Token | with |
Token ID | 351 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
blonde | +0.107 |
oph | +0.095 |
blush | +0.093 |
Her | +0.089 |
uct | +0.088 |
Neg logit contributions | |
boat | -0.080 |
boats | -0.076 |
bridge | -0.075 |
boat | -0.075 |
sailors | -0.073 |
Token | a |
Token ID | 257 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
blonde | +0.043 |
oph | +0.040 |
uct | +0.037 |
blush | +0.037 |
Her | +0.036 |
Neg logit contributions | |
sailors | -0.041 |
boats | -0.041 |
boat | -0.041 |
sail | -0.038 |
sharks | -0.038 |
Token | big |
Token ID | 1263 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
blonde | +0.079 |
oph | +0.076 |
uct | +0.076 |
Her | +0.070 |
omm | +0.068 |
Neg logit contributions | |
boat | -0.066 |
sail | -0.062 |
bridge | -0.059 |
raft | -0.057 |
sailors | -0.057 |
Token | smile |
Token ID | 8212 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
blonde | +0.059 |
oph | +0.053 |
uct | +0.052 |
Her | +0.051 |
blush | +0.050 |
Neg logit contributions | |
boat | -0.059 |
sail | -0.055 |
sailors | -0.054 |
bridge | -0.054 |
boats | -0.053 |
Token | on |
Token ID | 319 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
blonde | +0.069 |
oph | +0.061 |
uct | +0.060 |
blush | +0.059 |
fru | +0.059 |
Neg logit contributions | |
boat | -0.037 |
sailors | -0.037 |
boat | -0.036 |
boats | -0.034 |
ug | -0.034 |
Token | her |
Token ID | 607 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
blonde | +0.082 |
oph | +0.070 |
uct | +0.063 |
blush | +0.060 |
fru | +0.059 |
Neg logit contributions | |
boat | -0.150 |
sail | -0.149 |
boats | -0.148 |
sailors | -0.147 |
aro | -0.142 |
Token | face |
Token ID | 1986 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
blonde | +0.174 |
oph | +0.171 |
uct | +0.157 |
Could | +0.146 |
blush | +0.139 |
Neg logit contributions | |
boat | -0.174 |
sailors | -0.170 |
sail | -0.167 |
boats | -0.164 |
ship | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
blonde | +0.143 |
oph | +0.134 |
uct | +0.130 |
fru | +0.125 |
blush | +0.124 |
Neg logit contributions | |
boat | -0.064 |
sailors | -0.062 |
boats | -0.059 |
sail | -0.058 |
boat | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
blonde | +0.058 |
oph | +0.055 |
fru | +0.052 |
pron | +0.052 |
blush | +0.052 |
Neg logit contributions | |
sail | -0.040 |
sailors | -0.040 |
boats | -0.040 |
ug | -0.039 |
ull | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
blonde | +0.053 |
blush | +0.046 |
brist | +0.045 |
oph | +0.043 |
fru | +0.042 |
Neg logit contributions | |
sailors | -0.047 |
aro | -0.045 |
boat | -0.044 |
boats | -0.044 |
ug | -0.044 |
Token | After |
Token ID | 3260 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
blonde | +0.063 |
blush | +0.054 |
oph | +0.051 |
brist | +0.051 |
fru | +0.051 |
Neg logit contributions | |
sailors | -0.072 |
aro | -0.070 |
boats | -0.068 |
ug | -0.068 |
captains | -0.067 |
Token | with |
Token ID | 351 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
blonde | +0.132 |
oph | +0.120 |
fru | +0.111 |
blush | +0.111 |
uct | +0.109 |
Neg logit contributions | |
boat | -0.062 |
boat | -0.060 |
ug | -0.059 |
boats | -0.058 |
sailors | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
oph | +0.043 |
blonde | +0.043 |
uct | +0.040 |
anna | +0.037 |
Her | +0.037 |
Neg logit contributions | |
boats | -0.039 |
boat | -0.039 |
sailors | -0.038 |
sail | -0.036 |
sharks | -0.036 |
Token | cheerful |
Token ID | 37999 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
uct | +0.098 |
oph | +0.096 |
blonde | +0.085 |
omm | +0.083 |
meanings | +0.081 |
Neg logit contributions | |
boat | -0.067 |
sail | -0.062 |
fish | -0.057 |
crane | -0.055 |
boom | -0.053 |
Token | smile |
Token ID | 8212 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
uct | +0.114 |
oph | +0.104 |
she | +0.094 |
omm | +0.092 |
blonde | +0.091 |
Neg logit contributions | |
boat | -0.093 |
sail | -0.091 |
fish | -0.084 |
boom | -0.081 |
ull | -0.079 |
Token | on |
Token ID | 319 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
blonde | +0.067 |
oph | +0.060 |
uct | +0.057 |
brist | +0.057 |
fru | +0.057 |
Neg logit contributions | |
sailors | -0.033 |
boat | -0.032 |
boat | -0.032 |
aro | -0.030 |
ug | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
blonde | +0.082 |
oph | +0.070 |
uct | +0.064 |
Could | +0.063 |
pad | +0.062 |
Neg logit contributions | |
boat | -0.142 |
sail | -0.140 |
boats | -0.139 |
sailors | -0.138 |
aro | -0.136 |
Token | face |
Token ID | 1986 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
blonde | +0.180 |
oph | +0.176 |
uct | +0.160 |
Could | +0.156 |
aman | +0.149 |
Neg logit contributions | |
sailors | -0.148 |
boat | -0.147 |
sail | -0.140 |
boats | -0.133 |
ship | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
blonde | +0.143 |
oph | +0.132 |
fru | +0.125 |
uct | +0.125 |
brist | +0.124 |
Neg logit contributions | |
boat | -0.053 |
sailors | -0.053 |
aro | -0.049 |
boats | -0.049 |
boat | -0.047 |
Token | She |
Token ID | 1375 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
ited | +0.066 |
blonde | +0.061 |
fru | +0.058 |
uct | +0.057 |
oph | +0.057 |
Neg logit contributions | |
boats | -0.052 |
they | -0.050 |
They | -0.050 |
bridge | -0.047 |
Fin | -0.046 |
Token | knew |
Token ID | 2993 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
blonde | +0.129 |
amas | +0.104 |
oph | +0.103 |
blond | +0.103 |
uct | +0.103 |
Neg logit contributions | |
boat | -0.085 |
boats | -0.081 |
sailors | -0.079 |
sailed | -0.077 |
fish | -0.075 |
Token | it |
Token ID | 340 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
blonde | +0.085 |
brist | +0.072 |
blush | +0.071 |
oph | +0.069 |
amas | +0.068 |
Neg logit contributions | |
sailors | -0.061 |
aro | -0.060 |
boat | -0.059 |
boats | -0.058 |
sharks | -0.057 |
Token | got |
Token ID | 1392 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
blonde | +0.092 |
oph | +0.092 |
omm | +0.085 |
osa | +0.079 |
fru | +0.078 |
Neg logit contributions | |
boat | -0.033 |
aro | -0.031 |
boats | -0.029 |
boom | -0.029 |
sail | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
sailors | +0.020 |
boats | +0.020 |
boat | +0.020 |
sharks | +0.019 |
aro | +0.019 |
Neg logit contributions | |
blonde | -0.029 |
oph | -0.027 |
blush | -0.025 |
brist | -0.024 |
pron | -0.024 |
Token | big |
Token ID | 1263 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
blonde | +0.067 |
Her | +0.059 |
uct | +0.059 |
oph | +0.058 |
blush | +0.057 |
Neg logit contributions | |
boat | -0.055 |
sail | -0.051 |
bridge | -0.049 |
raft | -0.049 |
crane | -0.048 |
Token | stain |
Token ID | 18746 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
blonde | +0.040 |
Her | +0.033 |
oph | +0.033 |
blush | +0.033 |
uct | +0.032 |
Neg logit contributions | |
boat | -0.044 |
sailors | -0.042 |
boats | -0.041 |
sail | -0.041 |
bridge | -0.041 |
Token | on |
Token ID | 319 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
blonde | +0.046 |
oph | +0.040 |
blush | +0.039 |
Her | +0.038 |
fru | +0.038 |
Neg logit contributions | |
boat | -0.025 |
sailors | -0.025 |
boat | -0.023 |
ug | -0.023 |
boats | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
blonde | +0.088 |
aj | +0.076 |
oph | +0.073 |
anna | +0.072 |
uct | +0.071 |
Neg logit contributions | |
boat | -0.085 |
sail | -0.081 |
boats | -0.081 |
boom | -0.077 |
bridge | -0.077 |
Token | dress |
Token ID | 6576 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
blonde | +0.175 |
oph | +0.162 |
uct | +0.150 |
fru | +0.147 |
Could | +0.142 |
Neg logit contributions | |
boat | -0.165 |
ship | -0.148 |
boats | -0.147 |
sail | -0.147 |
sailors | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
blonde | +0.120 |
fru | +0.104 |
blond | +0.102 |
oph | +0.102 |
blush | +0.100 |
Neg logit contributions | |
boat | -0.040 |
boat | -0.039 |
bridge | -0.033 |
boats | -0.033 |
ug | -0.033 |
Token | She |
Token ID | 1375 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ited | +0.086 |
blonde | +0.086 |
iously | +0.082 |
oph | +0.080 |
brow | +0.079 |
Neg logit contributions | |
Fin | -0.039 |
they | -0.037 |
boat | -0.035 |
sail | -0.033 |
crane | -0.033 |
Token | started |
Token ID | 2067 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
blonde | +0.116 |
oph | +0.107 |
aman | +0.099 |
omm | +0.097 |
Deal | +0.094 |
Neg logit contributions | |
boat | -0.078 |
boats | -0.073 |
sailors | -0.071 |
ship | -0.071 |
sailed | -0.071 |
Token | crying |
Token ID | 13774 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
oph | +0.098 |
blonde | +0.096 |
uct | +0.087 |
fru | +0.084 |
omm | +0.083 |
Neg logit contributions | |
boats | -0.056 |
boat | -0.053 |
sail | -0.051 |
bridge | -0.050 |
boom | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
oph | +0.060 |
omm | +0.058 |
uct | +0.057 |
blonde | +0.056 |
amas | +0.056 |
Neg logit contributions | |
sailors | -0.044 |
boat | -0.042 |
boats | -0.042 |
sail | -0.042 |
aro | -0.041 |
Token | shiny |
Token ID | 22441 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
blonde | +0.044 |
uct | +0.044 |
oph | +0.043 |
Her | +0.041 |
blush | +0.040 |
Neg logit contributions | |
boat | -0.039 |
sail | -0.037 |
sailors | -0.037 |
bridge | -0.036 |
ship | -0.035 |
Token | h |
Token ID | 289 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
uct | +0.052 |
blonde | +0.051 |
oph | +0.050 |
Her | +0.046 |
blush | +0.045 |
Neg logit contributions | |
boat | -0.049 |
sail | -0.047 |
bridge | -0.044 |
ship | -0.044 |
crane | -0.043 |
Token | alo |
Token ID | 7335 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
blonde | +0.050 |
blush | +0.042 |
fru | +0.041 |
uct | +0.041 |
oph | +0.041 |
Neg logit contributions | |
aro | -0.060 |
ug | -0.058 |
sailors | -0.058 |
boat | -0.057 |
boat | -0.056 |
Token | on |
Token ID | 319 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
