -0.056 |
the | -0.056 |
Token | restored |
Token ID | 15032 |
Feature activation | -7.88e-03 |
Pos logit contributions | |
anna | +0.066 |
uster | +0.062 |
ivering | +0.061 |
annah | +0.060 |
ittens | +0.060 |
Neg logit contributions | |
a | -0.030 |
an | -0.029 |
da | -0.026 |
the | -0.025 |
pe | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
anna | +0.020 |
ivering | +0.019 |
ivery | +0.019 |
ittens | +0.019 |
agons | +0.019 |
Neg logit contributions | |
a | -0.007 |
da | -0.007 |
an | -0.007 |
to | -0.007 |
the | -0.006 |
Token | its |
Token ID | 663 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
anna | +0.069 |
uster | +0.065 |
ivering | +0.065 |
ittens | +0.063 |
agons | +0.062 |
Neg logit contributions | |
a | -0.027 |
an | -0.025 |
da | -0.025 |
the | -0.024 |
pe | -0.023 |
Token | former |
Token ID | 1966 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
anna | +0.048 |
uster | +0.043 |
ivering | +0.042 |
annah | +0.041 |
ittens | +0.041 |
Neg logit contributions | |
da | -0.047 |
a | -0.043 |
pe | -0.043 |
an | -0.043 |
cr | -0.041 |
Token | glory |
Token ID | 13476 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
anna | +0.164 |
uster | +0.158 |
ivering | +0.149 |
ivery | +0.147 |
ancer | +0.142 |
Neg logit contributions | |
da | -0.229 |
pe | -0.213 |
an | -0.207 |
a | -0.205 |
cr | -0.203 |
Token | ." |
Token ID | 526 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
anna | +0.080 |
ivering | +0.077 |
ivery | +0.077 |
uster | +0.075 |
agons | +0.074 |
Neg logit contributions | |
a | -0.031 |
da | -0.031 |
an | -0.029 |
the | -0.028 |
to | -0.027 |
Token | |
Token ID | 220 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
da | +0.025 |
pe | +0.021 |
a | +0.020 |
an | +0.020 |
cr | +0.019 |
Neg logit contributions | |
anna | -0.060 |
ivering | -0.054 |
uster | -0.054 |
annah | -0.054 |
agons | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
da | +0.019 |
a | +0.015 |
pe | +0.015 |
an | +0.015 |
Sof | +0.013 |
Neg logit contributions | |
anna | -0.064 |
ivering | -0.059 |
uster | -0.058 |
agons | -0.058 |
belt | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
da | +0.012 |
pe | +0.009 |
an | +0.009 |
cr | +0.009 |
a | +0.009 |
Neg logit contributions | |
anna | -0.027 |
annah | -0.024 |
ivering | -0.024 |
uster | -0.024 |
ittens | -0.023 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
anna | +0.084 |
ivering | +0.073 |
uster | +0.072 |
annah | +0.072 |
agons | +0.071 |
Neg logit contributions | |
da | -0.078 |
pe | -0.069 |
a | -0.068 |
an | -0.068 |
cr | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
anna | +0.026 |
ivering | +0.022 |
over | +0.022 |
belt | +0.021 |
uster | +0.021 |
Neg logit contributions | |
da | -0.017 |
pe | -0.014 |
Sof | -0.014 |
cr | -0.013 |
ho | -0.013 |
Token | shared |
Token ID | 4888 |
Feature activation | -3.81e-03 |
Pos logit contributions | |
anna | +0.045 |
ivering | +0.040 |
uster | +0.040 |
annah | +0.040 |
agons | +0.039 |
Neg logit contributions | |
da | -0.029 |
pe | -0.025 |
a | -0.025 |
an | -0.025 |
Sof | -0.024 |
Token | their |
Token ID | 511 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
anna | +0.008 |
ittens | +0.007 |
lifestyle | +0.007 |
annah | +0.007 |
agons | +0.007 |
Neg logit contributions | |
ho | -0.004 |
hex | -0.003 |
da | -0.003 |
cr | -0.003 |
gl | -0.003 |
Token | l |
Token ID | 300 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
anna | +0.151 |
ivering | +0.135 |
annah | +0.135 |
uster | +0.134 |
agons | +0.134 |
Neg logit contributions | |
da | -0.074 |
pe | -0.062 |
an | -0.061 |
a | -0.060 |
Sof | -0.057 |
Token | oll |
Token ID | 692 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
anna | +0.071 |
ivering | +0.059 |
uster | +0.059 |
annah | +0.058 |
agons | +0.057 |
Neg logit contributions | |
da | -0.097 |
pe | -0.088 |
a | -0.087 |
an | -0.086 |
Sof | -0.084 |
Token | ip |
Token ID | 541 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
anna | +0.179 |
ivering | +0.154 |
uster | +0.152 |
ivery | +0.149 |
annah | +0.148 |
Neg logit contributions | |
da | -0.228 |
pe | -0.206 |
a | -0.201 |
an | -0.200 |
cr | -0.198 |
Token | ops |
Token ID | 2840 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
anna | +0.124 |
annah | +0.103 |
ivering | +0.102 |
agons | +0.102 |
ittens | +0.100 |
Neg logit contributions | |
da | -0.182 |
pe | -0.166 |
an | -0.166 |
a | -0.164 |
Sof | -0.160 |
Token | every |
Token ID | 790 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
anna | +0.065 |
annah | +0.059 |
ivering | +0.058 |
ittens | +0.057 |
agons | +0.057 |
Neg logit contributions | |
da | -0.029 |
pe | -0.024 |
an | -0.024 |
Sof | -0.022 |
a | -0.022 |
Token | time |
Token ID | 640 |
Feature activation | +1.77e-03 |
Pos logit contributions | |
anna | +0.092 |
agons | +0.087 |
ivery | +0.086 |
uster | +0.086 |
amas | +0.086 |
Neg logit contributions | |
da | -0.096 |
a | -0.089 |
pe | -0.089 |
an | -0.083 |
cr | -0.082 |
Token | they |
Token ID | 484 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
da | +0.002 |
a | +0.001 |
pe | +0.001 |
an | +0.001 |
cr | +0.001 |
Neg logit contributions | |
anna | -0.005 |
ivering | -0.004 |
uster | -0.004 |
ivery | -0.004 |
agons | -0.004 |
Token | songs |
Token ID | 7259 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
anna | +0.056 |
amas | +0.048 |
uster | +0.048 |
agons | +0.047 |
ivering | +0.046 |
Neg logit contributions | |
da | -0.040 |
Sof | -0.036 |
pe | -0.035 |
ho | -0.035 |
cr | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -4.72e-03 |
Pos logit contributions | |
anna | +0.035 |
uster | +0.031 |
ivering | +0.031 |
annah | +0.031 |
belt | +0.030 |
Neg logit contributions | |
da | -0.015 |
pe | -0.012 |
Sof | -0.011 |
an | -0.011 |
cr | -0.010 |
Token | shaking |
Token ID | 17275 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
anna | +0.009 |
ivering | +0.008 |
annah | +0.008 |
uster | +0.008 |
agons | +0.008 |
Neg logit contributions | |
da | -0.008 |
pe | -0.007 |
an | -0.006 |
a | -0.006 |
Sof | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
da | +0.003 |
Sof | +0.002 |
pe | +0.002 |
ho | +0.002 |
cr | +0.002 |
Neg logit contributions | |
anna | -0.007 |
ivering | -0.006 |
agons | -0.006 |
uster | -0.006 |
amas | -0.006 |
Token | t |
Token ID | 256 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
anna | +0.082 |
ivering | +0.072 |
uster | +0.072 |
annah | +0.072 |
ivery | +0.071 |
Neg logit contributions | |
da | -0.078 |
pe | -0.071 |
a | -0.070 |
an | -0.068 |
cr | -0.067 |
Token | amb |
Token ID | 4131 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
anna | +0.079 |
ivering | +0.065 |
annah | +0.065 |
uster | +0.065 |
agons | +0.064 |
Neg logit contributions | |
da | -0.118 |
pe | -0.108 |
a | -0.106 |
an | -0.106 |
cr | -0.103 |
Token | our |
Token ID | 454 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
ivering | +0.157 |
uster | +0.157 |
ivery | +0.151 |
anna | +0.148 |
ittens | +0.146 |
Neg logit contributions | |
da | -0.216 |
pe | -0.208 |
are | -0.205 |
aw | -0.199 |
an | -0.199 |
Token | ine |
Token ID | 500 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
anna | +0.079 |
ivering | +0.074 |
uster | +0.073 |
annah | +0.073 |
agons | +0.073 |
Neg logit contributions | |
da | -0.026 |
a | -0.023 |
pe | -0.021 |
an | -0.021 |
cr | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
anna | +0.064 |
uster | +0.060 |
ivering | +0.060 |
ivery | +0.059 |
annah | +0.059 |
Neg logit contributions | |
da | -0.014 |
a | -0.011 |
pe | -0.011 |
an | -0.009 |
cr | -0.009 |
Token | Whenever |
Token ID | 21326 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
anna | +0.028 |
ivering | +0.027 |
agons | +0.026 |
uster | +0.026 |
ivery | +0.026 |
Neg logit contributions | |
da | -0.015 |
a | -0.013 |
an | -0.013 |
pe | -0.012 |
Sof | -0.012 |
Token | she |
Token ID | 673 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
anna | +0.026 |
annah | +0.023 |
ivering | +0.023 |
belt | +0.023 |
ital | +0.023 |
Neg logit contributions | |
da | -0.012 |
pe | -0.010 |
an | -0.009 |
cr | -0.009 |
a | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
anna | +0.111 |
uster | +0.103 |
agons | +0.102 |
annah | +0.101 |
ivery | +0.100 |
Neg logit contributions | |
da | -0.051 |
pe | -0.042 |
a | -0.042 |
an | -0.040 |
cr | -0.038 |
Token | It |
Token ID | 632 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
anna | +0.075 |
ivering | +0.068 |
uster | +0.067 |
annah | +0.066 |
agons | +0.066 |
Neg logit contributions | |
da | -0.041 |
a | -0.036 |
an | -0.035 |
pe | -0.035 |
Sof | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
anna | +0.041 |
ital | +0.036 |
ivering | +0.035 |
belt | +0.035 |
annah | +0.035 |
Neg logit contributions | |
da | -0.021 |
Sof | -0.017 |
aw | -0.017 |
eleven | -0.016 |
an | -0.016 |
Token | an |
Token ID | 281 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
anna | +0.006 |
ivering | +0.005 |
belt | +0.005 |
uster | +0.005 |
annah | +0.005 |
Neg logit contributions | |
da | -0.001 |
pe | -0.001 |
Sof | -0.001 |
aw | -0.001 |
cr | -0.001 |
Token | amazing |
Token ID | 4998 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
da | +0.017 |
pe | +0.015 |
a | +0.015 |
an | +0.015 |
cr | +0.014 |
Neg logit contributions | |
anna | -0.026 |
ivering | -0.023 |
uster | -0.023 |
annah | -0.023 |
agons | -0.023 |
Token | tw |
Token ID | 665 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
anna | +0.120 |
ivering | +0.107 |
annah | +0.106 |
uster | +0.105 |
belt | +0.105 |
Neg logit contributions | |
da | -0.058 |
an | -0.049 |
Sof | -0.047 |
a | -0.047 |
pe | -0.046 |
Token | ig |
Token ID | 328 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
anna | +0.168 |
uster | +0.143 |
ivering | +0.142 |
annah | +0.139 |
ivery | +0.138 |
Neg logit contributions | |
da | -0.237 |
pe | -0.215 |
a | -0.208 |
an | -0.207 |
cr | -0.203 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
anna | +0.205 |
uster | +0.195 |
ivering | +0.192 |
ivery | +0.191 |
agons | +0.191 |
Neg logit contributions | |
da | -0.050 |
a | -0.037 |
pe | -0.036 |
an | -0.033 |
cr | -0.031 |
Token | The |
Token ID | 383 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
anna | +0.047 |
ivering | +0.043 |
uster | +0.042 |
ivery | +0.042 |
annah | +0.042 |
Neg logit contributions | |
da | -0.023 |
a | -0.022 |
an | -0.021 |
Sof | -0.020 |
pe | -0.020 |
Token | tw |
Token ID | 665 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
anna | +0.039 |
ivering | +0.035 |
uster | +0.035 |
annah | +0.035 |
agons | +0.035 |
Neg logit contributions | |
da | -0.017 |
an | -0.014 |
pe | -0.014 |
Sof | -0.013 |
a | -0.013 |
Token | ig |
Token ID | 328 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
anna | +0.161 |
ivering | +0.142 |
uster | +0.141 |
ivery | +0.140 |
amas | +0.137 |
Neg logit contributions | |
da | -0.217 |
pe | -0.196 |
a | -0.186 |
an | -0.184 |
Sof | -0.181 |
Token | it |
Token ID | 340 |
Feature activation | +7.76e-03 |
Pos logit contributions | |
anna | +0.011 |
ivering | +0.010 |
ivery | +0.010 |
uster | +0.010 |
annah | +0.010 |
Neg logit contributions | |
da | -0.003 |
a | -0.003 |
an | -0.003 |
the | -0.003 |
pe | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
da | +0.007 |
pe | +0.006 |
an | +0.006 |
a | +0.005 |
Sof | +0.005 |
Neg logit contributions | |
anna | -0.020 |
ivering | -0.018 |
annah | -0.018 |
uster | -0.018 |
belt | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
da | +0.013 |
a | +0.010 |
pe | +0.010 |
an | +0.010 |
cr | +0.008 |
Neg logit contributions | |
anna | -0.049 |
ivering | -0.044 |
uster | -0.044 |
annah | -0.044 |
agons | -0.044 |