blonde | +0.036 |
oph | +0.033 |
brist | +0.031 |
blush | +0.031 |
fru | +0.031 |
Neg logit contributions | |
aro | -0.018 |
boat | -0.018 |
sailors | -0.018 |
boat | -0.017 |
ug | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
blonde | +0.034 |
aj | +0.030 |
oph | +0.030 |
uct | +0.028 |
amas | +0.028 |
Neg logit contributions | |
sail | -0.052 |
boat | -0.052 |
boats | -0.050 |
sailors | -0.050 |
boom | -0.050 |
Token | head |
Token ID | 1182 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
blonde | +0.175 |
oph | +0.171 |
uct | +0.162 |
fru | +0.149 |
blush | +0.144 |
Neg logit contributions | |
boat | -0.151 |
sailors | -0.144 |
ship | -0.140 |
sail | -0.138 |
boats | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
blonde | +0.062 |
oph | +0.058 |
uct | +0.055 |
fru | +0.055 |
brist | +0.055 |
Neg logit contributions | |
boat | -0.031 |
boat | -0.031 |
sailors | -0.030 |
aro | -0.030 |
sail | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
blonde | +0.063 |
pron | +0.058 |
brist | +0.057 |
brow | +0.057 |
eyel | +0.056 |
Neg logit contributions | |
Fin | -0.028 |
boats | -0.027 |
they | -0.027 |
boat | -0.026 |
bridge | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
blonde | +0.035 |
blush | +0.031 |
brist | +0.030 |
brow | +0.028 |
oph | +0.028 |
Neg logit contributions | |
sailors | -0.024 |
boat | -0.024 |
aro | -0.023 |
boats | -0.023 |
ug | -0.023 |
Token | " |
Token ID | 1 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
blonde | +0.068 |
blush | +0.061 |
brow | +0.059 |
omm | +0.058 |
brist | +0.058 |
Neg logit contributions | |
boat | -0.036 |
boats | -0.034 |
sailors | -0.034 |
bridge | -0.034 |
boat | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
blonde | +0.012 |
blush | +0.010 |
brist | +0.010 |
oph | +0.010 |
Her | +0.009 |
Neg logit contributions | |
sailors | -0.013 |
boat | -0.012 |
aro | -0.012 |
boats | -0.012 |
sharks | -0.012 |
Token | She |
Token ID | 3347 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
blonde | +0.038 |
blush | +0.033 |
brist | +0.032 |
oph | +0.031 |
fru | +0.031 |
Neg logit contributions | |
sailors | -0.031 |
boat | -0.030 |
boats | -0.029 |
aro | -0.029 |
captains | -0.029 |
Token | put |
Token ID | 1234 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
blonde | +0.069 |
Her | +0.057 |
amas | +0.056 |
oph | +0.055 |
omm | +0.055 |
Neg logit contributions | |
boat | -0.058 |
sailors | -0.057 |
sailed | -0.056 |
ship | -0.055 |
boats | -0.054 |
Token | Anna |
Token ID | 11735 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
blonde | +0.040 |
oph | +0.036 |
blush | +0.034 |
brist | +0.034 |
Her | +0.034 |
Neg logit contributions | |
sailors | -0.029 |
boat | -0.028 |
boats | -0.028 |
aro | -0.028 |
boats | -0.027 |
Token | on |
Token ID | 319 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
blonde | +0.067 |
oph | +0.061 |
brist | +0.058 |
blush | +0.058 |
fru | +0.056 |
Neg logit contributions | |
sailors | -0.042 |
boat | -0.042 |
boats | -0.040 |
aro | -0.039 |
boat | -0.039 |
Token | her |
Token ID | 607 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
blonde | +0.087 |
uct | +0.085 |
oph | +0.084 |
elt | +0.079 |
fru | +0.077 |
Neg logit contributions | |
boat | -0.066 |
boats | -0.065 |
sail | -0.061 |
sailors | -0.060 |
sharks | -0.059 |
Token | bed |
Token ID | 3996 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
oph | +0.178 |
blonde | +0.140 |
uct | +0.138 |
aman | +0.133 |
elt | +0.130 |
Neg logit contributions | |
boat | -0.158 |
boats | -0.138 |
sail | -0.137 |
bridge | -0.136 |
sailors | -0.132 |
Token | and |
Token ID | 290 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
blonde | +0.095 |
blush | +0.084 |
oph | +0.083 |
brist | +0.081 |
uct | +0.079 |
Neg logit contributions | |
boat | -0.061 |
boat | -0.058 |
sailors | -0.057 |
ship | -0.055 |
boats | -0.055 |
Token | picked |
Token ID | 6497 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
blonde | +0.049 |
omm | +0.040 |
oph | +0.040 |
brist | +0.039 |
Her | +0.039 |
Neg logit contributions | |
boat | -0.053 |
sailors | -0.053 |
boats | -0.051 |
sail | -0.050 |
ship | -0.049 |
Token | up |
Token ID | 510 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
blonde | +0.066 |
uct | +0.054 |
oph | +0.054 |
brist | +0.053 |
blush | +0.053 |
Neg logit contributions | |
sailors | -0.063 |
boat | -0.062 |
boats | -0.062 |
sharks | -0.060 |
aro | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
blonde | +0.030 |
oph | +0.026 |
uct | +0.025 |
brist | +0.025 |
blush | +0.025 |
Neg logit contributions | |
sailors | -0.042 |
boats | -0.041 |
boat | -0.041 |
sharks | -0.041 |
aro | -0.040 |
Token | Jane |
Token ID | 41083 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
blonde | +0.048 |
brist | +0.043 |
blush | +0.042 |
brow | +0.040 |
fru | +0.038 |
Neg logit contributions | |
sailors | -0.044 |
ull | -0.043 |
boat | -0.043 |
bridge | -0.042 |
boats | -0.042 |
Token | went |
Token ID | 1816 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
blonde | +0.049 |
blush | +0.043 |
brist | +0.042 |
oph | +0.041 |
fru | +0.039 |
Neg logit contributions | |
boat | -0.048 |
boats | -0.046 |
sailors | -0.045 |
ship | -0.044 |
ug | -0.043 |
Token | home |
Token ID | 1363 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
blonde | +0.037 |
brist | +0.031 |
blush | +0.030 |
oph | +0.030 |
fru | +0.029 |
Neg logit contributions | |
sailors | -0.040 |
boat | -0.039 |
boats | -0.039 |
aro | -0.037 |
captains | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
blonde | +0.058 |
blush | +0.051 |
oph | +0.050 |
brist | +0.049 |
fru | +0.047 |
Neg logit contributions | |
sailors | -0.039 |
boat | -0.037 |
boats | -0.036 |
bridge | -0.034 |
sail | -0.034 |
Token | brushed |
Token ID | 31782 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
blonde | +0.072 |
omm | +0.067 |
brist | +0.065 |
Deal | +0.064 |
oph | +0.062 |
Neg logit contributions | |
boat | -0.051 |
sailed | -0.049 |
ship | -0.049 |
boats | -0.048 |
sail | -0.047 |
Token | her |
Token ID | 607 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
blonde | +0.088 |
oph | +0.080 |
pron | +0.077 |
uct | +0.076 |
fru | +0.072 |
Neg logit contributions | |
boats | -0.095 |
ug | -0.095 |
sailors | -0.094 |
boat | -0.093 |
aro | -0.091 |
Token | hair |
Token ID | 4190 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
oph | +0.165 |
blonde | +0.145 |
aman | +0.134 |
uct | +0.128 |
ited | +0.125 |
Neg logit contributions | |
boat | -0.135 |
boats | -0.135 |
bridge | -0.130 |
sail | -0.122 |
cross | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
blonde | +0.153 |
oph | +0.144 |
fru | +0.132 |
uct | +0.130 |
omm | +0.129 |
Neg logit contributions | |
boat | -0.069 |
boat | -0.064 |
boats | -0.063 |
sail | -0.060 |
ug | -0.059 |
Token | But |
Token ID | 887 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
pron | +0.083 |
ppa | +0.074 |
oph | +0.074 |
cavity | +0.072 |
fru | +0.072 |
Neg logit contributions | |
bridge | -0.070 |
nation | -0.067 |
sail | -0.065 |
drivers | -0.065 |
boats | -0.065 |
Token | something |
Token ID | 1223 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
blonde | +0.080 |
oph | +0.073 |
fru | +0.071 |
brist | +0.070 |
amas | +0.069 |
Neg logit contributions | |
boat | -0.045 |
aro | -0.043 |
sailors | -0.042 |
bridge | -0.041 |
boats | -0.041 |
Token | tasted |
Token ID | 29187 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
blonde | +0.041 |
oph | +0.035 |
amas | +0.034 |
blush | +0.034 |
brist | +0.034 |
Neg logit contributions | |
boat | -0.033 |
aro | -0.032 |
boats | -0.031 |
bridge | -0.030 |
boat | -0.030 |
Token | She |
Token ID | 1375 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
pron | +0.049 |
oph | +0.048 |
blonde | +0.047 |
blush | +0.046 |
ited | +0.045 |
Neg logit contributions | |
crane | -0.048 |
Fin | -0.047 |
boats | -0.046 |
bridge | -0.046 |
sail | -0.045 |
Token | gently |
Token ID | 15165 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
blonde | +0.092 |
blush | +0.077 |
oph | +0.076 |
Her | +0.075 |
omm | +0.073 |
Neg logit contributions | |
boat | -0.086 |
boats | -0.082 |
sailors | -0.080 |
ship | -0.076 |
raft | -0.076 |
Token | scrub |
Token ID | 27268 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
blonde | +0.095 |
omm | +0.086 |
oph | +0.084 |
uct | +0.079 |
meanings | +0.078 |
Neg logit contributions | |
boat | -0.098 |
boats | -0.094 |
sail | -0.092 |
sailors | -0.089 |
raft | -0.089 |
Token | bed |
Token ID | 3077 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
blonde | +0.178 |
oph | +0.156 |
blush | +0.145 |
Her | +0.144 |
fru | +0.142 |
Neg logit contributions | |
ug | -0.142 |
sailors | -0.136 |
boats | -0.133 |
aro | -0.132 |
boat | -0.129 |
Token | and |
Token ID | 290 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
blonde | +0.175 |
oph | +0.161 |
uct | +0.151 |
blush | +0.149 |
Her | +0.147 |
Neg logit contributions | |
boats | -0.103 |
sailors | -0.101 |
boat | -0.101 |
ug | -0.099 |
aro | -0.095 |
Token | scrub |
Token ID | 27268 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
blonde | +0.090 |
oph | +0.082 |
omm | +0.079 |
Her | +0.078 |
uct | +0.071 |
Neg logit contributions | |
sailors | -0.087 |
boat | -0.086 |
boats | -0.084 |
sail | -0.082 |
ug | -0.080 |
Token | bed |
Token ID | 3077 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
blonde | +0.176 |
oph | +0.157 |
blush | +0.146 |
Her | +0.144 |
uct | +0.140 |
Neg logit contributions | |
ug | -0.151 |
sailors | -0.145 |
boats | -0.140 |
aro | -0.139 |
boat | -0.136 |
Token | until |
Token ID | 1566 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
blonde | +0.166 |
oph | +0.152 |
uct | +0.141 |
blush | +0.141 |
Her | +0.138 |
Neg logit contributions | |
sailors | -0.112 |
boats | -0.112 |
ug | -0.112 |
boat | -0.110 |