Token | biggest |
Token ID | 4094 |
Feature activation | -1.56e-04 |
Pos logit contributions | |
da | +0.037 |
pe | +0.032 |
an | +0.031 |
a | +0.031 |
Sof | +0.030 |
Neg logit contributions | |
anna | -0.062 |
ivering | -0.055 |
uster | -0.055 |
annah | -0.055 |
agons | -0.055 |
Token | l |
Token ID | 300 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
anna | +0.000 |
ivering | +0.000 |
annah | +0.000 |
uster | +0.000 |
agons | +0.000 |
Neg logit contributions | |
da | -0.000 |
pe | -0.000 |
an | -0.000 |
a | -0.000 |
Sof | -0.000 |
Token | oll |
Token ID | 692 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
anna | +0.045 |
ivering | +0.039 |
ivery | +0.039 |
uster | +0.038 |
agons | +0.038 |
Neg logit contributions | |
da | -0.055 |
pe | -0.050 |
a | -0.049 |
an | -0.048 |
Sof | -0.048 |
Token | ipop |
Token ID | 42800 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
anna | +0.203 |
ivering | +0.199 |
ivery | +0.199 |
uster | +0.189 |
urance | +0.189 |
Neg logit contributions | |
da | -0.194 |
pe | -0.184 |
cr | -0.172 |
a | -0.170 |
ho | -0.159 |
Token | Peter |
Token ID | 5613 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
anna | +0.095 |
ivering | +0.085 |
annah | +0.085 |
uster | +0.085 |
belt | +0.084 |
Neg logit contributions | |
da | -0.043 |
pe | -0.036 |
an | -0.034 |
a | -0.034 |
Sof | -0.033 |
Token | had |
Token ID | 550 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
ivery | +0.117 |
anna | +0.117 |
ivering | +0.116 |
uster | +0.113 |
agons | +0.113 |
Neg logit contributions | |
da | -0.051 |
a | -0.046 |
pe | -0.044 |
an | -0.041 |
cr | -0.040 |
Token | ever |
Token ID | 1683 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
da | +0.002 |
pe | +0.002 |
a | +0.002 |
an | +0.002 |
cr | +0.002 |
Neg logit contributions | |
anna | -0.005 |
ivering | -0.004 |
uster | -0.004 |
annah | -0.004 |
agons | -0.004 |
Token | seen |
Token ID | 1775 |
Feature activation | +3.29e-03 |
Pos logit contributions | |
anna | +0.043 |
ivering | +0.038 |
uster | +0.038 |
annah | +0.038 |
agons | +0.038 |
Neg logit contributions | |
da | -0.023 |
pe | -0.020 |
a | -0.019 |
an | -0.019 |
cr | -0.018 |
Token | treasure |
Token ID | 14068 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
anna | +0.100 |
ivery | +0.089 |
ivering | +0.089 |
uster | +0.087 |
annah | +0.086 |
Neg logit contributions | |
da | -0.062 |
pe | -0.055 |
a | -0.054 |
cr | -0.052 |
an | -0.052 |
Token | - |
Token ID | 532 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
anna | +0.142 |
ivering | +0.128 |
annah | +0.128 |
uster | +0.128 |
agons | +0.127 |
Neg logit contributions | |
da | -0.052 |
pe | -0.041 |
an | -0.040 |
a | -0.039 |
Sof | -0.037 |
Token | lots |
Token ID | 6041 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
anna | +0.013 |
ivering | +0.011 |
annah | +0.011 |
uster | +0.011 |
agons | +0.011 |
Neg logit contributions | |
da | -0.004 |
pe | -0.003 |
a | -0.003 |
an | -0.003 |
cr | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
da | +0.014 |
pe | +0.012 |
a | +0.012 |
an | +0.011 |
cr | +0.011 |
Neg logit contributions | |
anna | -0.032 |
ivering | -0.029 |
uster | -0.029 |
annah | -0.029 |
agons | -0.029 |
Token | l |
Token ID | 300 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
anna | +0.082 |
ivering | +0.074 |
uster | +0.074 |
annah | +0.073 |
ivery | +0.073 |
Neg logit contributions | |
da | -0.040 |
pe | -0.034 |
a | -0.033 |
an | -0.033 |
cr | -0.031 |
Token | oll |
Token ID | 692 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
anna | +0.054 |
ivering | +0.047 |
annah | +0.046 |
uster | +0.045 |
ivery | +0.045 |
Neg logit contributions | |
da | -0.057 |
pe | -0.051 |
a | -0.050 |
an | -0.050 |
Sof | -0.048 |
Token | ies |
Token ID | 444 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
anna | +0.208 |
ivering | +0.192 |
ivery | +0.188 |
uster | +0.182 |
ital | +0.181 |
Neg logit contributions | |
da | -0.195 |
pe | -0.174 |
cr | -0.171 |
a | -0.169 |
an | -0.164 |
Token | ! |
Token ID | 0 |
Feature activation | -5.23e-04 |
Pos logit contributions | |
anna | +0.080 |
ivering | +0.073 |
uster | +0.073 |
annah | +0.073 |
ivery | +0.072 |
Neg logit contributions | |
da | -0.019 |
pe | -0.014 |
a | -0.014 |
an | -0.013 |
cr | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
anna | +0.001 |
ivering | +0.001 |
ivery | +0.001 |
ital | +0.001 |
agons | +0.001 |
Neg logit contributions | |
da | -0.001 |
a | -0.001 |
an | -0.001 |
Sof | -0.001 |
the | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
anna | +0.054 |
annah | +0.048 |
belt | +0.047 |
ivering | +0.047 |
ital | +0.047 |
Neg logit contributions | |
da | -0.025 |
an | -0.020 |
Sof | -0.020 |
pe | -0.019 |
a | -0.019 |
Token | so |
Token ID | 523 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
da | +0.002 |
cr | +0.001 |
pe | +0.001 |
aw | +0.001 |
ho | +0.001 |
Neg logit contributions | |
anna | -0.005 |
annah | -0.004 |
ivering | -0.004 |
belt | -0.004 |
uster | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -1.95e-03 |
Pos logit contributions | |
anna | +0.028 |
annah | +0.024 |
ivering | +0.024 |
amas | +0.024 |
Tomorrow | +0.024 |
Neg logit contributions | |
da | -0.019 |
aw | -0.015 |
pe | -0.014 |
cr | -0.014 |
eleven | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
anna | +0.005 |
ittens | +0.005 |
uster | +0.005 |
agons | +0.005 |
amas | +0.005 |
Neg logit contributions | |
da | -0.001 |
ho | -0.001 |
pe | -0.001 |
Sof | -0.001 |
cr | -0.001 |
Token | deer |
Token ID | 20096 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
da | +0.024 |
pe | +0.021 |
a | +0.020 |
an | +0.020 |
cr | +0.019 |
Neg logit contributions | |
anna | -0.033 |
ivering | -0.029 |
uster | -0.029 |
annah | -0.029 |
agons | -0.029 |
Token | named |
Token ID | 3706 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
anna | +0.049 |
ivering | +0.043 |
agons | +0.041 |
annah | +0.041 |
uster | +0.041 |
Neg logit contributions | |
da | -0.038 |
pe | -0.032 |
an | -0.032 |
Sof | -0.032 |
a | -0.031 |
Token | B |
Token ID | 347 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
anna | +0.086 |
ivering | +0.076 |
uster | +0.076 |
annah | +0.075 |
agons | +0.075 |
Neg logit contributions | |
da | -0.058 |
pe | -0.050 |
a | -0.049 |
an | -0.049 |
cr | -0.047 |
Token | amb |
Token ID | 4131 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
anna | +0.079 |
ivering | +0.073 |
ital | +0.072 |
belt | +0.071 |
ivery | +0.071 |
Neg logit contributions | |
da | -0.088 |
a | -0.077 |
pe | -0.077 |
Sof | -0.076 |
an | -0.075 |
Token | i |
Token ID | 72 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
amas | +0.216 |
ivering | +0.216 |
ivery | +0.212 |
uster | +0.206 |
anna | +0.202 |
Neg logit contributions | |
da | -0.167 |
pe | -0.159 |
ho | -0.138 |
an | -0.138 |
Sof | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
anna | +0.076 |
agons | +0.066 |
ivering | +0.066 |
ittens | +0.065 |
annah | +0.065 |
Neg logit contributions | |
da | -0.029 |
Sof | -0.023 |
an | -0.023 |
pe | -0.023 |
cr | -0.021 |
Token | B |
Token ID | 347 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
anna | +0.062 |
ivering | +0.055 |
annah | +0.055 |
ital | +0.054 |
belt | +0.053 |
Neg logit contributions | |
da | -0.038 |
a | -0.035 |
an | -0.034 |
pe | -0.034 |
Sof | -0.031 |
Token | amb |
Token ID | 4131 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
anna | +0.080 |
ivering | +0.072 |
belt | +0.071 |
ivery | +0.071 |
ital | +0.070 |
Neg logit contributions | |
da | -0.109 |
pe | -0.099 |
a | -0.096 |
an | -0.095 |
Sof | -0.095 |
Token | i |
Token ID | 72 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
ivering | +0.229 |
ivery | +0.229 |
amas | +0.225 |
uster | +0.217 |
ital | +0.217 |
Neg logit contributions | |
da | -0.156 |
pe | -0.153 |
ho | -0.131 |
Sof | -0.126 |
an | -0.125 |
Token | happened |
Token ID | 3022 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
anna | +0.029 |
ivering | +0.026 |
annah | +0.026 |
uster | +0.026 |
belt | +0.026 |
Neg logit contributions | |
da | -0.014 |
pe | -0.011 |
an | -0.011 |
a | -0.011 |
Sof | -0.011 |
Token | : |
Token ID | 25 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
anna | +0.025 |
ivering | +0.022 |
belt | +0.022 |
annah | +0.022 |
uster | +0.022 |
Neg logit contributions | |
da | -0.009 |
pe | -0.007 |
Sof | -0.007 |
cr | -0.006 |
aw | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
da | +0.036 |
pe | +0.029 |
an | +0.026 |
Sof | +0.026 |
a | +0.026 |
Neg logit contributions | |
anna | -0.093 |
uster | -0.085 |
ivering | -0.084 |
annah | -0.084 |
agons | -0.084 |
Token | modern |
Token ID | 3660 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
da | +0.020 |
an | +0.016 |
Sof | +0.016 |
pe | +0.016 |
a | +0.016 |
Neg logit contributions | |
anna | -0.039 |
ivering | -0.035 |
uster | -0.035 |
belt | -0.035 |
annah | -0.034 |
Token | l |
Token ID | 300 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
anna | +0.042 |
annah | +0.037 |
ivering | +0.037 |
belt | +0.037 |
uster | +0.037 |
Neg logit contributions | |
da | -0.021 |
an | -0.018 |
pe | -0.018 |
a | -0.017 |
Sof | -0.017 |
Token | oll |
Token ID | 692 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
anna | +0.042 |
ivering | +0.035 |
uster | +0.035 |
annah | +0.035 |
agons | +0.034 |
Neg logit contributions | |
da | -0.058 |
pe | -0.053 |
an | -0.053 |
a | -0.052 |
cr | -0.051 |
Token | ipop |
Token ID | 42800 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
anna | +0.194 |
ivering | +0.176 |
ivery | +0.175 |
uster | +0.170 |
agons | +0.167 |
Neg logit contributions | |
da | -0.209 |
pe | -0.194 |
cr | -0.185 |
a | -0.182 |
an | -0.175 |
Token | machine |
Token ID | 4572 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
anna | +0.069 |
ivering | +0.063 |
uster | +0.063 |
annah | +0.063 |
agons | +0.062 |
Neg logit contributions | |
da | -0.022 |
pe | -0.017 |
a | -0.016 |
an | -0.016 |
cr | -0.015 |
Token | came |
Token ID | 1625 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
anna | +0.017 |
ivering | +0.016 |
uster | +0.016 |
annah | +0.016 |
agons | +0.016 |
Neg logit contributions | |
da | -0.006 |
pe | -0.005 |
a | -0.005 |
an | -0.004 |
cr | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
da | +0.004 |
Sof | +0.003 |
pe | +0.003 |
aw | +0.003 |
cr | +0.003 |
Neg logit contributions | |
anna | -0.011 |
uster | -0.010 |
ivering | -0.010 |
annah | -0.009 |
amas | -0.009 |
Token | their |
Token ID | 511 |
Feature activation | +3.64e-03 |
Pos logit contributions | |
da | +0.018 |
pe | +0.014 |
a | +0.013 |
an | +0.013 |
cr | +0.012 |
Neg logit contributions | |
anna | -0.057 |
ivering | -0.052 |
uster | -0.052 |
annah | -0.052 |
agons | -0.052 |
Token | not |
Token ID | 407 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
anna | +0.057 |
uster | +0.051 |
agons | +0.050 |
ivering | +0.050 |
annah | +0.050 |
Neg logit contributions | |
da | -0.026 |
a | -0.024 |
pe | -0.024 |
an | -0.024 |
Sof | -0.021 |
Token | find |
Token ID | 1064 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
da | +0.047 |
pe | +0.041 |
an | +0.040 |
a | +0.040 |
cr | +0.039 |
Neg logit contributions | |
anna | -0.044 |
ivering | -0.037 |
annah | -0.037 |
uster | -0.037 |
ivery | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
da | +0.021 |
ho | +0.016 |
pe | +0.016 |
cr | +0.015 |
Sof | +0.015 |
Neg logit contributions | |
anna | -0.041 |
uster | -0.037 |
annah | -0.036 |
ittens | -0.036 |
belt | -0.036 |
Token | rare |
Token ID | 4071 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
da | +0.021 |
aw | +0.018 |
an | +0.018 |
Sof | +0.017 |
a | +0.017 |
Neg logit contributions | |
anna | -0.048 |
uster | -0.043 |
annah | -0.043 |
ivering | -0.043 |
belt | -0.042 |
Token | l |
Token ID | 300 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
anna | +0.042 |
uster | +0.037 |
ivering | +0.037 |
annah | +0.037 |
belt | +0.037 |
Neg logit contributions | |
da | -0.014 |
an | -0.011 |
Sof | -0.011 |
aw | -0.011 |
pe | -0.011 |
Token | oll |
Token ID | 692 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
anna | +0.042 |
uster | +0.035 |
ivering | +0.035 |
annah | +0.034 |
agons | +0.034 |
Neg logit contributions | |
da | -0.064 |
pe | -0.058 |
an | -0.057 |
a | -0.057 |
cr | -0.056 |
Token | ipop |
Token ID | 42800 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
anna | +0.187 |
ivering | +0.169 |
ivery | +0.165 |
uster | +0.159 |
amas | +0.158 |
Neg logit contributions | |
da | -0.213 |
pe | -0.197 |
a | -0.189 |
cr | -0.189 |
an | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
anna | +0.081 |
ivering | +0.074 |
uster | +0.073 |
annah | +0.073 |
agons | +0.073 |
Neg logit contributions | |
da | -0.021 |
pe | -0.016 |
a | -0.016 |
an | -0.015 |
cr | -0.014 |
Token | Finally |
Token ID | 9461 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
anna | +0.026 |
ivering | +0.023 |
uster | +0.023 |
annah | +0.023 |
agons | +0.023 |
Neg logit contributions | |
da | -0.010 |
pe | -0.009 |
a | -0.009 |
an | -0.009 |
Sof | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -6.45e-03 |
Pos logit contributions | |
anna | +0.043 |
ivering | +0.040 |
uster | +0.040 |
agons | +0.039 |
ivery | +0.039 |
Neg logit contributions | |
da | -0.008 |
a | -0.006 |
an | -0.006 |
pe | -0.006 |
the | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
anna | +0.014 |
belt | +0.012 |
annah | +0.012 |
uster | +0.012 |
ivering | +0.012 |
Neg logit contributions | |
da | -0.009 |
pe | -0.008 |
Sof | -0.007 |
an | -0.007 |
cr | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
anna | +0.037 |
ivering | +0.035 |
ivery | +0.035 |
annah | +0.035 |
uster | +0.034 |
Neg logit contributions | |
a | -0.005 |
da | -0.005 |
an | -0.004 |
to | -0.004 |
the | -0.004 |
Token | One |
Token ID | 1881 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
anna | +0.039 |
ivering | +0.039 |
ivery | +0.037 |
ital | +0.037 |
annah | +0.037 |
Neg logit contributions | |
da | -0.017 |
a | -0.016 |
an | -0.015 |
pe | -0.015 |
the | -0.014 |
Token | day |
Token ID | 1110 |
Feature activation | -7.29e-03 |
Pos logit contributions | |
anna | +0.059 |
ivering | +0.049 |
uster | +0.049 |
annah | +0.049 |
agons | +0.048 |
Neg logit contributions | |
da | -0.079 |
pe | -0.072 |
a | -0.071 |
an | -0.070 |
cr | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | -9.21e-03 |
Pos logit contributions | |
anna | +0.020 |
uster | +0.018 |
ivering | +0.018 |
annah | +0.018 |
agons | +0.018 |
Neg logit contributions | |
da | -0.006 |
pe | -0.004 |
an | -0.004 |
a | -0.004 |
Sof | -0.004 |
Token | B |
Token ID | 347 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
anna | +0.021 |
ivering | +0.019 |
annah | +0.019 |
ital | +0.018 |
agons | +0.018 |
Neg logit contributions | |
da | -0.013 |
a | -0.012 |
an | -0.012 |
pe | -0.011 |
the | -0.011 |
Token | amb |
Token ID | 4131 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
anna | +0.081 |
ivering | +0.076 |
belt | +0.076 |
ital | +0.075 |
ivery | +0.075 |
Neg logit contributions | |
da | -0.106 |
pe | -0.096 |
Sof | -0.092 |
a | -0.092 |
an | -0.091 |
Token | i |
Token ID | 72 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
ivering | +0.236 |
ivery | +0.235 |
amas | +0.231 |
uster | +0.222 |
ital | +0.222 |
Neg logit contributions | |
da | -0.154 |
pe | -0.150 |
ho | -0.126 |
an | -0.124 |
Sof | -0.124 |
Token | was |
Token ID | 373 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
anna | +0.105 |
uster | +0.100 |
annah | +0.098 |
ivery | +0.098 |
agons | +0.098 |
Neg logit contributions | |
da | -0.031 |
pe | -0.026 |
a | -0.024 |
an | -0.022 |
aw | -0.021 |
Token | running |
Token ID | 2491 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
anna | +0.023 |
agons | +0.021 |
uster | +0.021 |
annah | +0.020 |
ivering | +0.020 |
Neg logit contributions | |
a | -0.014 |
da | -0.014 |
an | -0.013 |
pe | -0.013 |
high | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
anna | +0.059 |
uster | +0.053 |
ivering | +0.052 |
belt | +0.052 |
annah | +0.052 |
Neg logit contributions | |
da | -0.036 |
cr | -0.028 |
pe | -0.028 |
Sof | -0.027 |
aw | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
da | +0.032 |
ho | +0.025 |
aw | +0.025 |
cr | +0.023 |
cr | +0.020 |
Neg logit contributions | |
anna | -0.117 |
uster | -0.111 |
annah | -0.111 |
agons | -0.110 |
lifestyle | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
da | +0.002 |
pe | +0.001 |
an | +0.001 |
Sof | +0.001 |
a | +0.001 |
Neg logit contributions | |
anna | -0.004 |
uster | -0.004 |
belt | -0.004 |
annah | -0.004 |
ivering | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
anna | +0.044 |
ivering | +0.039 |
annah | +0.038 |
uster | +0.038 |
ivery | +0.038 |
Neg logit contributions | |
da | -0.042 |
a | -0.038 |
an | -0.038 |
pe | -0.038 |
cr | -0.036 |
Token | always |
Token ID | 1464 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
anna | +0.072 |
ivering | +0.064 |
uster | +0.064 |
annah | +0.064 |
agons | +0.063 |
Neg logit contributions | |
da | -0.045 |
pe | -0.039 |
a | -0.038 |
an | -0.038 |
cr | -0.036 |
Token | had |
Token ID | 550 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
anna | +0.159 |
uster | +0.149 |
ivering | +0.146 |
agons | +0.146 |
ittens | +0.144 |
Neg logit contributions | |
da | -0.083 |
a | -0.077 |
pe | -0.077 |
an | -0.074 |
cr | -0.074 |
Token | a |
Token ID | 257 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
ho | +0.005 |
da | +0.005 |
Sof | +0.004 |
cr | +0.004 |
pe | +0.003 |
Neg logit contributions | |
anna | -0.023 |
annah | -0.020 |
agons | -0.020 |
uster | -0.020 |
belt | -0.020 |
Token | tw |
Token ID | 665 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
anna | +0.019 |
agons | +0.017 |
belt | +0.017 |
annah | +0.017 |
ital | +0.017 |
Neg logit contributions | |
da | -0.012 |
Sof | -0.011 |
aw | -0.010 |
cr | -0.010 |
pe | -0.010 |
Token | ig |
Token ID | 328 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
anna | +0.150 |
uster | +0.129 |
ivering | +0.129 |
ivery | +0.128 |
amas | +0.124 |
Neg logit contributions | |
da | -0.245 |
pe | -0.224 |
an | -0.214 |
high | -0.212 |
a | -0.212 |
Token | in |
Token ID | 287 |
Feature activation | -4.60e-03 |
Pos logit contributions | |
anna | +0.157 |
ivering | +0.143 |
agons | +0.142 |
ivery | +0.142 |
uster | +0.142 |
Neg logit contributions | |
da | -0.076 |
a | -0.064 |
pe | -0.063 |
an | -0.062 |
cr | -0.060 |
Token | his |
Token ID | 465 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
anna | +0.012 |
ivering | +0.011 |
uster | +0.011 |
annah | +0.011 |
agons | +0.011 |
Neg logit contributions | |
da | -0.004 |
a | -0.004 |
pe | -0.004 |
an | -0.004 |
cr | -0.003 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
anna | +0.105 |
ivering | +0.091 |
uster | +0.090 |
annah | +0.089 |
agons | +0.088 |
Neg logit contributions | |
da | -0.102 |
pe | -0.091 |
a | -0.090 |
an | -0.090 |
cr | -0.087 |
Token | so |
Token ID | 523 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
anna | +0.038 |
ivery | +0.036 |
ivering | +0.036 |
agons | +0.036 |
ital | +0.035 |
Neg logit contributions | |
da | -0.007 |
a | -0.007 |
cr | -0.006 |
to | -0.006 |
an | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | +4.70e-04 |
Pos logit contributions | |
anna | +0.071 |
uster | +0.066 |
ivering | +0.066 |
agons | +0.066 |
ivery | +0.065 |
Neg logit contributions | |
da | -0.014 |
a | -0.011 |
pe | -0.010 |
an | -0.010 |
the | -0.009 |
Token | all |
Token ID | 477 |
Feature activation | +8.52e-03 |
Pos logit contributions | |
da | +0.001 |
pe | +0.000 |
an | +0.000 |
a | +0.000 |
Sof | +0.000 |
Neg logit contributions | |
anna | -0.001 |
annah | -0.001 |
ivering | -0.001 |
uster | -0.001 |
belt | -0.001 |
Token | valued |
Token ID | 17560 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
da | +0.010 |
pe | +0.009 |
a | +0.009 |
an | +0.009 |
the | +0.008 |
Neg logit contributions | |
anna | -0.020 |
uster | -0.019 |
agons | -0.018 |
ivering | -0.018 |
amas | -0.018 |
Token | their |
Token ID | 511 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
anna | +0.058 |
ivering | +0.053 |
uster | +0.053 |
annah | +0.053 |
agons | +0.053 |
Neg logit contributions | |
da | -0.020 |
pe | -0.016 |
an | -0.014 |
a | -0.014 |
Sof | -0.014 |
Token | l |
Token ID | 300 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
anna | +0.085 |
uster | +0.078 |
ivering | +0.077 |
ivery | +0.076 |
annah | +0.076 |
Neg logit contributions | |
da | -0.048 |
pe | -0.041 |
a | -0.040 |
an | -0.039 |
cr | -0.038 |
Token | oll |
Token ID | 692 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
anna | +0.060 |
ivering | +0.051 |
uster | +0.051 |
ivery | +0.050 |
agons | +0.050 |
Neg logit contributions | |
da | -0.074 |
pe | -0.066 |
a | -0.065 |
an | -0.064 |
Sof | -0.064 |
Token | ip |
Token ID | 541 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
anna | +0.188 |
ivering | +0.174 |
ivery | +0.172 |
uster | +0.171 |
ital | +0.165 |
Neg logit contributions | |
da | -0.209 |
pe | -0.190 |
cr | -0.184 |
a | -0.183 |
an | -0.177 |
Token | ops |
Token ID | 2840 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
anna | +0.136 |
uster | +0.125 |
ivering | +0.121 |
belt | +0.118 |
ivery | +0.118 |
Neg logit contributions | |
da | -0.152 |
pe | -0.137 |
a | -0.136 |
cr | -0.132 |
an | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | +4.57e-03 |
Pos logit contributions | |
anna | +0.067 |
uster | +0.061 |
ivering | +0.061 |
annah | +0.061 |
agons | +0.060 |
Neg logit contributions | |
da | -0.018 |
a | -0.013 |
pe | -0.013 |
an | -0.013 |
cr | -0.012 |
Token | same |
Token ID | 976 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
da | +0.005 |
a | +0.005 |
pe | +0.005 |
an | +0.004 |
cr | +0.004 |
Neg logit contributions | |
anna | -0.011 |
uster | -0.010 |
ivering | -0.010 |
ivery | -0.010 |
annah | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
anna | +0.041 |
uster | +0.038 |
ivering | +0.038 |
ivery | +0.038 |
agons | +0.037 |
Neg logit contributions | |
da | -0.018 |
a | -0.015 |
pe | -0.015 |
cr | -0.014 |
an | -0.014 |
Token | B |
Token ID | 347 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
anna | +0.086 |
ivering | +0.076 |
uster | +0.076 |
annah | +0.075 |
agons | +0.075 |
Neg logit contributions | |
da | -0.058 |
pe | -0.050 |
a | -0.049 |
an | -0.049 |
cr | -0.047 |
Token | amb |
Token ID | 4131 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
anna | +0.079 |
ivering | +0.073 |
ital | +0.072 |
belt | +0.071 |
ivery | +0.071 |
Neg logit contributions | |
da | -0.088 |
a | -0.077 |
pe | -0.077 |
Sof | -0.076 |
an | -0.075 |
Token | i |
Token ID | 72 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
amas | +0.216 |
ivering | +0.216 |
ivery | +0.212 |
uster | +0.206 |
anna | +0.202 |
Neg logit contributions | |
da | -0.167 |
pe | -0.159 |
ho | -0.138 |
an | -0.138 |
Sof | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
anna | +0.076 |
agons | +0.066 |
ivering | +0.066 |
ittens | +0.065 |
annah | +0.065 |
Neg logit contributions | |
da | -0.029 |
Sof | -0.023 |
an | -0.023 |
pe | -0.023 |
cr | -0.021 |
Token | B |
Token ID | 347 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
anna | +0.062 |
ivering | +0.055 |
annah | +0.055 |
ital | +0.054 |
belt | +0.053 |