aro | -0.107 |
Token | the |
Token ID | 262 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
blonde | +0.060 |
oph | +0.053 |
brist | +0.050 |
blush | +0.050 |
uct | +0.049 |
Neg logit contributions | |
boat | -0.044 |
boats | -0.041 |
sail | -0.040 |
aro | -0.039 |
sailors | -0.038 |
Token | penny |
Token ID | 26369 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
blonde | +0.052 |
oph | +0.048 |
Her | +0.047 |
blush | +0.046 |
uct | +0.044 |
Neg logit contributions | |
boat | -0.048 |
sail | -0.044 |
boats | -0.044 |
sailors | -0.043 |
raft | -0.043 |
Token | was |
Token ID | 373 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
blonde | +0.054 |
blush | +0.045 |
Her | +0.045 |
oph | +0.044 |
brist | +0.043 |
Neg logit contributions | |
boat | -0.052 |
boat | -0.050 |
boats | -0.048 |
sailors | -0.047 |
aro | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
blonde | +0.032 |
oph | +0.029 |
blush | +0.028 |
brist | +0.028 |
fru | +0.028 |
Neg logit contributions | |
sailors | -0.019 |
boat | -0.019 |
boat | -0.018 |
boats | -0.018 |
aro | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
oph | +0.067 |
omm | +0.062 |
uct | +0.061 |
amas | +0.058 |
blonde | +0.058 |
Neg logit contributions | |
boat | -0.049 |
sailors | -0.049 |
boats | -0.049 |
sail | -0.047 |
ship | -0.044 |
Token | she |
Token ID | 673 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
oph | +0.060 |
amas | +0.060 |
blonde | +0.058 |
uct | +0.058 |
omm | +0.055 |
Neg logit contributions | |
sailors | -0.072 |
boat | -0.072 |
boats | -0.071 |
sail | -0.066 |
whales | -0.066 |
Token | always |
Token ID | 1464 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
blonde | +0.068 |
oph | +0.065 |
blush | +0.061 |
uct | +0.060 |
amas | +0.059 |
Neg logit contributions | |
sailors | -0.054 |
boat | -0.054 |
boats | -0.053 |
sailed | -0.051 |
ship | -0.051 |
Token | brushed |
Token ID | 31782 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
blonde | +0.036 |
oph | +0.034 |
uct | +0.032 |
omm | +0.032 |
blush | +0.031 |
Neg logit contributions | |
sailors | -0.043 |
boat | -0.041 |
boat | -0.040 |
sail | -0.040 |
boats | -0.040 |
Token | her |
Token ID | 607 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
blonde | +0.090 |
oph | +0.084 |
uct | +0.080 |
pron | +0.076 |
fru | +0.073 |
Neg logit contributions | |
sailors | -0.110 |
boats | -0.108 |
ug | -0.106 |
aro | -0.105 |
boat | -0.105 |
Token | hair |
Token ID | 4190 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
oph | +0.178 |
blonde | +0.144 |
uct | +0.141 |
cake | +0.140 |
Da | +0.132 |
Neg logit contributions | |
boat | -0.151 |
boats | -0.143 |
sail | -0.136 |
sailors | -0.134 |
crew | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
blonde | +0.163 |
oph | +0.154 |
fru | +0.140 |
uct | +0.138 |
blond | +0.135 |
Neg logit contributions | |
boat | -0.089 |
boats | -0.085 |
boat | -0.083 |
ug | -0.081 |
aro | -0.079 |
Token | One |
Token ID | 1881 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
blonde | +0.050 |
pron | +0.050 |
brist | +0.049 |
oph | +0.049 |
blush | +0.048 |
Neg logit contributions | |
boats | -0.033 |
crane | -0.033 |
Fin | -0.032 |
boat | -0.031 |
sail | -0.031 |
Token | day |
Token ID | 1110 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
blonde | +0.065 |
blush | +0.058 |
brist | +0.057 |
oph | +0.056 |
Her | +0.056 |
Neg logit contributions | |
sailors | -0.034 |
boat | -0.032 |
aro | -0.031 |
boats | -0.031 |
boat | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
blonde | +0.059 |
uct | +0.054 |
blush | +0.054 |
oph | +0.054 |
brist | +0.054 |
Neg logit contributions | |
aro | -0.025 |
boat | -0.024 |
sailors | -0.024 |
boats | -0.023 |
sharks | -0.022 |
Token | had |
Token ID | 550 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
oph | +0.052 |
blonde | +0.051 |
uct | +0.048 |
omm | +0.048 |
amas | +0.046 |
Neg logit contributions | |
sailors | -0.058 |
sail | -0.053 |
captains | -0.053 |
boat | -0.053 |
boats | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
blonde | +0.034 |
uct | +0.033 |
omm | +0.033 |
brist | +0.032 |
oph | +0.032 |
Neg logit contributions | |
sailors | -0.035 |
boats | -0.034 |
boat | -0.032 |
captains | -0.031 |
sharks | -0.031 |
Token | big |
Token ID | 1263 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
uct | +0.028 |
blonde | +0.027 |
oph | +0.026 |
brist | +0.024 |
Her | +0.024 |
Neg logit contributions | |
boat | -0.028 |
boats | -0.026 |
sail | -0.025 |
sailors | -0.025 |
captains | -0.024 |
Token | smile |
Token ID | 8212 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
blonde | +0.014 |
uct | +0.013 |
oph | +0.012 |
blush | +0.012 |
Her | +0.012 |
Neg logit contributions | |
boat | -0.017 |
sailors | -0.016 |
boats | -0.016 |
ship | -0.016 |
sail | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
blonde | +0.054 |
oph | +0.049 |
uct | +0.049 |
fru | +0.048 |
brist | +0.047 |
Neg logit contributions | |
sailors | -0.027 |
boat | -0.026 |
boat | -0.025 |
boats | -0.024 |
sail | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
blonde | +0.047 |
oph | +0.039 |
uct | +0.038 |
fru | +0.036 |
brow | +0.036 |
Neg logit contributions | |
boats | -0.108 |
sailors | -0.107 |
boat | -0.105 |
sail | -0.104 |
captains | -0.099 |
Token | face |
Token ID | 1986 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
blonde | +0.150 |
oph | +0.147 |
uct | +0.137 |
Could | +0.127 |
cavity | +0.123 |
Neg logit contributions | |
sailors | -0.168 |
boat | -0.167 |
boats | -0.164 |
sail | -0.159 |
ship | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
blonde | +0.118 |
oph | +0.110 |
fru | +0.108 |
uct | +0.106 |
brist | +0.105 |
Neg logit contributions | |
sailors | -0.051 |
boat | -0.050 |
boats | -0.048 |
boat | -0.044 |
sail | -0.044 |
Token | One |
Token ID | 1881 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
blonde | +0.064 |
brist | +0.060 |
blush | +0.057 |
spat | +0.056 |
brow | +0.056 |
Neg logit contributions | |
boats | -0.040 |
boat | -0.039 |
sail | -0.035 |
bridge | -0.035 |
Fin | -0.034 |
Token | day |
Token ID | 1110 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
blonde | +0.068 |
blush | +0.061 |
brist | +0.060 |
oph | +0.059 |
Her | +0.058 |
Neg logit contributions | |
sailors | -0.039 |
boat | -0.037 |
aro | -0.036 |
boats | -0.036 |
boat | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
blonde | +0.052 |
uct | +0.046 |
oph | +0.046 |
blush | +0.046 |
brist | +0.046 |
Neg logit contributions | |
sailors | -0.026 |
boat | -0.026 |
aro | -0.026 |
boats | -0.025 |
ug | -0.025 |
Token | my |
Token ID | 1820 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
blonde | +0.029 |
blush | +0.024 |
brist | +0.024 |
oph | +0.022 |
Her | +0.022 |
Neg logit contributions | |
sailors | -0.035 |
boat | -0.034 |
boats | -0.033 |
boat | -0.033 |
captains | -0.033 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
blonde | +0.024 |
blush | +0.020 |
brist | +0.019 |
oph | +0.019 |
Her | +0.018 |
Neg logit contributions | |
sailors | -0.031 |
boat | -0.029 |
boats | -0.029 |
aro | -0.029 |
boat | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
blonde | +0.041 |
brist | +0.034 |
blush | +0.034 |
oph | +0.033 |
uct | +0.032 |
Neg logit contributions | |
sailors | -0.058 |
boats | -0.056 |
boat | -0.055 |
sharks | -0.054 |
ug | -0.054 |
Token | to |
Token ID | 284 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
blonde | +0.043 |
blush | +0.036 |
brist | +0.036 |
oph | +0.035 |
Her | +0.033 |
Neg logit contributions | |
sailors | -0.053 |
boat | -0.051 |
boats | -0.050 |
aro | -0.049 |
captains | -0.049 |
Token | brush |
Token ID | 14093 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
sailors | +0.004 |
aro | +0.004 |
boat | +0.004 |
boats | +0.004 |
sharks | +0.004 |
Neg logit contributions | |
blonde | -0.005 |
blush | -0.004 |
brist | -0.004 |
oph | -0.004 |
Her | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
blonde | +0.066 |
oph | +0.056 |
blush | +0.054 |
brist | +0.054 |
uct | +0.052 |
Neg logit contributions | |
boat | -0.067 |
sailors | -0.067 |
boats | -0.066 |
aro | -0.064 |
sharks | -0.063 |
Token | hair |
Token ID | 4190 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
oph | +0.165 |
blonde | +0.127 |
uct | +0.127 |
omm | +0.115 |
atisf | +0.111 |
Neg logit contributions | |
boat | -0.164 |
boats | -0.155 |
raft | -0.142 |
sail | -0.141 |
crane | -0.141 |
Token | before |
Token ID | 878 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
blonde | +0.129 |
oph | +0.118 |
fru | +0.108 |
uct | +0.107 |
brist | +0.106 |
Neg logit contributions | |
boat | -0.075 |
boat | -0.072 |
boats | -0.070 |
aro | -0.067 |
boats | -0.066 |
Token | going |
Token ID | 1016 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
blonde | +0.018 |
oph | +0.016 |
brist | +0.015 |
uct | +0.015 |
blush | +0.015 |
Neg logit contributions | |
boat | -0.021 |
boats | -0.021 |
sailors | -0.021 |
sail | -0.020 |
sharks | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
blonde | +0.092 |
oph | +0.081 |
brist | +0.077 |
blush | +0.076 |
fru | +0.075 |
Neg logit contributions | |
sailors | -0.074 |
boats | -0.073 |
boat | -0.073 |
aro | -0.071 |
bridge | -0.069 |
Token | school |
Token ID | 1524 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
blonde | +0.103 |
oph | +0.089 |
brow | +0.087 |
blush | +0.086 |
brist | +0.085 |
Neg logit contributions | |
boat | -0.064 |
boats | -0.063 |
sailors | -0.063 |
sail | -0.062 |
bridge | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
blonde | +0.048 |
oph | +0.044 |
uct | +0.041 |
Her | +0.040 |
omm | +0.040 |
Neg logit contributions | |
sailors | -0.046 |
boat | -0.046 |
boats | -0.046 |
sail | -0.044 |
raft | -0.043 |
Token | brush |
Token ID | 14093 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
blonde | +0.048 |
oph | +0.044 |