Neg logit contributions | |
da | -0.038 |
a | -0.035 |
an | -0.034 |
pe | -0.034 |
Sof | -0.031 |
Token | amb |
Token ID | 4131 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
anna | +0.080 |
ivering | +0.072 |
belt | +0.071 |
ivery | +0.071 |
ital | +0.070 |
Neg logit contributions | |
da | -0.109 |
pe | -0.099 |
a | -0.096 |
an | -0.095 |
Sof | -0.095 |
Token | i |
Token ID | 72 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
ivering | +0.229 |
ivery | +0.229 |
amas | +0.225 |
uster | +0.217 |
ital | +0.217 |
Neg logit contributions | |
da | -0.156 |
pe | -0.153 |
ho | -0.131 |
Sof | -0.126 |
an | -0.125 |
Token | was |
Token ID | 373 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
anna | +0.086 |
ivering | +0.076 |
uster | +0.076 |
annah | +0.075 |
agons | +0.075 |
Neg logit contributions | |
da | -0.052 |
pe | -0.044 |
a | -0.043 |
an | -0.043 |
Sof | -0.041 |
Token | gifted |
Token ID | 22527 |
Feature activation | -5.19e-03 |
Pos logit contributions | |
anna | +0.035 |
ivering | +0.032 |
uster | +0.032 |
annah | +0.032 |
agons | +0.032 |
Neg logit contributions | |
da | -0.007 |
pe | -0.004 |
an | -0.004 |
a | -0.004 |
cr | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
anna | +0.012 |
uster | +0.011 |
ittens | +0.011 |
ivering | +0.011 |
agons | +0.011 |
Neg logit contributions | |
da | -0.006 |
pe | -0.005 |
an | -0.005 |
Sof | -0.005 |
are | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
da | +0.007 |
pe | +0.006 |
an | +0.005 |
a | +0.005 |
Sof | +0.005 |
Neg logit contributions | |
anna | -0.018 |
agons | -0.016 |
uster | -0.016 |
annah | -0.016 |
ivering | -0.016 |
Token | swords |
Token ID | 19735 |
Feature activation | -7.38e-05 |
Pos logit contributions | |
anna | +0.021 |
ivering | +0.019 |
uster | +0.019 |
annah | +0.019 |
agons | +0.019 |
Neg logit contributions | |
da | -0.014 |
pe | -0.012 |
a | -0.012 |
an | -0.012 |
cr | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.53e-03 |
Pos logit contributions | |
anna | +0.000 |
ivering | +0.000 |
uster | +0.000 |
annah | +0.000 |
agons | +0.000 |
Neg logit contributions | |
da | -0.000 |
pe | -0.000 |
a | -0.000 |
an | -0.000 |
cr | -0.000 |
Token | They |
Token ID | 1119 |
Feature activation | -9.69e-03 |
Pos logit contributions | |
anna | +0.014 |
ivering | +0.014 |
belt | +0.013 |
agons | +0.013 |
ivery | +0.013 |
Neg logit contributions | |
a | -0.006 |
da | -0.006 |
an | -0.006 |
the | -0.005 |
Sof | -0.005 |
Token | swung |
Token ID | 28507 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
anna | +0.020 |
belt | +0.018 |
uster | +0.018 |
annah | +0.018 |
agons | +0.018 |
Neg logit contributions | |
da | -0.013 |
an | -0.011 |
aw | -0.011 |
Sof | -0.011 |
pe | -0.010 |
Token | them |
Token ID | 606 |
Feature activation | +4.17e-04 |
Pos logit contributions | |
agons | +0.033 |
belt | +0.032 |
uster | +0.031 |
anna | +0.030 |
lights | +0.029 |
Neg logit contributions | |
da | -0.025 |
Sof | -0.019 |
opot | -0.019 |
aw | -0.019 |
mel | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
da | +0.001 |
Sof | +0.001 |
aw | +0.001 |
mel | +0.001 |
cr | +0.000 |
Neg logit contributions | |
anna | -0.001 |
belt | -0.001 |
agons | -0.001 |
ider | -0.001 |
uster | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
da | +0.039 |
ho | +0.035 |
cr | +0.031 |
aw | +0.030 |
Sof | +0.028 |
Neg logit contributions | |
anna | -0.109 |
agons | -0.108 |
uster | -0.108 |
lifestyle | -0.108 |
annah | -0.106 |
Token | air |
Token ID | 1633 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
da | +0.070 |
Sof | +0.070 |
cr | +0.067 |
an | +0.066 |
ho | +0.065 |
Neg logit contributions | |
anna | -0.066 |
agons | -0.065 |
ivering | -0.060 |
ital | -0.058 |
annah | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
da | +0.023 |
pe | +0.018 |
an | +0.018 |
Sof | +0.017 |
cr | +0.016 |
Neg logit contributions | |
anna | -0.055 |
ivering | -0.050 |
annah | -0.049 |
uster | -0.049 |
belt | -0.049 |
Token | made |
Token ID | 925 |
Feature activation | +6.29e-03 |
Pos logit contributions | |
da | +0.011 |
aw | +0.009 |
an | +0.009 |
Sof | +0.009 |
pe | +0.009 |
Neg logit contributions | |
anna | -0.019 |
belt | -0.017 |
annah | -0.016 |
ital | -0.016 |
uster | -0.016 |
Token | loud |
Token ID | 7812 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
da | +0.006 |
ho | +0.006 |
Sof | +0.005 |
pe | +0.005 |
cr | +0.005 |
Neg logit contributions | |
anna | -0.014 |
agons | -0.013 |
uster | -0.012 |
immers | -0.012 |
amas | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
ho | +0.035 |
da | +0.035 |
Sof | +0.033 |
cr | +0.029 |
aw | +0.027 |
Neg logit contributions | |
anna | -0.093 |
uster | -0.093 |
agons | -0.090 |
belt | -0.088 |
lifestyle | -0.087 |
Token | round |
Token ID | 2835 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
da | +0.034 |
an | +0.028 |
Sof | +0.028 |
pe | +0.027 |
a | +0.027 |
Neg logit contributions | |
anna | -0.067 |
ivering | -0.061 |
uster | -0.060 |
belt | -0.060 |
agons | -0.060 |
Token | handle |
Token ID | 5412 |
Feature activation | +5.15e-03 |
Pos logit contributions | |
anna | +0.007 |
uster | +0.006 |
ivering | +0.006 |
annah | +0.006 |
belt | +0.006 |
Neg logit contributions | |
da | -0.004 |
an | -0.004 |
Sof | -0.004 |
pe | -0.004 |
a | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -7.62e-03 |
Pos logit contributions | |
da | +0.005 |
pe | +0.004 |
an | +0.004 |
Sof | +0.004 |
a | +0.004 |
Neg logit contributions | |
anna | -0.013 |
belt | -0.012 |
uster | -0.012 |
ivering | -0.012 |
annah | -0.012 |
Token | heard |
Token ID | 2982 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
anna | +0.019 |
belt | +0.018 |
annah | +0.017 |
uster | +0.017 |
agons | +0.017 |
Neg logit contributions | |
da | -0.007 |
Sof | -0.005 |
pe | -0.005 |
aw | -0.005 |
ho | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
da | +0.027 |
pe | +0.019 |
ho | +0.019 |
cr | +0.017 |
Sof | +0.016 |
Neg logit contributions | |
anna | -0.113 |
uster | -0.103 |
annah | -0.101 |
amas | -0.100 |
ivering | -0.099 |
Token | bell |
Token ID | 8966 |
Feature activation | +4.31e-03 |
Pos logit contributions | |
da | +0.067 |
an | +0.061 |
Sof | +0.059 |
aw | +0.057 |
a | +0.057 |
Neg logit contributions | |
anna | -0.098 |
ivering | -0.092 |
belt | -0.088 |
uster | -0.088 |
agons | -0.088 |
Token | ringing |
Token ID | 32333 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
da | +0.005 |
an | +0.004 |
pe | +0.004 |
Sof | +0.004 |
a | +0.004 |
Neg logit contributions | |
anna | -0.010 |
ivering | -0.009 |
belt | -0.009 |
uster | -0.009 |
agons | -0.009 |
Token | from |
Token ID | 422 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
da | +0.013 |
Sof | +0.010 |
cr | +0.009 |
pe | +0.009 |
ho | +0.009 |
Neg logit contributions | |
anna | -0.021 |
belt | -0.020 |
ivering | -0.019 |
amas | -0.019 |
uster | -0.018 |
Token | inside |
Token ID | 2641 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
da | +0.010 |
pe | +0.006 |
Sof | +0.005 |
cr | +0.005 |
an | +0.005 |
Neg logit contributions | |
anna | -0.048 |
uster | -0.044 |
ivering | -0.044 |
annah | -0.044 |
belt | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
da | +0.022 |
pe | +0.016 |
cr | +0.015 |
Sof | +0.015 |
an | +0.014 |
Neg logit contributions | |
anna | -0.060 |
ivering | -0.055 |
annah | -0.054 |
belt | -0.053 |
amas | -0.053 |
Token | One |
Token ID | 3198 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
anna | +0.050 |
ivering | +0.044 |
uster | +0.044 |
annah | +0.044 |
agons | +0.043 |
Neg logit contributions | |
da | -0.036 |
pe | -0.031 |
a | -0.030 |
an | -0.030 |
cr | -0.029 |
Token | day |
Token ID | 1110 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
anna | +0.057 |
ivering | +0.049 |
uster | +0.049 |
annah | +0.048 |
agons | +0.048 |
Neg logit contributions | |
da | -0.073 |
pe | -0.066 |
a | -0.066 |
an | -0.065 |
cr | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
anna | +0.034 |
uster | +0.031 |
ivering | +0.031 |
agons | +0.031 |
annah | +0.031 |
Neg logit contributions | |
da | -0.010 |
pe | -0.008 |
an | -0.007 |
Sof | -0.007 |
a | -0.007 |
Token | Louie |
Token ID | 48352 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
anna | +0.041 |
uster | +0.036 |
ivering | +0.036 |
agons | +0.035 |
annah | +0.035 |
Neg logit contributions | |
da | -0.035 |
pe | -0.031 |
an | -0.030 |
Sof | -0.029 |
a | -0.029 |
Token | heard |
Token ID | 2982 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
anna | +0.036 |
uster | +0.034 |
agons | +0.034 |
belt | +0.034 |
ivery | +0.034 |
Neg logit contributions | |
da | -0.010 |
pe | -0.009 |
a | -0.008 |
an | -0.008 |
the | -0.007 |
Token | something |
Token ID | 1223 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
da | +0.018 |
ho | +0.012 |
pe | +0.010 |
Sof | +0.009 |
cr | +0.009 |
Neg logit contributions | |
anna | -0.098 |
uster | -0.089 |
ivering | -0.088 |
amas | -0.086 |
agons | -0.086 |
Token | different |
Token ID | 1180 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
da | +0.060 |
Sof | +0.050 |
cr | +0.048 |
ho | +0.048 |
aw | +0.046 |
Neg logit contributions | |
anna | -0.107 |
agons | -0.098 |
ivering | -0.096 |
ittens | -0.094 |
uster | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
da | +0.022 |
Sof | +0.016 |
pe | +0.016 |
an | +0.016 |
cr | +0.016 |
Neg logit contributions | |
anna | -0.048 |
ivering | -0.044 |
agons | -0.043 |
ivery | -0.042 |
belt | -0.042 |
Token | It |
Token ID | 632 |
Feature activation | +5.78e-04 |
Pos logit contributions | |
anna | +0.028 |
ivering | +0.024 |
annah | +0.024 |
ivery | +0.024 |
uster | +0.024 |
Neg logit contributions | |
da | -0.026 |
a | -0.024 |
an | -0.024 |
pe | -0.024 |
Sof | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
da | +0.001 |
Sof | +0.001 |
cr | +0.001 |
aw | +0.001 |
ho | +0.001 |
Neg logit contributions | |
anna | -0.001 |
ivering | -0.001 |
rated | -0.001 |
ital | -0.001 |
ivery | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
da | +0.006 |
ho | +0.004 |
aw | +0.003 |
are | +0.003 |
pe | +0.003 |
Neg logit contributions | |
anna | -0.023 |
agons | -0.023 |
uster | -0.023 |
belt | -0.022 |
ivering | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
da | +0.027 |
pe | +0.022 |
a | +0.021 |
an | +0.021 |
Sof | +0.020 |
Neg logit contributions | |
anna | -0.063 |
ivering | -0.057 |
uster | -0.056 |
annah | -0.056 |
agons | -0.056 |
Token | himself |
Token ID | 2241 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
anna | +0.064 |
uster | +0.060 |
ivering | +0.059 |
ivery | +0.059 |
amas | +0.058 |
Neg logit contributions | |
a | -0.036 |
the | -0.035 |
an | -0.035 |
pe | -0.032 |
da | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
anna | +0.081 |
ivering | +0.074 |
uster | +0.074 |
ivery | +0.073 |
agons | +0.073 |
Neg logit contributions | |
da | -0.022 |
a | -0.018 |
an | -0.017 |
pe | -0.017 |
cr | -0.015 |
Token | went |
Token ID | 1816 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
anna | +0.059 |
uster | +0.056 |
ivering | +0.054 |
agons | +0.054 |
ivery | +0.053 |
Neg logit contributions | |
da | -0.029 |
a | -0.026 |
pe | -0.026 |
an | -0.025 |
the | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
anna | +0.084 |
ivering | +0.080 |
ivery | +0.080 |
uster | +0.078 |
agons | +0.078 |
Neg logit contributions | |
da | -0.012 |
a | -0.010 |
pe | -0.009 |
an | -0.009 |
to | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
da | +0.018 |
a | +0.017 |
pe | +0.016 |
an | +0.016 |
cr | +0.015 |
Neg logit contributions | |
anna | -0.028 |
ivering | -0.025 |
uster | -0.025 |
agons | -0.025 |
ivery | -0.025 |
Token | cafeteria |