uct | +0.044 |
Her | +0.041 |
blush | +0.041 |
Neg logit contributions | |
boat | -0.049 |
sail | -0.045 |
sailors | -0.045 |
raft | -0.044 |
bridge | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
blonde | +0.043 |
oph | +0.038 |
blush | +0.037 |
brist | +0.036 |
Her | +0.035 |
Neg logit contributions | |
boat | -0.028 |
sailors | -0.027 |
boats | -0.027 |
boat | -0.026 |
aro | -0.026 |
Token | She |
Token ID | 1375 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
pron | +0.049 |
oph | +0.048 |
blonde | +0.047 |
blush | +0.046 |
ited | +0.045 |
Neg logit contributions | |
crane | -0.048 |
Fin | -0.047 |
boats | -0.046 |
bridge | -0.046 |
sail | -0.045 |
Token | gently |
Token ID | 15165 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
blonde | +0.092 |
blush | +0.077 |
oph | +0.076 |
Her | +0.075 |
omm | +0.073 |
Neg logit contributions | |
boat | -0.086 |
boats | -0.082 |
sailors | -0.080 |
ship | -0.076 |
raft | -0.076 |
Token | scrub |
Token ID | 27268 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
blonde | +0.095 |
omm | +0.086 |
oph | +0.084 |
uct | +0.079 |
meanings | +0.078 |
Neg logit contributions | |
boat | -0.098 |
boats | -0.094 |
sail | -0.092 |
sailors | -0.089 |
raft | -0.089 |
Token | bed |
Token ID | 3077 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
blonde | +0.178 |
oph | +0.156 |
blush | +0.145 |
Her | +0.144 |
fru | +0.142 |
Neg logit contributions | |
ug | -0.142 |
sailors | -0.136 |
boats | -0.133 |
aro | -0.132 |
boat | -0.129 |
Token | and |
Token ID | 290 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
blonde | +0.175 |
oph | +0.161 |
uct | +0.151 |
blush | +0.149 |
Her | +0.147 |
Neg logit contributions | |
boats | -0.103 |
sailors | -0.101 |
boat | -0.101 |
ug | -0.099 |
aro | -0.095 |
Token | scrub |
Token ID | 27268 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
blonde | +0.090 |
oph | +0.082 |
omm | +0.079 |
Her | +0.078 |
uct | +0.071 |
Neg logit contributions | |
sailors | -0.087 |
boat | -0.086 |
boats | -0.084 |
sail | -0.082 |
ug | -0.080 |
Token | bed |
Token ID | 3077 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
blonde | +0.176 |
oph | +0.157 |
blush | +0.146 |
Her | +0.144 |
uct | +0.140 |
Neg logit contributions | |
ug | -0.151 |
sailors | -0.145 |
boats | -0.140 |
aro | -0.139 |
boat | -0.136 |
Token | until |
Token ID | 1566 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
blonde | +0.166 |
oph | +0.152 |
uct | +0.141 |
blush | +0.141 |
Her | +0.138 |
Neg logit contributions | |
sailors | -0.112 |
boats | -0.112 |
ug | -0.112 |
boat | -0.110 |
aro | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
blonde | +0.046 |
blush | +0.041 |
brist | +0.039 |
oph | +0.039 |
Her | +0.038 |
Neg logit contributions | |
sailors | -0.034 |
aro | -0.032 |
boats | -0.032 |
boat | -0.032 |
ug | -0.031 |
Token | Julie |
Token ID | 21946 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
blonde | +0.024 |
blush | +0.020 |
pron | +0.020 |
brist | +0.020 |
fru | +0.019 |
Neg logit contributions | |
sailors | -0.031 |
boats | -0.030 |
boat | -0.029 |
whales | -0.029 |
bridge | -0.029 |
Token | started |
Token ID | 2067 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
blonde | +0.101 |
blush | +0.085 |
oph | +0.081 |
Her | +0.080 |
amas | +0.079 |
Neg logit contributions | |
boat | -0.100 |
sailors | -0.098 |
boats | -0.098 |
aro | -0.097 |
ug | -0.094 |
Token | to |
Token ID | 284 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
oph | +0.096 |
blonde | +0.089 |
uct | +0.089 |
amas | +0.081 |
fru | +0.081 |
Neg logit contributions | |
boats | -0.074 |
boat | -0.071 |
sailors | -0.070 |
bridge | -0.069 |
sail | -0.068 |
Token | comb |
Token ID | 1974 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
oph | +0.084 |
blonde | +0.083 |
omm | +0.080 |
amas | +0.077 |
Her | +0.075 |
Neg logit contributions | |
sail | -0.080 |
boat | -0.076 |
bridge | -0.074 |
boats | -0.073 |
sailors | -0.073 |
Token | her |
Token ID | 607 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
blonde | +0.107 |
oph | +0.092 |
blush | +0.092 |
uct | +0.089 |
Her | +0.088 |
Neg logit contributions | |
sailors | -0.088 |
aro | -0.087 |
boats | -0.086 |
boat | -0.085 |
ug | -0.085 |
Token | own |
Token ID | 898 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
oph | +0.160 |
uct | +0.131 |
Da | +0.126 |
blonde | +0.123 |
Acc | +0.116 |
Neg logit contributions | |
boat | -0.150 |
boats | -0.136 |
crane | -0.131 |
sail | -0.131 |
bridge | -0.123 |
Token | hair |
Token ID | 4190 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
oph | +0.124 |
uct | +0.112 |
blonde | +0.103 |
auldron | +0.094 |
fru | +0.093 |
Neg logit contributions | |
boat | -0.150 |
boats | -0.142 |
sail | -0.136 |
crane | -0.135 |
sailors | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
blonde | +0.132 |
oph | +0.120 |
uct | +0.116 |
fru | +0.113 |
blush | +0.112 |
Neg logit contributions | |
boat | -0.076 |
boat | -0.073 |
boats | -0.071 |
boats | -0.069 |
bridge | -0.069 |
Token | She |
Token ID | 1375 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
blonde | +0.046 |
fru | +0.041 |
oph | +0.041 |
pron | +0.040 |
uct | +0.040 |
Neg logit contributions | |
sailors | -0.053 |
boats | -0.052 |
ug | -0.052 |
bridge | -0.051 |
aro | -0.050 |
Token | was |
Token ID | 373 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
blonde | +0.135 |
amas | +0.127 |
omm | +0.123 |
oph | +0.120 |
Deal | +0.115 |
Neg logit contributions | |
boat | -0.108 |
boats | -0.106 |
sailed | -0.101 |
sailors | -0.101 |
aro | -0.099 |
Token | with |
Token ID | 351 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
blonde | +0.033 |
blush | +0.029 |
oph | +0.029 |
brist | +0.028 |
Her | +0.028 |
Neg logit contributions | |
sailors | -0.028 |
boat | -0.026 |
boats | -0.026 |
aro | -0.026 |
boat | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
blonde | +0.009 |
blush | +0.008 |
brist | +0.008 |
oph | +0.008 |
uct | +0.008 |
Neg logit contributions | |
sailors | -0.010 |
boat | -0.009 |
boats | -0.009 |
sharks | -0.009 |
whales | -0.009 |
Token | big |
Token ID | 1263 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
blonde | +0.047 |
blush | +0.041 |
oph | +0.041 |
Her | +0.041 |
brist | +0.041 |
Neg logit contributions | |
boat | -0.040 |
sailors | -0.039 |
sail | -0.037 |
boat | -0.036 |
boats | -0.036 |
Token | smile |
Token ID | 8212 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
blonde | +0.028 |
blush | +0.024 |
oph | +0.024 |
brist | +0.024 |
Her | +0.023 |
Neg logit contributions | |
sailors | -0.032 |
boat | -0.032 |
boats | -0.031 |
boat | -0.030 |
sharks | -0.030 |
Token | on |
Token ID | 319 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
blonde | +0.023 |
oph | +0.020 |
blush | +0.020 |
brist | +0.020 |
Her | +0.019 |
Neg logit contributions | |
sailors | -0.013 |
boat | -0.013 |
boat | -0.013 |
aro | -0.012 |
boats | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
blonde | +0.061 |
oph | +0.052 |
fru | +0.051 |
uct | +0.050 |
elt | +0.049 |
Neg logit contributions | |
sail | -0.116 |
boat | -0.114 |
sailors | -0.114 |
boats | -0.109 |
aro | -0.107 |
Token | face |
Token ID | 1986 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
blonde | +0.141 |
oph | +0.127 |
uct | +0.115 |
blush | +0.113 |
brist | +0.109 |
Neg logit contributions | |
sailors | -0.174 |
boat | -0.172 |
sail | -0.167 |
boats | -0.164 |
ship | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
blonde | +0.100 |
oph | +0.092 |
brist | +0.088 |
fru | +0.088 |
uct | +0.087 |
Neg logit contributions | |
boat | -0.050 |
sailors | -0.049 |
boat | -0.046 |
sail | -0.046 |
aro | -0.045 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
blonde | +0.057 |
blush | +0.055 |
fru | +0.055 |
brist | +0.054 |
brow | +0.052 |
Neg logit contributions | |
sailors | -0.026 |
drivers | -0.022 |
sail | -0.022 |
they | -0.022 |
boom | -0.021 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
sailors | +0.025 |
boat | +0.024 |
aro | +0.023 |
boats | +0.023 |
sharks | +0.023 |
Neg logit contributions | |
blonde | -0.025 |
blush | -0.022 |
brist | -0.022 |
oph | -0.021 |
Her | -0.021 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
blonde | +0.005 |
blush | +0.004 |
Her | +0.004 |
brist | +0.004 |
oph | +0.004 |
Neg logit contributions | |
sailors | -0.011 |
aro | -0.011 |
boat | -0.011 |
boats | -0.011 |
captains | -0.011 |
Token | 's |
Token ID | 338 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
blonde | +0.054 |
blush | +0.048 |
brist | +0.046 |
oph | +0.046 |
Her | +0.045 |
Neg logit contributions | |
sailors | -0.040 |
boat | -0.039 |
aro | -0.038 |
boats | -0.038 |
boat | -0.038 |
Token | order |
Token ID | 1502 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
oph | +0.089 |
blonde | +0.087 |
uct | +0.079 |
blush | +0.078 |
fru | +0.074 |
Neg logit contributions | |
boat | -0.075 |
sailors | -0.074 |
bridge | -0.070 |
ug | -0.068 |
boats | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
sailors | +0.010 |
boat | +0.009 |
boats | +0.009 |
aro | +0.009 |
boat | +0.009 |
Neg logit contributions | |
blonde | -0.013 |
blush | -0.011 |
oph | -0.011 |
brist | -0.011 |
Her | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
blonde | +0.011 |
blush | +0.010 |
brist | +0.010 |
oph | +0.009 |
fru | +0.009 |
Neg logit contributions | |
sailors | -0.006 |
boat | -0.006 |
boats | -0.006 |
ug | -0.006 |
boat | -0.006 |
Token | brushed |
Token ID | 31782 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
blonde | +0.101 |
omm | +0.087 |
amas | +0.086 |
oph | +0.085 |
Deal | +0.082 |
Neg logit contributions | |
boat | -0.079 |
boats | -0.077 |
sailors | -0.073 |
sailed | -0.072 |
ug | -0.070 |
Token | her |
Token ID | 607 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
blonde | +0.078 |
oph | +0.068 |
blush | +0.066 |