Token ID | 43075 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
da | +0.088 |
cr | +0.078 |
pe | +0.078 |
Sof | +0.078 |
ho | +0.075 |
Neg logit contributions | |
anna | -0.079 |
ital | -0.073 |
annah | -0.071 |
belt | -0.069 |
ivering | -0.069 |
Token | to |
Token ID | 284 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
da | +0.026 |
pe | +0.020 |
an | +0.020 |
a | +0.018 |
Sof | +0.018 |
Neg logit contributions | |
anna | -0.072 |
annah | -0.066 |
belt | -0.065 |
ivering | -0.065 |
ital | -0.065 |
Token | get |
Token ID | 651 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
anna | +0.035 |
uster | +0.032 |
ivering | +0.031 |
ittens | +0.031 |
agons | +0.030 |
Neg logit contributions | |
da | -0.021 |
a | -0.020 |
pe | -0.020 |
an | -0.020 |
the | -0.019 |
Token | some |
Token ID | 617 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
da | +0.030 |
a | +0.025 |
pe | +0.025 |
an | +0.025 |
cr | +0.023 |
Neg logit contributions | |
anna | -0.077 |
ivering | -0.070 |
uster | -0.069 |
annah | -0.068 |
agons | -0.068 |
Token | food |
Token ID | 2057 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
da | +0.018 |
pe | +0.015 |
a | +0.015 |
an | +0.015 |
cr | +0.014 |
Neg logit contributions | |
anna | -0.036 |
ivering | -0.033 |
uster | -0.032 |
annah | -0.032 |
agons | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
da | +0.011 |
aw | +0.007 |
Sof | +0.007 |
pe | +0.007 |
an | +0.007 |
Neg logit contributions | |
anna | -0.042 |
ivering | -0.038 |
annah | -0.037 |
uster | -0.037 |
ital | -0.037 |
Token | play |
Token ID | 711 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
da | +0.030 |
pe | +0.026 |
an | +0.025 |
a | +0.025 |
Sof | +0.025 |
Neg logit contributions | |
anna | -0.033 |
ivering | -0.028 |
annah | -0.028 |
uster | -0.028 |
agons | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
anna | +0.073 |
ivering | +0.067 |
agons | +0.066 |
annah | +0.065 |
ivery | +0.065 |
Neg logit contributions | |
da | -0.027 |
pe | -0.021 |
Sof | -0.021 |
an | -0.020 |
cr | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
anna | +0.049 |
ivering | +0.046 |
agons | +0.046 |
belt | +0.044 |
uster | +0.044 |
Neg logit contributions | |
da | -0.022 |
a | -0.019 |
an | -0.018 |
pe | -0.018 |
Sof | -0.017 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
anna | +0.098 |
ivering | +0.088 |
annah | +0.088 |
uster | +0.087 |
agons | +0.087 |
Neg logit contributions | |
da | -0.036 |
pe | -0.029 |
an | -0.028 |
a | -0.028 |
Sof | -0.027 |
Token | something |
Token ID | 1223 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
ho | +0.028 |
engu | +0.026 |
opot | +0.025 |
hex | +0.024 |
cr | +0.021 |
Neg logit contributions | |
ittens | -0.042 |
anna | -0.040 |
doctors | -0.039 |
cowboy | -0.038 |
nights | -0.038 |
Token | big |
Token ID | 1263 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
da | +0.059 |
aw | +0.058 |
Sof | +0.057 |
eleven | +0.056 |
Ma | +0.055 |
Neg logit contributions | |
anna | -0.095 |
ittens | -0.091 |
agons | -0.091 |
ivering | -0.088 |
belt | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
da | +0.026 |
pe | +0.020 |
an | +0.019 |
a | +0.019 |
Sof | +0.018 |
Neg logit contributions | |
anna | -0.072 |
ivering | -0.065 |
uster | -0.064 |
annah | -0.064 |
agons | -0.064 |
Token | shiny |
Token ID | 22441 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
anna | +0.049 |
belt | +0.046 |
ivering | +0.044 |
agons | +0.044 |
annah | +0.044 |
Neg logit contributions | |
da | -0.023 |
Sof | -0.019 |
aw | -0.019 |
pe | -0.018 |
are | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
anna | +0.029 |
ivering | +0.027 |
belt | +0.027 |
agons | +0.027 |
ider | +0.026 |
Neg logit contributions | |
da | -0.014 |
Sof | -0.011 |
an | -0.010 |
pe | -0.010 |
cr | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ho | +0.011 |
da | +0.010 |
cr | +0.010 |
aw | +0.009 |
engu | +0.009 |
Neg logit contributions | |
anna | -0.026 |
annah | -0.025 |
Tomorrow | -0.025 |
agons | -0.025 |
lifestyle | -0.025 |
Token | put |
Token ID | 1234 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
anna | +0.009 |
uster | +0.008 |
ivering | +0.008 |
annah | +0.008 |
belt | +0.008 |
Neg logit contributions | |
da | -0.006 |
pe | -0.005 |
a | -0.005 |
an | -0.005 |
are | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
anna | +0.051 |
annah | +0.046 |
uster | +0.046 |
ivering | +0.046 |
agons | +0.046 |
Neg logit contributions | |
da | -0.014 |
pe | -0.011 |
an | -0.010 |
a | -0.010 |
Sof | -0.010 |
Token | blanket |
Token ID | 18447 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
da | +0.034 |
an | +0.029 |
pe | +0.029 |
a | +0.029 |
Sof | +0.029 |
Neg logit contributions | |
anna | -0.054 |
ivering | -0.048 |
uster | -0.048 |
agons | -0.047 |
annah | -0.047 |
Token | over |
Token ID | 625 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
anna | +0.033 |
agons | +0.030 |
annah | +0.030 |
ivering | +0.030 |
uster | +0.030 |
Neg logit contributions | |
da | -0.011 |
a | -0.010 |
pe | -0.009 |
an | -0.009 |
cr | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +8.15e-03 |
Pos logit contributions | |
da | +0.026 |
a | +0.022 |
an | +0.020 |
pe | +0.019 |
the | +0.018 |
Neg logit contributions | |
anna | -0.091 |
ivering | -0.085 |
uster | -0.085 |
ivery | -0.084 |
agons | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -6.57e-04 |
Pos logit contributions | |
a | +0.007 |
da | +0.006 |
an | +0.006 |
to | +0.006 |
high | +0.006 |
Neg logit contributions | |
anna | -0.022 |
uster | -0.021 |
agons | -0.021 |
ivering | -0.021 |
ascal | -0.021 |
Token | Or |
Token ID | 1471 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
anna | +0.002 |
agons | +0.001 |
ivering | +0.001 |
annah | +0.001 |
ivery | +0.001 |
Neg logit contributions | |
da | -0.001 |
a | -0.001 |
an | -0.001 |
Sof | -0.001 |
pe | -0.001 |
Token | we |
Token ID | 356 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
anna | +0.076 |
ivering | +0.070 |
ivery | +0.068 |
agons | +0.068 |
uster | +0.067 |
Neg logit contributions | |
da | -0.042 |
a | -0.039 |
an | -0.037 |
pe | -0.037 |
cr | -0.034 |
Token | can |
Token ID | 460 |
Feature activation | -5.24e-03 |
Pos logit contributions | |
da | +0.009 |
pe | +0.009 |
are | +0.009 |
a | +0.008 |
an | +0.008 |
Neg logit contributions | |
anna | -0.033 |
ivering | -0.031 |
annah | -0.031 |
amas | -0.031 |
agons | -0.031 |
Token | say |
Token ID | 910 |
Feature activation | -7.38e-03 |
Pos logit contributions | |
anna | +0.012 |
uster | +0.011 |
annah | +0.011 |
ivering | +0.011 |
agons | +0.011 |
Neg logit contributions | |
da | -0.006 |
pe | -0.006 |
a | -0.006 |
an | -0.006 |
are | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
anna | +0.017 |
ivering | +0.015 |
uster | +0.015 |
annah | +0.015 |
agons | +0.015 |
Neg logit contributions | |
da | -0.010 |
a | -0.009 |
an | -0.008 |
pe | -0.008 |
cr | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -8.73e-03 |
Pos logit contributions | |
anna | +0.076 |
uster | +0.073 |
belt | +0.072 |
annah | +0.071 |
agons | +0.070 |
Neg logit contributions | |
da | -0.018 |
pe | -0.012 |
aw | -0.010 |
Sof | -0.010 |
cr | -0.009 |
Token | string |
Token ID | 4731 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
anna | +0.020 |
uster | +0.018 |
annah | +0.017 |
agons | +0.017 |
ivering | +0.017 |
Neg logit contributions | |
da | -0.011 |
pe | -0.009 |
Sof | -0.009 |
an | -0.009 |
a | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -7.05e-03 |
Pos logit contributions | |
anna | +0.037 |
belt | +0.034 |
uster | +0.034 |
annah | +0.034 |
agons | +0.033 |
Neg logit contributions | |
da | -0.012 |
pe | -0.008 |
Sof | -0.008 |
an | -0.008 |
aw | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
anna | +0.022 |
ivering | +0.021 |
uster | +0.021 |
annah | +0.020 |
agons | +0.020 |
Neg logit contributions | |
da | -0.003 |
pe | -0.001 |
a | -0.001 |
an | -0.001 |
cr | -0.001 |
Token | butterfly |
Token ID | 35113 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
da | +0.024 |
pe | +0.021 |
Sof | +0.020 |
an | +0.020 |
a | +0.019 |
Neg logit contributions | |
anna | -0.046 |
ivering | -0.041 |
annah | -0.041 |
uster | -0.041 |
ivery | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-03 |
Pos logit contributions | |
da | +0.021 |
pe | +0.016 |
an | +0.015 |
a | +0.015 |
Sof | +0.014 |
Neg logit contributions | |
anna | -0.069 |
ivering | -0.062 |
uster | -0.062 |
annah | -0.062 |
agons | -0.061 |
Token | it |
Token ID | 340 |
Feature activation | +5.57e-03 |
Pos logit contributions | |
anna | +0.003 |
belt | +0.003 |
annah | +0.003 |
ital | +0.003 |
uster | +0.003 |
Neg logit contributions | |
da | -0.001 |
Sof | -0.001 |
aw | -0.001 |
pe | -0.001 |
an | -0.001 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
da | +0.007 |
Sof | +0.006 |
an | +0.006 |
pe | +0.006 |
aw | +0.006 |
Neg logit contributions | |
anna | -0.012 |
ital | -0.011 |
belt | -0.011 |
annah | -0.010 |
ivering | -0.010 |
Token | ! |
Token ID | 0 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
anna | +0.038 |
annah | +0.034 |
uster | +0.034 |
belt | +0.034 |
agons | +0.034 |
Neg logit contributions | |
da | -0.018 |
pe | -0.014 |
Sof | -0.013 |
cr | -0.013 |
an | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | +2.68e-04 |
Pos logit contributions | |
da | +0.002 |
a | +0.001 |
an | +0.001 |
the | +0.001 |
Sof | +0.001 |
Neg logit contributions | |
anna | -0.003 |
ivering | -0.003 |
ivery | -0.003 |
agons | -0.003 |
belt | -0.003 |
Token | butterfly |
Token ID | 35113 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
da | +0.000 |
a | +0.000 |
pe | +0.000 |
an | +0.000 |
cr | +0.000 |
Neg logit contributions | |
anna | -0.001 |
uster | -0.001 |
ivering | -0.001 |
annah | -0.001 |
belt | -0.001 |
Token | picture |
Token ID | 4286 |
Feature activation | +8.60e-03 |
Pos logit contributions | |
anna | +0.086 |
annah | +0.075 |
ivering | +0.075 |
uster | +0.075 |
belt | +0.074 |
Neg logit contributions | |
da | -0.059 |
pe | -0.051 |
an | -0.050 |
a | -0.049 |
Sof | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-04 |
Pos logit contributions | |
da | +0.007 |
pe | +0.006 |
an | +0.005 |
a | +0.005 |
Sof | +0.005 |
Neg logit contributions | |
anna | -0.023 |
ivering | -0.021 |
uster | -0.021 |
annah | -0.021 |
agons | -0.021 |
Token | It |
Token ID | 632 |
Feature activation | -1.39e-03 |
Pos logit contributions | |
da | +0.000 |
pe | +0.000 |
a | +0.000 |
an | +0.000 |
cr | +0.000 |
Neg logit contributions | |
anna | -0.000 |
ivering | -0.000 |
uster | -0.000 |
annah | -0.000 |
agons | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +1.52e-03 |
Pos logit contributions | |
anna | +0.003 |
ital | +0.003 |
ivering | +0.003 |
annah | +0.003 |
belt | +0.003 |
Neg logit contributions | |
da | -0.002 |
Sof | -0.001 |
pe | -0.001 |
aw | -0.001 |
cr | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
da | +0.001 |
pe | +0.001 |
ho | +0.001 |
aw | +0.001 |
cr | +0.001 |
Neg logit contributions | |
anna | -0.004 |
annah | -0.004 |
belt | -0.004 |
ivering | -0.004 |
uster | -0.004 |
Token | picture |
Token ID | 4286 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
da | +0.018 |
Sof | +0.017 |
aw | +0.016 |
pe | +0.016 |
an | +0.016 |
Neg logit contributions | |
anna | -0.034 |
ital | -0.031 |
belt | -0.031 |
ivering | -0.031 |
annah | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
da | +0.012 |
pe | +0.010 |
an | +0.010 |
a | +0.010 |
Sof | +0.010 |
Neg logit contributions | |
anna | -0.024 |
ivering | -0.022 |
uster | -0.022 |
annah | -0.022 |
belt | -0.022 |
Token | remember |
Token ID | 3505 |
Feature activation | +7.90e-03 |