uct | +0.065 |
fru | +0.061 |
Neg logit contributions | |
sailors | -0.083 |
boat | -0.081 |
boats | -0.081 |
ug | -0.080 |
boat | -0.078 |
Token | hair |
Token ID | 4190 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
oph | +0.178 |
uct | +0.141 |
blonde | +0.139 |
assy | +0.128 |
Em | +0.127 |
Neg logit contributions | |
boat | -0.135 |
boats | -0.129 |
sail | -0.118 |
bridge | -0.113 |
paddle | -0.112 |
Token | with |
Token ID | 351 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
blonde | +0.152 |
oph | +0.141 |
uct | +0.130 |
fru | +0.127 |
blush | +0.125 |
Neg logit contributions | |
boat | -0.085 |
boat | -0.080 |
boats | -0.079 |
ug | -0.076 |
sail | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
blonde | +0.035 |
oph | +0.034 |
uct | +0.032 |
blush | +0.031 |
Her | +0.030 |
Neg logit contributions | |
sailors | -0.035 |
boats | -0.035 |
boat | -0.034 |
sail | -0.033 |
sharks | -0.032 |
Token | brush |
Token ID | 14093 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
oph | +0.075 |
uct | +0.066 |
blonde | +0.062 |
anna | +0.055 |
omm | +0.054 |
Neg logit contributions | |
boat | -0.082 |
crane | -0.079 |
bridge | -0.078 |
sail | -0.076 |
boats | -0.076 |
Token | very |
Token ID | 845 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
blonde | +0.081 |
oph | +0.074 |
uct | +0.070 |
blush | +0.069 |
brist | +0.068 |
Neg logit contributions | |
boat | -0.062 |
boats | -0.059 |
boat | -0.058 |
sailors | -0.058 |
sail | -0.057 |
Token | After |
Token ID | 3260 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
blonde | +0.058 |
blush | +0.051 |
brist | +0.048 |
fru | +0.047 |
blond | +0.047 |
Neg logit contributions | |
sailors | -0.043 |
boats | -0.042 |
boat | -0.042 |
captains | -0.041 |
ug | -0.041 |
Token | her |
Token ID | 607 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
sailors | +0.014 |
boat | +0.013 |
aro | +0.013 |
boats | +0.013 |
sharks | +0.013 |
Neg logit contributions | |
blonde | -0.018 |
blush | -0.015 |
brist | -0.015 |
oph | -0.015 |
Her | -0.015 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
blonde | +0.111 |
oph | +0.107 |
uct | +0.099 |
fru | +0.097 |
brow | +0.091 |
Neg logit contributions | |
boat | -0.088 |
boats | -0.085 |
bridge | -0.080 |
sailors | -0.079 |
sail | -0.079 |
Token | my |
Token ID | 1820 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
blonde | +0.085 |
brist | +0.068 |
oph | +0.068 |
fru | +0.068 |
brow | +0.066 |
Neg logit contributions | |
ug | -0.073 |
boat | -0.073 |
sailors | -0.072 |
boats | -0.071 |
ship | -0.068 |
Token | brushed |
Token ID | 31782 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
blonde | +0.082 |
blush | +0.065 |
oph | +0.065 |
fru | +0.064 |
brist | +0.064 |
Neg logit contributions | |
boat | -0.084 |
sailors | -0.082 |
ug | -0.081 |
boats | -0.081 |
aro | -0.077 |
Token | her |
Token ID | 607 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
blonde | +0.071 |
oph | +0.061 |
uct | +0.058 |
blush | +0.056 |
fru | +0.054 |
Neg logit contributions | |
boat | -0.096 |
boats | -0.095 |
ug | -0.094 |
sailors | -0.093 |
aro | -0.092 |
Token | hair |
Token ID | 4190 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
oph | +0.187 |
uct | +0.146 |
blonde | +0.146 |
Da | +0.143 |
fru | +0.131 |
Neg logit contributions | |
boat | -0.139 |
boats | -0.130 |
sail | -0.117 |
train | -0.116 |
bridge | -0.114 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
blonde | +0.148 |
oph | +0.137 |
uct | +0.130 |
fru | +0.125 |
blush | +0.123 |
Neg logit contributions | |
boat | -0.070 |
ug | -0.065 |
boats | -0.064 |
boat | -0.064 |
aro | -0.061 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
blonde | +0.053 |
oph | +0.046 |
brist | +0.045 |
uct | +0.044 |
brow | +0.043 |
Neg logit contributions | |
boat | -0.051 |
boats | -0.051 |
sailors | -0.050 |
sail | -0.047 |
sharks | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
blonde | +0.124 |
omm | +0.109 |
Deal | +0.107 |
oph | +0.106 |
fru | +0.106 |
Neg logit contributions | |
boat | -0.093 |
boats | -0.086 |
ship | -0.082 |
sailors | -0.081 |
sailed | -0.081 |
Token | her |
Token ID | 607 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
blonde | +0.041 |
brist | +0.032 |
oph | +0.030 |
blush | +0.029 |
blond | +0.028 |
Neg logit contributions | |
sailors | -0.078 |
boats | -0.076 |
boat | -0.076 |
ship | -0.071 |
sail | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
sailors | +0.045 |
boat | +0.043 |
aro | +0.043 |
boats | +0.043 |
sharks | +0.042 |
Neg logit contributions | |
blonde | -0.038 |
blush | -0.033 |
brist | -0.032 |
oph | -0.031 |
Her | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
sailors | +0.009 |
captains | +0.009 |
boat | +0.008 |
aro | +0.008 |
boats | +0.008 |
Neg logit contributions | |
blonde | -0.006 |
Her | -0.005 |
blush | -0.005 |
oph | -0.005 |
brist | -0.005 |
Token | After |
Token ID | 3260 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
sailors | +0.006 |
aro | +0.005 |
boat | +0.005 |
boats | +0.005 |
captains | +0.005 |
Neg logit contributions | |
blonde | -0.004 |
blush | -0.004 |
oph | -0.003 |
brist | -0.003 |
Her | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
sailors | +0.041 |
boat | +0.041 |
boats | +0.041 |
aro | +0.041 |
captains | +0.040 |
Neg logit contributions | |
blonde | -0.037 |
blush | -0.033 |
brist | -0.031 |
Her | -0.031 |
makeup | -0.030 |
Token | brushed |
Token ID | 31782 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
blonde | +0.075 |
Her | +0.061 |
amas | +0.061 |
oph | +0.061 |
brist | +0.059 |
Neg logit contributions | |
boat | -0.075 |
sailors | -0.072 |
boats | -0.071 |
sail | -0.071 |
aro | -0.069 |
Token | his |
Token ID | 465 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
blonde | +0.061 |
blush | +0.055 |
brist | +0.053 |
oph | +0.053 |
Her | +0.052 |
Neg logit contributions | |
sailors | -0.041 |
boat | -0.039 |
boats | -0.038 |
aro | -0.038 |
boat | -0.037 |
Token | hair |
Token ID | 4190 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
oph | +0.183 |
Da | +0.147 |
uct | +0.145 |
enny | +0.137 |
blonde | +0.136 |
Neg logit contributions | |
boat | -0.135 |
boats | -0.128 |
sail | -0.123 |
crane | -0.119 |
sailors | -0.119 |
Token | , |
Token ID | 11 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
blonde | +0.124 |
oph | +0.116 |
uct | +0.110 |
blush | +0.105 |
fru | +0.105 |
Neg logit contributions | |
boat | -0.070 |
boat | -0.066 |
boats | -0.064 |
ug | -0.062 |
sail | -0.062 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
aro | +0.024 |
sailors | +0.024 |
ug | +0.023 |
boat | +0.023 |
captains | +0.023 |
Neg logit contributions | |
blonde | -0.028 |
blush | -0.024 |
brist | -0.023 |
Her | -0.023 |
oph | -0.023 |
Token | would |
Token ID | 561 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
blonde | +0.056 |
oph | +0.047 |
blush | +0.047 |
brist | +0.046 |
Her | +0.045 |
Neg logit contributions | |
boat | -0.060 |
sailors | -0.059 |
boats | -0.058 |
boat | -0.056 |
ship | -0.056 |
Token | brush |
Token ID | 14093 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
blonde | +0.118 |
oph | +0.113 |
fru | +0.100 |
omm | +0.100 |
uct | +0.100 |
Neg logit contributions | |
sail | -0.094 |
boat | -0.091 |
sailors | -0.085 |
bridge | -0.084 |
boats | -0.083 |
Token | and |
Token ID | 290 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
blonde | +0.090 |
oph | +0.080 |
blush | +0.078 |
brist | +0.075 |
fru | +0.074 |
Neg logit contributions | |
boat | -0.061 |
boat | -0.061 |
ug | -0.059 |
boats | -0.058 |
sailors | -0.058 |
Token | put |
Token ID | 1234 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
blonde | +0.080 |
oph | +0.078 |
omm | +0.073 |
uct | +0.071 |
Her | +0.068 |
Neg logit contributions | |
boat | -0.087 |
sailors | -0.085 |
sail | -0.084 |
boats | -0.082 |
sailed | -0.079 |
Token | on |
Token ID | 319 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
blonde | +0.039 |
oph | +0.035 |
blush | +0.034 |
Her | +0.034 |
brist | +0.033 |
Neg logit contributions | |
sailors | -0.025 |
boat | -0.024 |
boats | -0.023 |
aro | -0.023 |
sharks | -0.022 |
Token | his |
Token ID | 465 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
blonde | +0.050 |
oph | +0.047 |
blush | +0.046 |
brist | +0.044 |
Her | +0.044 |
Neg logit contributions | |
boat | -0.025 |
sailors | -0.025 |
boats | -0.025 |
sharks | -0.023 |
aro | -0.023 |
Token | p |
Token ID | 279 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
oph | +0.111 |
uct | +0.094 |
blonde | +0.086 |
aman | +0.085 |
Her | +0.080 |
Neg logit contributions | |
boat | -0.104 |
boats | -0.097 |
sailors | -0.093 |
sail | -0.092 |
fish | -0.091 |
Token | aj |
Token ID | 1228 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
blonde | +0.080 |
oph | +0.070 |
blush | +0.069 |
uct | +0.067 |
brist | +0.064 |
Neg logit contributions | |
ug | -0.110 |
aro | -0.109 |
boat | -0.108 |
boats | -0.106 |
bridge | -0.106 |
Token | amas |
Token ID | 17485 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
uct | +0.102 |
blonde | +0.096 |
fru | +0.092 |
blush | +0.092 |
Could | +0.090 |
Neg logit contributions | |
ug | -0.170 |
sailors | -0.164 |
boats | -0.163 |
boat | -0.159 |
sail | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
blonde | +0.018 |
blush | +0.016 |
brist | +0.016 |
oph | +0.016 |
Her | +0.015 |
Neg logit contributions | |
sailors | -0.014 |
boat | -0.013 |
aro | -0.013 |
boat | -0.013 |
boats | -0.013 |
Token | Then |
Token ID | 3244 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
blonde | +0.028 |
blush | +0.027 |
oph | +0.027 |
brist | +0.026 |
uct | +0.026 |
Neg logit contributions | |
sailors | -0.016 |
sail | -0.016 |
boats | -0.015 |
boat | -0.015 |
bridge | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
sailors | +0.007 |
boat | +0.006 |
aro | +0.006 |
boats | +0.006 |
sharks | +0.006 |
Neg logit contributions | |
blonde | -0.010 |
blush | -0.009 |
brist | -0.009 |
oph | -0.008 |
Her | -0.008 |
Token | sn |
Token ID | 3013 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
blonde | +0.067 |
uct | +0.057 |
Her | +0.055 |
oph | +0.055 |
blush | +0.055 |
Neg logit contributions | |
boat | -0.063 |
sailors | -0.060 |
boats | -0.059 |
ship | -0.059 |
sail | -0.058 |
Token | with |
Token ID | 351 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
blonde | +0.085 |
blush | +0.074 |
oph | +0.072 |
brist | +0.071 |
fru | +0.069 |
Neg logit contributions | |
boat | -0.071 |
sailors | -0.070 |
boats | -0.067 |
ug | -0.066 |
aro | -0.065 |
Token | a |
Token ID | 257 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
blonde | +0.001 |
oph | +0.001 |
blush | +0.001 |
brist | +0.001 |
uct | +0.001 |
Neg logit contributions | |
sailors | -0.001 |
boat | -0.001 |
boats | -0.001 |
sharks | -0.001 |
sail | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
blonde | +0.027 |
oph | +0.024 |
uct | +0.024 |
brist | +0.023 |
blush | +0.023 |
Neg logit contributions | |
boat | -0.021 |
sail | -0.019 |
sailors | -0.019 |
bridge | -0.018 |
boat | -0.018 |
Token | smile |
Token ID | 8212 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
blonde | +0.031 |
oph | +0.026 |
blush | +0.026 |
brist | +0.025 |
Her | +0.025 |
Neg logit contributions | |
boat | -0.033 |
sailors | -0.033 |
boats | -0.032 |
boat | -0.031 |
sail | -0.031 |
Token | on |
Token ID | 319 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
blonde | +0.011 |
blush | +0.009 |
oph | +0.009 |
brist | +0.009 |
Her | +0.009 |
Neg logit contributions | |
sailors | -0.006 |
boat | -0.006 |
boat | -0.006 |
aro | -0.006 |
boats | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
blonde | +0.053 |
oph | +0.042 |
pad | +0.038 |
uct | +0.038 |
fru | +0.037 |
Neg logit contributions | |
sail | -0.099 |
boat | -0.098 |
sailors | -0.097 |
boats | -0.096 |
aro | -0.091 |
Token | face |
Token ID | 1986 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
blonde | +0.150 |
oph | +0.136 |
blush | +0.118 |
fru | +0.115 |
uct | +0.115 |
Neg logit contributions | |
boat | -0.161 |
sailors | -0.161 |
sail | -0.156 |
boats | -0.151 |
ship | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
blonde | +0.088 |
oph | +0.080 |
brist | +0.077 |
fru | +0.077 |
blush | +0.075 |
Neg logit contributions | |
boat | -0.041 |
sailors | -0.040 |
boat | -0.038 |
sail | -0.038 |
aro | -0.038 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
blonde | +0.048 |
blush | +0.043 |
blond | +0.041 |
brist | +0.041 |
brow | +0.040 |
Neg logit contributions | |
sailors | -0.020 |
boat | -0.019 |
boats | -0.019 |
sail | -0.019 |
Fin | -0.017 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
sailors | +0.014 |
boat | +0.013 |
aro | +0.013 |
boats | +0.013 |
sharks | +0.013 |
Neg logit contributions | |
blonde | -0.013 |
blush | -0.011 |
brist | -0.011 |
oph | -0.010 |
Her | -0.010 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
sailors | +0.001 |
aro | +0.001 |
boat | +0.001 |
captains | +0.001 |
boats | +0.001 |
Neg logit contributions | |
blonde | -0.000 |
blush | -0.000 |
Her | -0.000 |
oph | -0.000 |
brist | -0.000 |
Token | When |
Token ID | 2215 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
blonde | +0.047 |
blush | +0.040 |
brist | +0.038 |
oph | +0.037 |
fru | +0.037 |
Neg logit contributions | |
sailors | -0.054 |
aro | -0.051 |
boat | -0.051 |
boats | -0.050 |
captains | -0.050 |
Token | Julie |
Token ID | 21946 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
sailors | +0.002 |
boat | +0.002 |
boats | +0.002 |
aro | +0.002 |
sharks | +0.002 |
Neg logit contributions | |
blonde | -0.001 |
blush | -0.001 |
brist | -0.001 |
oph | -0.001 |
Her | -0.001 |
Token | finished |
Token ID | 5201 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
blonde | +0.095 |
amas | +0.080 |
brist | +0.079 |
omm | +0.077 |
brow | +0.076 |
Neg logit contributions | |
boat | -0.082 |
boats | -0.076 |
sailed | -0.075 |
sail | -0.074 |
aro | -0.073 |
Token | comb |
Token ID | 1974 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
blonde | +0.096 |
oph | +0.085 |
brow | +0.082 |
uct | +0.082 |
fru | +0.077 |
Neg logit contributions | |
boat | -0.090 |
boats | -0.089 |
aro | -0.086 |
sail | -0.085 |
bridge | -0.081 |
Token | ing |
Token ID | 278 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
blonde | +0.087 |
oph | +0.075 |
blush | +0.074 |
uct | +0.073 |
brist | +0.072 |
Neg logit contributions | |
boat | -0.069 |
aro | -0.069 |
sailors | -0.067 |
boats | -0.067 |
ug | -0.066 |
Token | her |
Token ID | 607 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
blonde | +0.072 |
oph | +0.061 |
blush | +0.061 |
brist | +0.059 |
uct | +0.058 |
Neg logit contributions | |
sailors | -0.071 |
aro | -0.070 |
boat | -0.069 |
boats | -0.069 |
ug | -0.066 |
Token | hair |
Token ID | 4190 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
oph | +0.169 |
Da | +0.147 |
uct | +0.143 |
blonde | +0.127 |
riet | +0.124 |
Neg logit contributions | |
boat | -0.132 |
boats | -0.123 |
sail | -0.122 |
crane | -0.115 |
train | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
blonde | +0.131 |
uct | +0.123 |
oph | +0.123 |
fru | +0.115 |
cavity | +0.115 |
Neg logit contributions | |
boat | -0.057 |
boat | -0.050 |
boats | -0.047 |
sail | -0.046 |
aro | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
blonde | +0.029 |
oph | +0.023 |
brist | +0.023 |
blush | +0.023 |
fru | +0.021 |
Neg logit contributions | |
sailors | -0.054 |
boat | -0.052 |
boats | -0.052 |
aro | -0.051 |
sharks | -0.050 |
Token | showed |
Token ID | 3751 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
blonde | +0.096 |
omm | +0.081 |
amas | +0.079 |
Her | +0.078 |
brist | +0.076 |
Neg logit contributions | |
boat | -0.077 |
sailors | -0.075 |
boats | -0.074 |
sailed | -0.072 |
sail | -0.072 |
Token | her |
Token ID | 607 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
blonde | +0.034 |
brist | +0.025 |
blush | +0.025 |
oph | +0.024 |
pron | +0.024 |
Neg logit contributions | |
sailors | -0.065 |
boat | -0.063 |
boats | -0.063 |
aro | -0.062 |
whales | -0.061 |
Token | straight |
Token ID | 3892 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
blonde | +0.008 |
blush | +0.007 |
brist | +0.007 |
Her | +0.007 |
oph | +0.007 |
Neg logit contributions | |
sailors | -0.010 |
boat | -0.010 |
boats | -0.010 |
aro | -0.009 |
boat | -0.009 |
Token | ened |
Token ID | 2945 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
blonde | +0.014 |
blush | +0.012 |
Her | +0.011 |
oph | +0.011 |
brist | +0.011 |
Neg logit contributions | |
sailors | -0.018 |
boat | -0.018 |
boats | -0.017 |
aro | -0.017 |
ug | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
blonde | +0.035 |
blush | +0.031 |
brist | +0.031 |
oph | +0.030 |
Her | +0.030 |
Neg logit contributions | |
sailors | -0.025 |
boat | -0.023 |
aro | -0.023 |
boats | -0.023 |
sharks | -0.023 |
Token | dress |
Token ID | 6576 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
blonde | +0.085 |
oph | +0.077 |
Her | +0.073 |
uct | +0.071 |
fru | +0.068 |
Neg logit contributions | |
boat | -0.089 |
sail | -0.081 |
bridge | -0.080 |
boats | -0.080 |
ship | -0.077 |
Token | on |
Token ID | 319 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
blonde | +0.049 |
blush | +0.043 |
brist | +0.042 |
oph | +0.041 |
Her | +0.040 |
Neg logit contributions | |
sailors | -0.044 |
boat | -0.043 |
aro | -0.042 |
boats | -0.042 |
boat | -0.042 |
Token | her |
Token ID | 607 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
blonde | +0.072 |
blush | +0.064 |
brist | +0.062 |
oph | +0.061 |
Her | +0.061 |
Neg logit contributions | |
sailors | -0.048 |
boat | -0.046 |
boats | -0.045 |
aro | -0.044 |
sharks | -0.043 |
Token | body |
Token ID | 1767 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
blonde | +0.143 |
oph | +0.132 |
uct | +0.122 |
cavity | +0.122 |
fru | +0.120 |
Neg logit contributions | |
boat | -0.170 |
sail | -0.158 |
boats | -0.156 |
ship | -0.155 |
sailors | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
blonde | +0.036 |
blush | +0.031 |
brist | +0.031 |
oph | +0.030 |
Her | +0.030 |
Neg logit contributions | |
sailors | -0.030 |
boat | -0.028 |
aro | -0.028 |
boats | -0.028 |
sharks | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
blonde | +0.038 |
pron | +0.036 |
blush | +0.035 |
cavity | +0.034 |
brist | +0.033 |
Neg logit contributions | |
whales | -0.034 |
sailors | -0.034 |
boats | -0.032 |
bridge | -0.031 |
aro | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
blonde | +0.046 |
blush | +0.039 |
brist | +0.037 |
oph | +0.037 |
Her | +0.037 |
Neg logit contributions | |
sailors | -0.055 |
boat | -0.054 |
aro | -0.053 |
boats | -0.053 |
boat | -0.053 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
blonde | +0.065 |
blush | +0.061 |
oph | +0.059 |
Her | +0.059 |
brist | +0.057 |
Neg logit contributions | |
sailors | -0.053 |
boats | -0.050 |
boat | -0.050 |
sharks | -0.048 |
sail | -0.048 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
sailors | +0.037 |
aro | +0.036 |
boats | +0.036 |
ug | +0.036 |
boat | +0.035 |
Neg logit contributions | |
blonde | -0.021 |
Her | -0.018 |
blush | -0.018 |
brist | -0.016 |
makeup | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
sailors | +0.079 |
captains | +0.077 |
boat | +0.076 |
aro | +0.075 |
boats | +0.074 |
Neg logit contributions | |
blonde | -0.051 |
oph | -0.048 |
Her | -0.045 |
blush | -0.042 |
omm | -0.041 |
Token | kids |
Token ID | 3988 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
ug | +0.089 |
boat | +0.087 |
afloat | +0.085 |
aro | +0.085 |
ull | +0.083 |
Neg logit contributions | |
blonde | -0.066 |
oph | -0.060 |
blush | -0.056 |
uct | -0.056 |
Her | -0.055 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