Pos logit contributions | |
anna | +0.074 |
ivering | +0.067 |
uster | +0.067 |
agons | +0.066 |
annah | +0.065 |
Neg logit contributions | |
da | -0.041 |
a | -0.037 |
pe | -0.036 |
an | -0.036 |
cr | -0.034 |
Token | ! |
Token ID | 0 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
da | +0.006 |
pe | +0.004 |
an | +0.004 |
a | +0.004 |
cr | +0.004 |
Neg logit contributions | |
anna | -0.022 |
ivering | -0.020 |
annah | -0.020 |
uster | -0.020 |
agons | -0.020 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
da | +0.007 |
pe | +0.005 |
an | +0.005 |
a | +0.005 |
cr | +0.005 |
Neg logit contributions | |
anna | -0.016 |
annah | -0.014 |
uster | -0.014 |
ivering | -0.014 |
agons | -0.014 |
Token | Frank |
Token ID | 17439 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
anna | +0.047 |
ivering | +0.042 |
uster | +0.042 |
annah | +0.042 |
agons | +0.042 |
Neg logit contributions | |
da | -0.016 |
a | -0.013 |
pe | -0.013 |
an | -0.012 |
Sof | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +5.41e-03 |
Pos logit contributions | |
da | +0.001 |
pe | +0.001 |
an | +0.001 |
a | +0.001 |
Sof | +0.001 |
Neg logit contributions | |
anna | -0.004 |
annah | -0.004 |
uster | -0.004 |
belt | -0.004 |
ivering | -0.004 |
Token | went |
Token ID | 1816 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
da | +0.007 |
a | +0.006 |
pe | +0.006 |
an | +0.006 |
the | +0.006 |
Neg logit contributions | |
anna | -0.013 |
ivering | -0.013 |
ivery | -0.012 |
agons | -0.012 |
ascal | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
anna | +0.043 |
ivering | +0.042 |
ivery | +0.042 |
ascal | +0.041 |
ittens | +0.041 |
Neg logit contributions | |
a | -0.012 |
da | -0.011 |
to | -0.011 |
pe | -0.011 |
an | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
da | +0.004 |
a | +0.004 |
an | +0.003 |
pe | +0.002 |
the | +0.001 |
Neg logit contributions | |
anna | -0.063 |
ivering | -0.060 |
ivery | -0.059 |
uster | -0.058 |
agons | -0.058 |
Token | ride |
Token ID | 6594 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
da | +0.031 |
a | +0.028 |
pe | +0.028 |
high | +0.026 |
an | +0.026 |
Neg logit contributions | |
anna | -0.038 |
ivering | -0.036 |
ivery | -0.036 |
agons | -0.036 |
amas | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -9.20e-04 |
Pos logit contributions | |
anna | +0.085 |
ivering | +0.079 |
agons | +0.078 |
uster | +0.078 |
ivery | +0.078 |
Neg logit contributions | |
da | -0.016 |
a | -0.014 |
an | -0.013 |
pe | -0.012 |
the | -0.011 |
Token | But |
Token ID | 887 |
Feature activation | -7.29e-03 |
Pos logit contributions | |
anna | +0.002 |
ivering | +0.002 |
agons | +0.002 |
ivery | +0.002 |
ital | +0.002 |
Neg logit contributions | |
a | -0.001 |
an | -0.001 |
the | -0.001 |
to | -0.001 |
pe | -0.001 |
Token | when |
Token ID | 618 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
agons | +0.018 |
anna | +0.018 |
ivering | +0.017 |
uster | +0.017 |
ivery | +0.017 |
Neg logit contributions | |
a | -0.009 |
the | -0.008 |
an | -0.008 |
pe | -0.007 |
da | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
a | +0.025 |
the | +0.024 |
an | +0.023 |
da | +0.020 |
high | +0.020 |
Neg logit contributions | |
anna | -0.061 |
uster | -0.056 |
ivering | -0.056 |
agons | -0.054 |
annah | -0.054 |
Token | got |
Token ID | 1392 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
anna | +0.070 |
agons | +0.069 |
ivery | +0.066 |
uster | +0.066 |
ivering | +0.066 |
Neg logit contributions | |
pe | -0.023 |
da | -0.022 |
a | -0.020 |
an | -0.018 |
the | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
da | +0.035 |
a | +0.031 |
an | +0.030 |
pe | +0.030 |
high | +0.027 |
Neg logit contributions | |
anna | -0.087 |
ivering | -0.079 |
agons | -0.078 |
uster | -0.078 |
annah | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
anna | +0.016 |
ivering | +0.014 |
annah | +0.014 |
uster | +0.014 |
belt | +0.014 |
Neg logit contributions | |
da | -0.005 |
pe | -0.004 |
an | -0.004 |
Sof | -0.004 |
a | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
da | +0.014 |
pe | +0.011 |
cr | +0.010 |
an | +0.010 |
aw | +0.010 |
Neg logit contributions | |
anna | -0.029 |
annah | -0.027 |
uster | -0.026 |
amas | -0.026 |
ivering | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -8.36e-03 |
Pos logit contributions | |
da | +0.014 |
pe | +0.011 |
cr | +0.011 |
an | +0.010 |
ho | +0.010 |
Neg logit contributions | |
anna | -0.026 |
annah | -0.024 |
uster | -0.023 |
ittens | -0.023 |
amas | -0.023 |
Token | Anna |
Token ID | 31160 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
anna | +0.017 |
ivering | +0.015 |
annah | +0.015 |
uster | +0.015 |
agons | +0.014 |
Neg logit contributions | |
da | -0.013 |
pe | -0.011 |
an | -0.011 |
a | -0.011 |
Sof | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
da | +0.033 |
pe | +0.026 |
an | +0.025 |
a | +0.025 |
Sof | +0.024 |
Neg logit contributions | |
anna | -0.089 |
ivering | -0.080 |
annah | -0.080 |
uster | -0.080 |
agons | -0.079 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
anna | +0.059 |
annah | +0.055 |
uster | +0.054 |
agons | +0.053 |
ittens | +0.053 |
Neg logit contributions | |
da | -0.044 |
pe | -0.038 |
aw | -0.036 |
an | -0.035 |
ho | -0.035 |
Token | run |
Token ID | 1057 |
Feature activation | -4.15e-03 |
Pos logit contributions | |
da | +0.032 |
Sof | +0.027 |
an | +0.026 |
cr | +0.025 |
aw | +0.025 |
Neg logit contributions | |
anna | -0.037 |
annah | -0.033 |
agons | -0.033 |
uster | -0.032 |
ivery | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
anna | +0.010 |
uster | +0.009 |
belt | +0.009 |
annah | +0.009 |
ital | +0.008 |
Neg logit contributions | |
da | -0.005 |
cr | -0.004 |
aw | -0.003 |
gl | -0.003 |
Sof | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
da | +0.026 |
aw | +0.025 |
ho | +0.020 |
cr | +0.019 |
cr | +0.017 |
Neg logit contributions | |
anna | -0.067 |
annah | -0.064 |
uster | -0.062 |
Tomorrow | -0.061 |
lifestyle | -0.060 |
Token | tree |
Token ID | 5509 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
da | +0.054 |
an | +0.047 |
Sof | +0.046 |
a | +0.045 |
pe | +0.044 |
Neg logit contributions | |
anna | -0.100 |
ivering | -0.090 |
belt | -0.088 |
annah | -0.087 |
ivery | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -4.98e-04 |
Pos logit contributions | |
da | +0.035 |
an | +0.027 |
aw | +0.027 |
pe | +0.026 |
Sof | +0.026 |
Neg logit contributions | |
anna | -0.080 |
ivering | -0.072 |
belt | -0.071 |
annah | -0.071 |
ittens | -0.069 |
Token | little |
Token ID | 1310 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
da | +0.002 |
a | +0.001 |
pe | +0.001 |
an | +0.001 |
cr | +0.001 |
Neg logit contributions | |
anna | -0.003 |
annah | -0.002 |
uster | -0.002 |
agons | -0.002 |
ivering | -0.002 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.44e-03 |
Pos logit contributions | |
anna | +0.020 |
ivering | +0.018 |
uster | +0.018 |
belt | +0.017 |
annah | +0.017 |
Neg logit contributions | |
da | -0.026 |
an | -0.023 |
pe | -0.023 |
Sof | -0.023 |
aw | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | +4.70e-03 |
Pos logit contributions | |
da | +0.007 |
pe | +0.006 |
a | +0.006 |
an | +0.006 |
cr | +0.005 |
Neg logit contributions | |
anna | -0.016 |
uster | -0.014 |
ivering | -0.014 |
agons | -0.014 |
annah | -0.014 |
Token | so |
Token ID | 523 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
da | +0.004 |
pe | +0.004 |
a | +0.004 |
an | +0.004 |
Sof | +0.003 |
Neg logit contributions | |
anna | -0.012 |
uster | -0.011 |
ivering | -0.011 |
agons | -0.011 |
annah | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | -7.21e-04 |
Pos logit contributions | |
da | +0.011 |
pe | +0.009 |
a | +0.009 |
an | +0.009 |
Sof | +0.009 |
Neg logit contributions | |
anna | -0.021 |
uster | -0.019 |
agons | -0.019 |
ivering | -0.019 |
annah | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
anna | +0.002 |
annah | +0.002 |
ivering | +0.002 |
uster | +0.002 |
belt | +0.002 |
Neg logit contributions | |
da | -0.001 |
pe | -0.000 |
cr | -0.000 |
an | -0.000 |
Sof | -0.000 |
Token | see |
Token ID | 766 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
anna | +0.041 |
uster | +0.041 |
amas | +0.040 |
belt | +0.040 |
ivering | +0.040 |
Neg logit contributions | |
a | -0.018 |
the | -0.017 |
an | -0.017 |
da | -0.017 |
pe | -0.016 |
Token | someone |
Token ID | 2130 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
da | +0.020 |
ho | +0.015 |
pe | +0.015 |
cr | +0.014 |
cr | +0.014 |
Neg logit contributions | |
anna | -0.068 |
annah | -0.062 |
uster | -0.061 |
ivering | -0.059 |
ittens | -0.059 |
Token | she |
Token ID | 673 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
da | +0.015 |
pe | +0.013 |
a | +0.012 |
an | +0.012 |
cr | +0.011 |
Neg logit contributions | |
anna | -0.041 |
uster | -0.038 |
ivering | -0.038 |
agons | -0.038 |
annah | -0.037 |
Token | could |
Token ID | 714 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
anna | +0.099 |
uster | +0.092 |
agons | +0.091 |
ivering | +0.090 |
ivery | +0.090 |
Neg logit contributions | |
da | -0.045 |
pe | -0.040 |
a | -0.038 |
an | -0.037 |
cr | -0.034 |
Token | play |
Token ID | 711 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
anna | +0.094 |
uster | +0.085 |
annah | +0.084 |
ivering | +0.084 |
amas | +0.083 |
Neg logit contributions | |
da | -0.044 |
a | -0.044 |
an | -0.042 |
pe | -0.041 |
to | -0.039 |
Token | done |
Token ID | 1760 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
da | +0.015 |
pe | +0.011 |
a | +0.010 |
an | +0.010 |
Sof | +0.010 |
Neg logit contributions | |
anna | -0.056 |
ivering | -0.051 |
uster | -0.050 |
annah | -0.050 |
agons | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
da | +0.010 |
a | +0.010 |
an | +0.009 |
pe | +0.007 |
the | +0.007 |
Neg logit contributions | |
anna | -0.061 |
uster | -0.057 |
ivering | -0.057 |
ivery | -0.056 |
agons | -0.056 |
Token | good |
Token ID | 922 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
da | +0.017 |
pe | +0.014 |
a | +0.014 |
an | +0.014 |
cr | +0.013 |
Neg logit contributions | |
anna | -0.034 |
ivering | -0.030 |
uster | -0.030 |
annah | -0.030 |
agons | -0.030 |
Token | job |
Token ID | 1693 |
Feature activation | +8.52e-03 |
Pos logit contributions | |
anna | +0.056 |
ivering | +0.051 |
ivery | +0.050 |
annah | +0.049 |
agons | +0.049 |
Neg logit contributions | |
da | -0.046 |
a | -0.044 |
an | -0.042 |
pe | -0.042 |
to | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
da | +0.005 |
a | +0.005 |
pe | +0.004 |
an | +0.004 |
to | +0.004 |
Neg logit contributions | |
anna | -0.025 |
ivery | -0.024 |
uster | -0.023 |
agons | -0.023 |
ivering | -0.023 |
Token | Together |
Token ID | 17083 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
anna | +0.044 |
ivery | +0.043 |
agons | +0.043 |
ivering | +0.043 |
immers | +0.041 |
Neg logit contributions | |
a | -0.018 |
an | -0.018 |
da | -0.017 |
Sof | -0.017 |
the | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
anna | +0.055 |
ivering | +0.051 |
uster | +0.051 |
ivery | +0.051 |
agons | +0.050 |
Neg logit contributions | |
da | -0.012 |
a | -0.009 |
an | -0.009 |
pe | -0.008 |
the | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | -4.07e-03 |
Pos logit contributions | |
da | +0.001 |
a | +0.001 |
the | +0.001 |
an | +0.001 |
pe | +0.001 |
Neg logit contributions | |
anna | -0.005 |
ivering | -0.005 |
ivery | -0.005 |
uster | -0.004 |
agons | -0.004 |
Token | left |
Token ID | 1364 |
Feature activation | -8.61e-03 |
Pos logit contributions | |
anna | +0.009 |
ivering | +0.008 |
uster | +0.008 |
agons | +0.008 |
belt | +0.008 |
Neg logit contributions | |