sailors | +0.109 |
captains | +0.106 |
boats | +0.103 |
aro | +0.102 |
whales | +0.102 |
Neg logit contributions | |
blonde | -0.070 |
Her | -0.062 |
unw | -0.061 |
blush | -0.060 |
oph | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
sailors | +0.082 |
ug | +0.081 |
aro | +0.081 |
boat | +0.080 |
captains | +0.079 |
Neg logit contributions | |
blonde | -0.087 |
Her | -0.078 |
blush | -0.076 |
brist | -0.071 |
She | -0.071 |
Token | zo |
Token ID | 40565 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
afloat | +0.097 |
aro | +0.095 |
ug | +0.095 |
boat | +0.088 |
boats | +0.087 |
Neg logit contributions | |
blonde | -0.104 |
Her | -0.092 |
l | -0.089 |
brist | -0.088 |
me | -0.087 |
Token | oke |
Token ID | 2088 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
afloat | +0.220 |
raft | +0.217 |
sail | +0.199 |
boats | +0.195 |
sailors | +0.192 |
Neg logit contributions | |
Her | -0.110 |
She | -0.099 |
blush | -0.099 |
blonde | -0.096 |
anna | -0.091 |
Token | eper |
Token ID | 5723 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
afloat | +0.101 |
port | +0.100 |
flood | +0.099 |
raft | +0.096 |
sail | +0.095 |
Neg logit contributions | |
brow | -0.108 |
Her | -0.108 |
her | -0.106 |
herself | -0.102 |
uct | -0.100 |
Token | said |
Token ID | 531 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
sailors | +0.101 |
sharks | +0.099 |
captains | +0.099 |
boats | +0.098 |
boats | +0.098 |
Neg logit contributions | |
blonde | -0.044 |
Her | -0.040 |
blush | -0.039 |
brushed | -0.036 |
unw | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
sailors | +0.012 |
aro | +0.012 |
captains | +0.012 |
sharks | +0.012 |
boat | +0.012 |
Neg logit contributions | |
blonde | -0.011 |
Her | -0.010 |
blush | -0.010 |
brist | -0.009 |
brow | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
sailors | +0.061 |
boat | +0.059 |
aro | +0.059 |
boats | +0.058 |
sharks | +0.058 |
Neg logit contributions | |
blonde | -0.033 |
blush | -0.027 |
brist | -0.025 |
oph | -0.024 |
Her | -0.024 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ug | +0.046 |
boat | +0.045 |
boats | +0.045 |
aro | +0.043 |
captains | +0.042 |
Neg logit contributions | |
blonde | -0.041 |
blush | -0.036 |
makeup | -0.034 |
fru | -0.034 |
oph | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
aro | +0.053 |
boat | +0.052 |
sailors | +0.052 |
boats | +0.050 |
captains | +0.050 |
Neg logit contributions | |
blonde | -0.051 |
blush | -0.046 |
oph | -0.046 |
Her | -0.045 |
brist | -0.045 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ug | +0.037 |
boat | +0.037 |
boats | +0.036 |
aro | +0.035 |
captains | +0.034 |
Neg logit contributions | |
blonde | -0.032 |
blush | -0.028 |
makeup | -0.028 |
honey | -0.028 |
fru | -0.028 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
aro | +0.056 |
sailors | +0.054 |
boat | +0.054 |
captains | +0.052 |
ug | +0.052 |
Neg logit contributions | |
blonde | -0.053 |
blush | -0.048 |
brist | -0.048 |
Her | -0.047 |
oph | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
sailors | +0.059 |
aro | +0.057 |
boat | +0.056 |
captains | +0.056 |
boats | +0.056 |
Neg logit contributions | |
blonde | -0.059 |
blush | -0.052 |
Her | -0.051 |
brist | -0.050 |
oph | -0.048 |
Token | zo |
Token ID | 40565 |
Feature activation | -5.94e+00 |
Pos logit contributions | |
ug | +0.068 |
aro | +0.064 |
boats | +0.060 |
afloat | +0.059 |
boat | +0.058 |
Neg logit contributions | |
blonde | -0.098 |
makeup | -0.087 |
brow | -0.086 |
brist | -0.086 |
blush | -0.086 |
Token | oke |
Token ID | 2088 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
raft | +0.209 |
afloat | +0.204 |
sail | +0.188 |
boat | +0.185 |
boat | +0.183 |
Neg logit contributions | |
blush | -0.114 |
Her | -0.110 |
blonde | -0.108 |
spat | -0.105 |
oph | -0.104 |
Token | ep |
Token ID | 538 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
port | +0.090 |
planet | +0.086 |
afloat | +0.086 |
flood | +0.085 |
raft | +0.085 |
Neg logit contributions | |
brow | -0.104 |
uct | -0.100 |
her | -0.098 |
Her | -0.097 |
herself | -0.097 |
Token | ers |
Token ID | 364 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
sailors | +0.102 |
aro | +0.099 |
raft | +0.099 |
sharks | +0.099 |
boats | +0.098 |
Neg logit contributions | |
blonde | -0.060 |
oph | -0.060 |
Her | -0.059 |
uct | -0.058 |
blush | -0.058 |
Token | said |
Token ID | 531 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
aro | +0.117 |
sailors | +0.117 |
ug | +0.112 |
boats | +0.111 |
boat | +0.111 |
Neg logit contributions | |
blonde | -0.066 |
blush | -0.060 |
Her | -0.057 |
oph | -0.053 |
spat | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
blonde | +0.007 |
blush | +0.006 |
brist | +0.006 |
Her | +0.006 |
oph | +0.005 |
Neg logit contributions | |
sailors | -0.006 |
aro | -0.006 |
boat | -0.006 |
boats | -0.006 |
sharks | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
sailors | +0.049 |
boats | +0.047 |
aro | +0.046 |
boat | +0.046 |
sharks | +0.046 |
Neg logit contributions | |
blonde | -0.039 |
Her | -0.033 |
oph | -0.033 |
blush | -0.032 |
uct | -0.031 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
sailors | +0.027 |
boats | +0.026 |
aro | +0.025 |
boat | +0.025 |
sharks | +0.025 |
Neg logit contributions | |
blonde | -0.024 |
oph | -0.020 |
Her | -0.020 |
blush | -0.020 |
brist | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
sailors | +0.061 |
aro | +0.059 |
captains | +0.058 |
boats | +0.058 |
ug | +0.057 |
Neg logit contributions | |
blonde | -0.050 |
Her | -0.041 |
blush | -0.040 |
oph | -0.040 |
brist | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
ug | +0.064 |
sailors | +0.063 |
aro | +0.063 |
boats | +0.061 |
captains | +0.061 |
Neg logit contributions | |
blonde | -0.062 |
blush | -0.053 |
oph | -0.052 |
Her | -0.052 |
brow | -0.049 |
Token | big |
Token ID | 1263 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
sailors | +0.023 |
aro | +0.023 |
boats | +0.022 |
captains | +0.022 |
boats | +0.022 |
Neg logit contributions | |
blonde | -0.024 |
blush | -0.020 |
brist | -0.020 |
Her | -0.019 |
oph | -0.018 |
Token | tank |
Token ID | 6873 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
aro | +0.029 |
sailors | +0.029 |
captains | +0.028 |
boats | +0.027 |
ug | +0.027 |
Neg logit contributions | |
blonde | -0.032 |
blush | -0.027 |
brist | -0.027 |
makeup | -0.025 |
Her | -0.025 |
Token | came |
Token ID | 1625 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
aro | +0.243 |
sailors | +0.239 |
ug | +0.236 |
captains | +0.229 |
boats | +0.227 |
Neg logit contributions | |
spat | -0.080 |
blonde | -0.079 |
blush | -0.067 |
unw | -0.063 |
brow | -0.062 |
Token | out |
Token ID | 503 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
aro | +0.076 |
sailors | +0.074 |
captains | +0.072 |
boat | +0.072 |
boats | +0.072 |
Neg logit contributions | |
blonde | -0.060 |
Her | -0.051 |
brow | -0.050 |
brist | -0.049 |
blush | -0.048 |
Token | of |
Token ID | 286 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
aro | +0.060 |
captains | +0.060 |
boats | +0.060 |
sailors | +0.058 |
boat | +0.058 |
Neg logit contributions | |
blonde | -0.056 |
Her | -0.050 |
blush | -0.049 |
She | -0.048 |
brist | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
sailors | +0.047 |
aro | +0.045 |
boat | +0.044 |
captains | +0.044 |
boats | +0.044 |
Neg logit contributions | |
blonde | -0.059 |
blush | -0.051 |
brist | -0.051 |
Her | -0.049 |
oph | -0.049 |
Token | bushes |
Token ID | 37413 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
aro | +0.041 |
ug | +0.038 |
sailors | +0.033 |
whales | +0.031 |
ull | +0.031 |
Neg logit contributions | |
blonde | -0.073 |
makeup | -0.066 |
blush | -0.065 |
brow | -0.065 |
brist | -0.065 |
Token | One |
Token ID | 3198 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
sailors | +0.045 |
boat | +0.043 |
boats | +0.043 |
sharks | +0.042 |
whales | +0.042 |
Neg logit contributions | |
blonde | -0.030 |
Her | -0.024 |
oph | -0.024 |
uct | -0.024 |
blush | -0.023 |
Token | day |
Token ID | 1110 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
aro | +0.047 |
sailors | +0.046 |
captains | +0.044 |
boats | +0.043 |
ug | +0.043 |
Neg logit contributions | |
blonde | -0.041 |
pron | -0.034 |
Her | -0.034 |
blush | -0.033 |
oph | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
sailors | +0.058 |
boat | +0.057 |
boats | +0.057 |
captains | +0.056 |
aro | +0.055 |
Neg logit contributions | |
blonde | -0.054 |
blush | -0.045 |
Her | -0.045 |
brist | -0.042 |
makeup | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
sailors | +0.048 |
boat | +0.047 |
ug | +0.047 |
boats | +0.046 |
aro | +0.046 |
Neg logit contributions | |
blonde | -0.053 |
blush | -0.045 |
Her | -0.044 |
brist | -0.043 |
oph | -0.042 |
Token | two |
Token ID | 734 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
aro | +0.114 |
ug | +0.112 |
boat | +0.103 |
boats | +0.099 |
afloat | +0.099 |
Neg logit contributions | |
blonde | -0.106 |
blush | -0.092 |
makeup | -0.088 |
oph | -0.085 |
pron | -0.085 |
Token | teams |
Token ID | 3466 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
aro | +0.119 |
boat | +0.114 |
afloat | +0.113 |
boom | +0.109 |
boats | +0.107 |
Neg logit contributions | |
blonde | -0.122 |
oph | -0.111 |
Her | -0.104 |
blush | -0.102 |
makeup | -0.095 |
Token | decided |
Token ID | 3066 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
aro | +0.227 |
sailors | +0.220 |
sharks | +0.214 |
ug | +0.210 |
whales | +0.210 |
Neg logit contributions | |
blonde | -0.110 |
blush | -0.094 |
Her | -0.087 |
oph | -0.084 |
brushed | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
sailors | +0.021 |
aro | +0.021 |
ug | +0.020 |
boat | +0.020 |
boat | +0.020 |
Neg logit contributions | |
blonde | -0.012 |
blush | -0.009 |
Her | -0.009 |