da | -0.006 |
an | -0.005 |
pe | -0.005 |
Sof | -0.005 |
a | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
anna | +0.026 |
ivering | +0.024 |
annah | +0.024 |
uster | +0.024 |
agons | +0.023 |
Neg logit contributions | |
da | -0.005 |
pe | -0.003 |
an | -0.002 |
a | -0.002 |
Sof | -0.002 |
Token | church |
Token ID | 4928 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
da | +0.046 |
a | +0.041 |
pe | +0.040 |
cr | +0.039 |
high | +0.039 |
Neg logit contributions | |
anna | -0.075 |
uster | -0.066 |
annah | -0.065 |
ittens | -0.064 |
ivery | -0.064 |
Token | Sarah |
Token ID | 29284 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
anna | +0.024 |
ivering | +0.021 |
uster | +0.021 |
agons | +0.021 |
annah | +0.021 |
Neg logit contributions | |
da | -0.019 |
a | -0.017 |
an | -0.017 |
pe | -0.017 |
Sof | -0.016 |
Token | followed |
Token ID | 3940 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
da | +0.014 |
pe | +0.012 |
a | +0.012 |
an | +0.011 |
cr | +0.011 |
Neg logit contributions | |
anna | -0.037 |
uster | -0.035 |
agons | -0.035 |
ivering | -0.034 |
ivery | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
anna | +0.066 |
ivering | +0.061 |
uster | +0.060 |
annah | +0.060 |
agons | +0.060 |
Neg logit contributions | |
da | -0.012 |
pe | -0.008 |
a | -0.007 |
an | -0.007 |
Sof | -0.006 |
Token | music |
Token ID | 2647 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
da | +0.039 |
a | +0.035 |
pe | +0.034 |
an | +0.033 |
cr | +0.032 |
Neg logit contributions | |
anna | -0.058 |
ivering | -0.052 |
uster | -0.052 |
ivery | -0.051 |
annah | -0.051 |
Token | until |
Token ID | 1566 |
Feature activation | +7.70e-03 |
Pos logit contributions | |
da | +0.013 |
pe | +0.010 |
a | +0.010 |
an | +0.010 |
cr | +0.009 |
Neg logit contributions | |
anna | -0.035 |
ivering | -0.032 |
uster | -0.031 |
annah | -0.031 |
agons | -0.031 |
Token | she |
Token ID | 673 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
da | +0.007 |
pe | +0.006 |
a | +0.006 |
an | +0.006 |
Sof | +0.005 |
Neg logit contributions | |
anna | -0.020 |
ivering | -0.018 |
uster | -0.018 |
annah | -0.018 |
agons | -0.018 |
Token | found |
Token ID | 1043 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
anna | +0.038 |
ivering | +0.033 |
ital | +0.033 |
annah | +0.033 |
uster | +0.032 |
Neg logit contributions | |
da | -0.021 |
an | -0.017 |
pe | -0.016 |
cr | -0.016 |
a | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
da | +0.013 |
ho | +0.012 |
pe | +0.010 |
hex | +0.010 |
cr | +0.009 |
Neg logit contributions | |
anna | -0.045 |
uster | -0.042 |
belt | -0.041 |
annah | -0.041 |
amas | -0.039 |
Token | room |
Token ID | 2119 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
da | +0.045 |
pe | +0.038 |
an | +0.037 |
Sof | +0.037 |
a | +0.036 |
Neg logit contributions | |
anna | -0.092 |
ivering | -0.083 |
uster | -0.082 |
annah | -0.081 |
belt | -0.081 |
Token | with |
Token ID | 351 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
da | +0.018 |
pe | +0.014 |
Sof | +0.014 |
an | +0.014 |
a | +0.013 |
Neg logit contributions | |
anna | -0.044 |
belt | -0.040 |
ivering | -0.040 |
annah | -0.039 |
uster | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
da | +0.022 |
ho | +0.019 |
Sof | +0.016 |
pe | +0.016 |
cr | +0.015 |
Neg logit contributions | |
anna | -0.095 |
uster | -0.089 |
belt | -0.088 |
amas | -0.086 |
agons | -0.086 |
Token | explore |
Token ID | 7301 |
Feature activation | -8.95e-03 |
Pos logit contributions | |
anna | +0.074 |
uster | +0.069 |
ivering | +0.068 |
annah | +0.066 |
ider | +0.064 |
Neg logit contributions | |
a | -0.036 |
da | -0.035 |
pe | -0.034 |
cr | -0.033 |
an | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -7.27e-03 |
Pos logit contributions | |
anna | +0.020 |
agons | +0.019 |
ittens | +0.018 |
lifestyle | +0.018 |
nights | +0.018 |
Neg logit contributions | |
ho | -0.009 |
da | -0.009 |
Sof | -0.008 |
cr | -0.008 |
bug | -0.006 |
Token | have |
Token ID | 423 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
anna | +0.016 |
uster | +0.015 |
ivering | +0.015 |
annah | +0.015 |
agons | +0.015 |
Neg logit contributions | |
da | -0.010 |
pe | -0.009 |
a | -0.009 |
an | -0.009 |
the | -0.008 |
Token | new |
Token ID | 649 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
ho | +0.033 |
da | +0.028 |
Sof | +0.026 |
cr | +0.025 |
opot | +0.024 |
Neg logit contributions | |
anna | -0.043 |
lifestyle | -0.040 |
agons | -0.039 |
ital | -0.039 |
nights | -0.038 |
Token | adventures |
Token ID | 17545 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
anna | +0.075 |
ivering | +0.067 |
uster | +0.066 |
annah | +0.066 |
ivery | +0.065 |
Neg logit contributions | |
da | -0.059 |
pe | -0.053 |
a | -0.051 |
an | -0.051 |
cr | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
anna | +0.178 |
ivering | +0.164 |
uster | +0.163 |
annah | +0.162 |
ivery | +0.161 |
Neg logit contributions | |
da | -0.042 |
a | -0.033 |
pe | -0.032 |
an | -0.032 |
cr | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -4.17e-03 |
Pos logit contributions | |
anna | +0.054 |
ivering | +0.047 |
uster | +0.046 |
annah | +0.046 |
ivery | +0.046 |
Neg logit contributions | |
da | -0.047 |
a | -0.041 |
pe | -0.041 |
an | -0.041 |
Sof | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
anna | +0.009 |
ittens | +0.008 |
annah | +0.008 |
uster | +0.008 |
ivering | +0.008 |
Neg logit contributions | |
da | -0.005 |
pe | -0.004 |
cr | -0.004 |
aw | -0.004 |
an | -0.004 |
Token | One |
Token ID | 3198 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
anna | +0.044 |
agons | +0.039 |
ivering | +0.039 |
annah | +0.038 |
ittens | +0.038 |
Neg logit contributions | |
da | -0.040 |
pe | -0.035 |
an | -0.033 |
a | -0.033 |
Sof | -0.033 |
Token | day |
Token ID | 1110 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
anna | +0.055 |
ivering | +0.046 |
uster | +0.046 |
annah | +0.046 |
agons | +0.045 |
Neg logit contributions | |
da | -0.074 |
pe | -0.067 |
an | -0.066 |
a | -0.065 |
Sof | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
anna | +0.040 |
ittens | +0.037 |
agons | +0.037 |
annah | +0.037 |
ivering | +0.036 |
Neg logit contributions | |
da | -0.015 |
pe | -0.011 |
Sof | -0.010 |
an | -0.010 |
aw | -0.009 |
Token | their |
Token ID | 511 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
anna | +0.003 |
ivering | +0.003 |
agons | +0.003 |
uster | +0.003 |
ivery | +0.003 |
Neg logit contributions | |
da | -0.001 |
a | -0.001 |
an | -0.001 |
pe | -0.001 |
the | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
anna | +0.080 |
ivering | +0.072 |
uster | +0.070 |
annah | +0.070 |
ivery | +0.070 |
Neg logit contributions | |
da | -0.042 |
pe | -0.037 |
a | -0.036 |
an | -0.035 |
cr | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
da | +0.022 |
pe | +0.018 |
a | +0.018 |
an | +0.018 |
Sof | +0.016 |
Neg logit contributions | |
anna | -0.054 |
ivering | -0.048 |
uster | -0.048 |
annah | -0.048 |
agons | -0.048 |
Token | busy |
Token ID | 8179 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
da | +0.021 |
a | +0.019 |
pe | +0.019 |
an | +0.019 |
high | +0.017 |
Neg logit contributions | |
anna | -0.040 |
uster | -0.035 |
agons | -0.035 |
ivering | -0.035 |
annah | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +4.90e-04 |
Pos logit contributions | |
da | +0.019 |
a | +0.018 |
pe | +0.018 |
an | +0.017 |
the | +0.016 |
Neg logit contributions | |
anna | -0.060 |
uster | -0.056 |
agons | -0.055 |
ivering | -0.053 |
ivery | -0.053 |
Token | sne |
Token ID | 10505 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
da | +0.001 |
a | +0.000 |
pe | +0.000 |
an | +0.000 |
cr | +0.000 |
Neg logit contributions | |
anna | -0.001 |
uster | -0.001 |
ivering | -0.001 |
agons | -0.001 |
annah | -0.001 |
Token | aked |
Token ID | 4335 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
anna | +0.028 |
belt | +0.027 |
uster | +0.026 |
annah | +0.026 |
amas | +0.025 |
Neg logit contributions | |
da | -0.024 |
aw | -0.024 |
a | -0.023 |
an | -0.023 |
pe | -0.022 |
Token | into |
Token ID | 656 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
anna | +0.007 |
uster | +0.006 |
annah | +0.006 |
belt | +0.006 |
amas | +0.006 |
Neg logit contributions | |
da | -0.003 |
pe | -0.002 |
Sof | -0.002 |
aw | -0.002 |
cr | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
da | +0.024 |
aw | +0.016 |
pe | +0.013 |
ho | +0.012 |
cr | +0.012 |
Neg logit contributions | |
anna | -0.119 |
annah | -0.113 |
uster | -0.112 |
ivering | -0.110 |
belt | -0.110 |
Token | garage |
Token ID | 15591 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
da | +0.074 |
pe | +0.066 |
an | +0.065 |
a | +0.065 |
Sof | +0.064 |
Neg logit contributions | |
anna | -0.065 |
ivering | -0.056 |
uster | -0.055 |
annah | -0.055 |
agons | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +6.86e-03 |
Pos logit contributions | |
da | +0.020 |
pe | +0.015 |
an | +0.015 |
Sof | +0.014 |
a | +0.014 |
Neg logit contributions | |
anna | -0.051 |
annah | -0.047 |
belt | -0.047 |
ivering | -0.047 |
uster | -0.046 |
Token | themselves |
Token ID | 2405 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
anna | +0.066 |
agons | +0.060 |
annah | +0.059 |
ivering | +0.059 |
belt | +0.058 |
Neg logit contributions | |
da | -0.020 |
pe | -0.015 |
cr | -0.014 |
Sof | -0.013 |
an | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
anna | +0.047 |
ivering | +0.043 |
uster | +0.043 |
annah | +0.042 |
agons | +0.042 |
Neg logit contributions | |
da | -0.013 |
pe | -0.010 |
a | -0.009 |
an | -0.009 |
cr | -0.008 |
Token | Tim |
Token ID | 5045 |
Feature activation | +6.08e-03 |
Pos logit contributions | |
a | +0.006 |
da | +0.006 |
an | +0.006 |
pe | +0.005 |
the | +0.005 |
Neg logit contributions | |
anna | -0.009 |
ivering | -0.009 |
uster | -0.009 |
ivery | -0.009 |
agons | -0.009 |
Token | my |
Token ID | 1820 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
da | +0.008 |
pe | +0.007 |
a | +0.006 |
an | +0.006 |
cr | +0.006 |
Neg logit contributions | |
anna | -0.014 |
uster | -0.013 |
belt | -0.013 |
ivery | -0.013 |
ider | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
anna | +0.028 |
ivering | +0.025 |
annah | +0.025 |
uster | +0.025 |
agons | +0.025 |
Neg logit contributions | |
da | -0.012 |
pe | -0.009 |
an | -0.009 |
a | -0.009 |
Sof | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
anna | +0.105 |
ivering | +0.099 |
uster | +0.097 |
ivery | +0.096 |
ider | +0.095 |
Neg logit contributions | |
da | -0.034 |
a | -0.029 |
pe | -0.028 |
an | -0.028 |
the | -0.028 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
anna | +0.148 |
uster | +0.129 |
ivering | +0.128 |
annah | +0.128 |
ivery | +0.125 |
Neg logit contributions | |
da | -0.125 |
pe | -0.111 |
a | -0.109 |
an | -0.108 |
cr | -0.104 |
Token | decided |
Token ID | 3066 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
anna | +0.006 |
ivering | +0.005 |
uster | +0.005 |
annah | +0.005 |
agons | +0.005 |
Neg logit contributions | |
da | -0.004 |
pe | -0.003 |
an | -0.003 |
a | -0.003 |
Sof | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -7.93e-03 |
Pos logit contributions | |
da | +0.004 |
pe | +0.002 |
cr | +0.002 |
Sof | +0.002 |
an | +0.002 |
Neg logit contributions | |
anna | -0.018 |
annah | -0.017 |
belt | -0.016 |
uster | -0.016 |
ivering | -0.016 |
Token | go |
Token ID | 467 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
anna | +0.018 |
ivering | +0.016 |
uster | +0.016 |
annah | +0.016 |
belt | +0.016 |
Neg logit contributions | |
da | -0.010 |
pe | -0.009 |
a | -0.009 |
an | -0.009 |
are | -0.008 |
Token | back |
Token ID | 736 |
Feature activation | +5.70e-03 |
Pos logit contributions | |
anna | +0.056 |
ivering | +0.051 |
uster | +0.051 |
annah | +0.051 |
ivery | +0.050 |
Neg logit contributions | |
da | -0.022 |
pe | -0.019 |
a | -0.018 |
an | -0.018 |
cr | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
anna | +0.023 |
ittens | +0.022 |
agons | +0.021 |
ivering | +0.021 |
ivery | +0.021 |
Neg logit contributions | |
da | -0.004 |
ho | -0.002 |
pe | -0.002 |
Sof | -0.002 |
cr | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
da | +0.023 |
pe | +0.020 |
an | +0.020 |
a | +0.020 |
Sof | +0.019 |
Neg logit contributions | |
anna | -0.029 |
ivering | -0.025 |
uster | -0.025 |
annah | -0.025 |
agons | -0.025 |
Token | fish |
Token ID | 5916 |
Feature activation | +6.05e-04 |
Pos logit contributions | |
anna | +0.039 |
ivering | +0.035 |
uster | +0.034 |
annah | +0.034 |
agons | +0.034 |
Neg logit contributions | |
da | -0.035 |
an | -0.032 |
pe | -0.031 |
a | -0.031 |
Sof | -0.031 |
Token | y |
Token ID | 88 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
da | +0.001 |
Sof | +0.001 |
an | +0.001 |
pe | +0.001 |
a | +0.001 |
Neg logit contributions | |
anna | -0.001 |
ivering | -0.001 |
agons | -0.001 |
ivery | -0.001 |
ittens | -0.001 |
Token | named |
Token ID | 3706 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
anna | +0.068 |
uster | +0.063 |
annah | +0.062 |
ivery | +0.062 |
amas | +0.061 |
Neg logit contributions | |
da | -0.028 |
pe | -0.023 |
a | -0.022 |
an | -0.020 |
cr | -0.020 |
Token | Bub |
Token ID | 19645 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
anna | +0.068 |
ivering | +0.059 |
uster | +0.059 |
annah | +0.058 |
agons | +0.058 |
Neg logit contributions | |
da | -0.065 |
pe | -0.058 |
a | -0.057 |
an | -0.057 |
cr | -0.055 |
Token | bles |
Token ID | 7689 |
Feature activation | -4.79e-03 |
Pos logit contributions | |
anna | +0.109 |
belt | +0.090 |
annah | +0.090 |
uster | +0.090 |
ivering | +0.090 |
Neg logit contributions | |
da | -0.152 |
pe | -0.138 |
a | -0.135 |
an | -0.134 |
cr | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
anna | +0.010 |
ivering | +0.009 |
agons | +0.009 |
ittens | +0.009 |
ascal | +0.009 |
Neg logit contributions | |
da | -0.006 |
Sof | -0.005 |
conf | -0.005 |
an | -0.005 |
pe | -0.005 |
Token | Bub |
Token ID | 19645 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
anna | +0.074 |
ivering | +0.063 |
annah | +0.063 |
uster | +0.063 |
belt | +0.062 |
Neg logit contributions | |
da | -0.068 |
pe | -0.061 |
a | -0.061 |
an | -0.060 |
cr | -0.058 |
Token | bles |
Token ID | 7689 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
anna | +0.112 |
ivering | +0.093 |
annah | +0.093 |
uster | +0.092 |
belt | +0.092 |
Neg logit contributions | |
da | -0.155 |
pe | -0.141 |
a | -0.137 |
an | -0.137 |
cr | -0.134 |
Token | lived |
Token ID | 5615 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
anna | +0.028 |
agons | +0.024 |
ivering | +0.024 |
annah | +0.023 |
ivery | +0.023 |
Neg logit contributions | |
da | -0.022 |
Sof | -0.020 |
an | -0.019 |
pe | -0.018 |
a | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
anna | +0.004 |
ivering | +0.004 |
ivery | +0.004 |
uster | +0.004 |
annah | +0.004 |
Neg logit contributions | |
da | -0.000 |
a | -0.000 |
an | -0.000 |
to | -0.000 |
pe | +0.000 |
Token | create |
Token ID | 2251 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
anna | +0.065 |
amas | +0.061 |
belt | +0.061 |
uster | +0.060 |
ittens | +0.060 |
Neg logit contributions | |
a | -0.028 |
an | -0.026 |
pe | -0.026 |
the | -0.025 |
da | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -8.89e-04 |
Pos logit contributions | |
anna | +0.057 |
ivering | +0.052 |
uster | +0.051 |
annah | +0.051 |
agons | +0.051 |
Neg logit contributions | |
da | -0.020 |
pe | -0.016 |
a | -0.016 |
an | -0.015 |
cr | -0.014 |
Token | safe |
Token ID | 3338 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
anna | +0.002 |
annah | +0.002 |
uster | +0.002 |
ivering | +0.002 |
ivery | +0.002 |
Neg logit contributions | |
da | -0.001 |
pe | -0.001 |
a | -0.001 |
an | -0.001 |
cr | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
anna | +0.089 |
ittens | +0.080 |
ivery | +0.078 |
annah | +0.078 |
ivering | +0.077 |
Neg logit contributions | |
da | -0.063 |
a | -0.060 |
pe | -0.057 |
an | -0.057 |
the | -0.057 |
Token | comfortable |
Token ID | 6792 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
anna | +0.077 |
uster | +0.070 |
ivering | +0.070 |
ittens | +0.069 |
agons | +0.069 |
Neg logit contributions | |
da | -0.039 |
a | -0.037 |
an | -0.036 |
pe | -0.035 |
the | -0.034 |
Token | home |
Token ID | 1363 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
anna | +0.162 |
ivery | +0.155 |
ittens | +0.152 |
ivering | +0.148 |
annah | +0.145 |
Neg logit contributions | |
a | -0.095 |
da | -0.095 |
to | -0.093 |
the | -0.093 |
pe | -0.089 |
Token | for |
Token ID | 329 |
Feature activation | -4.88e-03 |
Pos logit contributions | |
anna | +0.093 |
ivering | +0.087 |
uster | +0.087 |
ivery | +0.086 |
agons | +0.085 |
Neg logit contributions | |
da | -0.018 |
a | -0.018 |
an | -0.016 |
the | -0.014 |
pe | -0.014 |
Token | all |
Token ID | 477 |
Feature activation | -6.68e-03 |
Pos logit contributions | |
anna | +0.013 |
ivering | +0.012 |
uster | +0.012 |
ivery | +0.012 |
belt | +0.012 |
Neg logit contributions | |
a | -0.005 |
da | -0.005 |
an | -0.005 |
the | -0.004 |
pe | -0.004 |
Token | living |
Token ID | 2877 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
anna | +0.019 |
ivering | +0.017 |
uster | +0.017 |
annah | +0.017 |
ivery | +0.017 |
Neg logit contributions | |
da | -0.005 |
a | -0.004 |
pe | -0.004 |
an | -0.004 |
cr | -0.003 |
Token | creatures |
Token ID | 8109 |
Feature activation | -3.87e-03 |
Pos logit contributions | |
anna | +0.102 |
ittens | +0.100 |
ivering | +0.097 |
ivery | +0.097 |
uster | +0.095 |
Neg logit contributions | |
a | -0.037 |
an | -0.034 |
the | -0.034 |
to | -0.033 |
da | -0.029 |
Token | stupid |
Token ID | 8531 |
Feature activation | -4.91e-03 |
Pos logit contributions | |
da | +0.016 |
Sof | +0.014 |
ho | +0.014 |
cr | +0.013 |
pe | +0.013 |
Neg logit contributions | |
anna | -0.029 |
ivering | -0.027 |
annah | -0.025 |
uster | -0.025 |
ivery | -0.025 |
Token | trying |
Token ID | 2111 |
Feature activation | +1.06e-03 |
Pos logit contributions | |
anna | +0.015 |
ivering | +0.013 |
annah | +0.013 |
ivery | +0.013 |
agons | +0.013 |
Neg logit contributions | |
da | -0.003 |
a | -0.003 |
an | -0.002 |
pe | -0.002 |
cr | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
da | +0.001 |
ho | +0.001 |
Sof | +0.001 |
pe | +0.001 |
aw | +0.001 |
Neg logit contributions | |
anna | -0.003 |
annah | -0.003 |
ivering | -0.002 |
uster | -0.002 |
agons | -0.002 |
Token | play |
Token ID | 711 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
anna | +0.024 |
belt | +0.022 |
uster | +0.022 |
annah | +0.021 |
ivering | +0.021 |
Neg logit contributions | |
da | -0.013 |
a | -0.012 |
pe | -0.012 |
an | -0.012 |
the | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
anna | +0.100 |
uster | +0.091 |
ivering | +0.090 |
annah | +0.090 |
agons | +0.090 |
Neg logit contributions | |
da | -0.030 |
a | -0.025 |
an | -0.024 |
pe | -0.023 |
cr | -0.021 |
Token | fl |
Token ID | 781 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
da | +0.019 |
pe | +0.015 |
an | +0.014 |
a | +0.014 |
Sof | +0.013 |
Neg logit contributions | |
anna | -0.054 |
ivering | -0.049 |
uster | -0.049 |
annah | -0.049 |
agons | -0.049 |
Token | ute |
Token ID | 1133 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
anna | +0.115 |
ivering | +0.096 |
annah | +0.096 |
uster | +0.094 |
agons | +0.094 |
Neg logit contributions | |
da | -0.155 |
pe | -0.139 |
a | -0.138 |
an | -0.137 |
cr | -0.134 |
Token | like |
Token ID | 588 |
Feature activation | +9.23e-03 |
Pos logit contributions | |
anna | +0.082 |
uster | +0.075 |
annah | +0.073 |
agons | +0.073 |
ivering | +0.073 |
Neg logit contributions | |
da | -0.027 |
a | -0.025 |
an | -0.023 |
pe | -0.022 |
high | -0.021 |
Token | that |
Token ID | 326 |
Feature activation | -2.60e-03 |
Pos logit contributions | |
da | +0.011 |
pe | +0.009 |
an | +0.009 |
a | +0.009 |
Sof | +0.009 |
Neg logit contributions | |
anna | -0.021 |
annah | -0.019 |
ivering | -0.019 |
uster | -0.019 |
agons | -0.019 |
Token | ." |
Token ID | 526 |
Feature activation | +9.66e-03 |
Pos logit contributions | |
anna | +0.006 |
uster | +0.006 |
agons | +0.006 |
annah | +0.006 |
ivering | +0.006 |
Neg logit contributions | |
da | -0.003 |
a | -0.003 |
an | -0.002 |
pe | -0.002 |
the | -0.002 |
Token | Mia |
Token ID | 32189 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
da | +0.011 |
pe | +0.008 |
an | +0.008 |
a | +0.008 |
cr | +0.008 |
Neg logit contributions | |
anna | -0.024 |
annah | -0.021 |
amas | -0.021 |
ivering | -0.021 |
ital | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
da | +0.008 |
aw | +0.007 |
pe | +0.006 |
cr | +0.006 |
ho | +0.006 |
Neg logit contributions | |
anna | -0.017 |
annah | -0.015 |
belt | -0.014 |
ital | -0.014 |
amas | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
anna | +0.009 |
uster | +0.008 |
agons | +0.008 |
ivering | +0.008 |
annah | +0.008 |
Neg logit contributions | |
da | -0.002 |
pe | -0.002 |
a | -0.002 |
an | -0.002 |
cr | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
da | +0.015 |
pe | +0.012 |
a | +0.012 |
an | +0.012 |
cr | +0.010 |
Neg logit contributions | |
anna | -0.043 |
ivering | -0.039 |
uster | -0.039 |
annah | -0.039 |
agons | -0.038 |
Token | blue |
Token ID | 4171 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
da | +0.028 |
pe | +0.023 |
an | +0.023 |
a | +0.023 |
Sof | +0.022 |
Neg logit contributions | |
anna | -0.057 |
ivering | -0.051 |
uster | -0.051 |
annah | -0.051 |
belt | -0.050 |
Token | l |
Token ID | 300 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
anna | +0.028 |
ivering | +0.025 |
annah | +0.025 |
agons | +0.024 |
uster | +0.024 |
Neg logit contributions | |
da | -0.018 |
pe | -0.016 |
a | -0.016 |
an | -0.015 |
cr | -0.015 |
Token | oll |
Token ID | 692 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
anna | +0.019 |
ivering | +0.016 |
annah | +0.016 |
agons | +0.016 |
ivery | +0.016 |
Neg logit contributions | |
da | -0.023 |
pe | -0.021 |
a | -0.021 |
an | -0.021 |
cr | -0.020 |
Token | ipop |
Token ID | 42800 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
anna | +0.167 |
ivery | +0.157 |
ivering | +0.156 |
ital | +0.149 |
amas | +0.148 |
Neg logit contributions | |
da | -0.172 |
pe | -0.159 |
cr | -0.155 |
a | -0.151 |
an | -0.144 |
Token | ! |
Token ID | 0 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
anna | +0.060 |
ivering | +0.054 |
uster | +0.054 |
annah | +0.054 |
belt | +0.054 |
Neg logit contributions | |
da | -0.015 |
pe | -0.011 |
an | -0.011 |
a | -0.010 |
Sof | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
da | +0.011 |
pe | +0.009 |
a | +0.009 |
an | +0.009 |
Sof | +0.008 |
Neg logit contributions | |
anna | -0.025 |
ivering | -0.023 |
uster | -0.022 |
annah | -0.022 |
agons | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
da | +0.004 |
pe | +0.003 |
cr | +0.003 |
an | +0.003 |
Sof | +0.003 |
Neg logit contributions | |
anna | -0.007 |
annah | -0.006 |
ivering | -0.006 |
ittens | -0.006 |
uster | -0.006 |
Token | M |
Token ID | 44 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
anna | +0.030 |
ivering | +0.027 |
annah | +0.026 |
ivery | +0.026 |
uster | +0.026 |
Neg logit contributions | |
da | -0.013 |
pe | -0.011 |
an | -0.010 |
a | -0.010 |
cr | -0.010 |