brist | -0.009 |
oph | -0.009 |
Token | enter |
Token ID | 3802 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
aro | +0.080 |
sailors | +0.079 |
sharks | +0.078 |
ug | +0.077 |
boats | +0.076 |
Neg logit contributions | |
blonde | -0.072 |
blush | -0.064 |
Her | -0.062 |
makeup | -0.059 |
unw | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
aro | +0.069 |
sailors | +0.068 |
boat | +0.067 |
captains | +0.066 |
ug | +0.066 |
Neg logit contributions | |
blonde | -0.063 |
makeup | -0.052 |
blush | -0.052 |
Her | -0.052 |
brist | -0.049 |
Token | race |
Token ID | 3234 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
aro | +0.050 |
sailors | +0.048 |
ug | +0.048 |
ull | +0.043 |
boat | +0.043 |
Neg logit contributions | |
blonde | -0.052 |
oph | -0.045 |
pron | -0.045 |
makeup | -0.044 |
blush | -0.044 |
Token | But |
Token ID | 1537 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
sailors | +0.048 |
aro | +0.047 |
boat | +0.047 |
boats | +0.046 |
ug | +0.046 |
Neg logit contributions | |
blonde | -0.021 |
Just | -0.017 |
brist | -0.017 |
Her | -0.016 |
oph | -0.016 |
Token | then |
Token ID | 788 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
sailors | +0.061 |
boat | +0.060 |
boats | +0.059 |
ug | +0.059 |
captains | +0.058 |
Neg logit contributions | |
blonde | -0.047 |
blush | -0.042 |
Her | -0.039 |
brist | -0.039 |
oph | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
boat | +0.048 |
boats | +0.045 |
aro | +0.044 |
ug | +0.044 |
sailors | +0.043 |
Neg logit contributions | |
blonde | -0.039 |
blush | -0.034 |
Her | -0.033 |
makeup | -0.031 |
She | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
boat | +0.044 |
ug | +0.044 |
boats | +0.043 |
aro | +0.042 |
sailors | +0.042 |
Neg logit contributions | |
blonde | -0.055 |
blush | -0.051 |
Her | -0.048 |
makeup | -0.047 |
oph | -0.045 |
Token | big |
Token ID | 1263 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
sailors | +0.037 |
aro | +0.036 |
ug | +0.035 |
captains | +0.034 |
boats | +0.034 |
Neg logit contributions | |
blonde | -0.040 |
blush | -0.035 |
brist | -0.034 |
pron | -0.032 |
fru | -0.032 |
Token | truck |
Token ID | 7779 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
aro | +0.032 |
sailors | +0.031 |
captains | +0.031 |
boats | +0.030 |
ug | +0.030 |
Neg logit contributions | |
blonde | -0.037 |
blush | -0.034 |
brist | -0.033 |
makeup | -0.031 |
fru | -0.030 |
Token | comes |
Token ID | 2058 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
sailors | +0.212 |
afloat | +0.210 |
aro | +0.209 |
ug | +0.209 |
crew | +0.200 |
Neg logit contributions | |
blonde | -0.095 |
blush | -0.094 |
spat | -0.092 |
Her | -0.092 |
She | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
aro | +0.106 |
boat | +0.101 |
boats | +0.101 |
sailors | +0.100 |
captains | +0.098 |
Neg logit contributions | |
blonde | -0.057 |
brow | -0.052 |
Her | -0.050 |
brist | -0.047 |
She | -0.045 |
Token | It |
Token ID | 632 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
sailors | +0.084 |
aro | +0.083 |
boats | +0.082 |
boat | +0.082 |
captains | +0.082 |
Neg logit contributions | |
blonde | -0.050 |
Her | -0.043 |
blush | -0.040 |
brist | -0.039 |
oph | -0.036 |
Token | drives |
Token ID | 10182 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
sailors | +0.106 |
ug | +0.105 |
aro | +0.104 |
boat | +0.102 |
captains | +0.099 |
Neg logit contributions | |
blonde | -0.058 |
blush | -0.047 |
Her | -0.046 |
brist | -0.046 |
fru | -0.045 |
Token | on |
Token ID | 319 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
sailors | +0.079 |
aro | +0.077 |
boat | +0.075 |
captains | +0.075 |
boats | +0.074 |
Neg logit contributions | |
blonde | -0.069 |
blush | -0.059 |
Her | -0.057 |
brist | -0.057 |
oph | -0.055 |
Token | while |
Token ID | 981 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
aro | +0.048 |
sailors | +0.047 |
ug | +0.046 |
ull | +0.044 |
whales | +0.044 |
Neg logit contributions | |
blonde | -0.042 |
blush | -0.034 |
pron | -0.034 |
brushed | -0.033 |
Her | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
boat | +0.064 |
boats | +0.063 |
captains | +0.063 |
sailors | +0.063 |
aro | +0.062 |
Neg logit contributions | |
blonde | -0.046 |
Her | -0.036 |
blush | -0.034 |
brow | -0.034 |
brist | -0.033 |
Token | but |
Token ID | 475 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
blonde | +0.005 |
blush | +0.004 |
brist | +0.004 |
Her | +0.003 |
brow | +0.003 |
Neg logit contributions | |
aro | -0.008 |
sailors | -0.008 |
boat | -0.008 |
boats | -0.008 |
ug | -0.008 |
Token | then |
Token ID | 788 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
sailors | +0.043 |
captains | +0.041 |
aro | +0.040 |
boats | +0.040 |
boat | +0.040 |
Neg logit contributions | |
blonde | -0.039 |
blush | -0.033 |
Her | -0.033 |
brist | -0.032 |
brow | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
boat | +0.020 |
aro | +0.020 |
boats | +0.020 |
sailors | +0.020 |
ug | +0.019 |
Neg logit contributions | |
blonde | -0.017 |
blush | -0.015 |
Her | -0.014 |
brist | -0.014 |
oph | -0.013 |
Token | truck |
Token ID | 7779 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
aro | +0.046 |
sailors | +0.044 |
ug | +0.043 |
boats | +0.043 |
boats | +0.042 |
Neg logit contributions | |
blonde | -0.041 |
blush | -0.035 |
brist | -0.034 |
pron | -0.034 |
makeup | -0.032 |
Token | passed |
Token ID | 3804 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
aro | +0.215 |
sailors | +0.212 |
sharks | +0.211 |
whales | +0.209 |
ug | +0.203 |
Neg logit contributions | |
blonde | -0.093 |
Her | -0.084 |
spat | -0.083 |
blush | -0.082 |
brushed | -0.081 |
Token | it |
Token ID | 340 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
sailors | +0.076 |
aro | +0.074 |
boat | +0.073 |
captains | +0.072 |
boats | +0.072 |
Neg logit contributions | |
blonde | -0.064 |
blush | -0.054 |
brist | -0.053 |
Her | -0.052 |
oph | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
sailors | +0.070 |
aro | +0.067 |
whales | +0.065 |
captains | +0.065 |
sharks | +0.064 |
Neg logit contributions | |
blonde | -0.058 |
blush | -0.049 |
Her | -0.049 |
brist | -0.047 |
uct | -0.045 |
Token | The |
Token ID | 383 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
sailors | +0.044 |
boat | +0.042 |
aro | +0.042 |
boats | +0.042 |
sharks | +0.041 |
Neg logit contributions | |
blonde | -0.040 |
blush | -0.035 |
brist | -0.034 |
oph | -0.033 |
Her | -0.033 |
Token | car |
Token ID | 1097 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
aro | +0.080 |
ull | +0.076 |
ug | +0.075 |
whales | +0.072 |
boat | +0.071 |
Neg logit contributions | |
blonde | -0.079 |
makeup | -0.066 |
pron | -0.065 |
blush | -0.065 |
brow | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
sailors | +0.028 |
boat | +0.027 |
captains | +0.027 |
boats | +0.026 |
boats | +0.026 |
Neg logit contributions | |
blonde | -0.017 |
Her | -0.015 |
blush | -0.014 |
brist | -0.014 |
oph | -0.013 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
sailors | +0.019 |
boat | +0.018 |
boats | +0.018 |
sharks | +0.018 |
whales | +0.018 |
Neg logit contributions | |
blonde | -0.015 |
Her | -0.012 |
blush | -0.012 |
brist | -0.012 |
oph | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
sailors | +0.013 |
boat | +0.012 |
aro | +0.012 |
captains | +0.012 |
boats | +0.012 |
Neg logit contributions | |
blonde | -0.012 |
blush | -0.011 |
Her | -0.010 |
brist | -0.010 |
makeup | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
sailors | +0.013 |
aro | +0.012 |
boat | +0.012 |
boat | +0.012 |
ug | +0.012 |
Neg logit contributions | |
blonde | -0.012 |
blush | -0.011 |
brist | -0.010 |
Her | -0.010 |
oph | -0.010 |
Token | big |
Token ID | 1263 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
aro | +0.049 |
sailors | +0.049 |
ug | +0.046 |
boats | +0.046 |
captains | +0.046 |
Neg logit contributions | |
blonde | -0.054 |
blush | -0.046 |
brist | -0.045 |
pron | -0.044 |
makeup | -0.042 |
Token | truck |
Token ID | 7779 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
aro | +0.041 |
sailors | +0.040 |
captains | +0.039 |
boats | +0.037 |
boat | +0.037 |
Neg logit contributions | |
blonde | -0.046 |
blush | -0.042 |
brist | -0.041 |
makeup | -0.039 |
lipstick | -0.037 |
Token | came |
Token ID | 1625 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
sailors | +0.225 |
aro | +0.220 |
ug | +0.216 |
sharks | +0.215 |
afloat | +0.214 |
Neg logit contributions | |
blonde | -0.089 |
blush | -0.085 |
Her | -0.085 |
spat | -0.082 |
She | -0.077 |
Token | out |
Token ID | 503 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
aro | +0.096 |
sailors | +0.093 |
boats | +0.092 |
boat | +0.092 |
captains | +0.091 |
Neg logit contributions | |
blonde | -0.059 |
Her | -0.053 |
brow | -0.050 |
brist | -0.049 |
She | -0.047 |
Token | of |
Token ID | 286 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
boat | +0.063 |
boats | +0.062 |
aro | +0.062 |
captains | +0.061 |
boat | +0.060 |
Neg logit contributions | |
blonde | -0.052 |
She | -0.049 |
Her | -0.049 |
brist | -0.046 |
her | -0.046 |
Token | nowhere |
Token ID | 12062 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
sailors | +0.040 |
aro | +0.038 |
boat | +0.038 |
boats | +0.037 |
captains | +0.037 |
Neg logit contributions | |
blonde | -0.058 |
blush | -0.051 |
brist | -0.050 |
Her | -0.049 |
oph | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
sailors | +0.036 |
captains | +0.035 |
aro | +0.034 |
boats | +0.034 |
boat | +0.034 |
Neg logit contributions | |
blonde | -0.025 |
blush | -0.021 |
Her | -0.021 |
brist | -0.021 |
makeup | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
blonde | +0.063 |
pron | +0.061 |
wrapper | +0.060 |
oph | +0.059 |
sweets | +0.057 |
Neg logit contributions | |
boats | -0.056 |
boat | -0.055 |
ug | -0.053 |
sailors | -0.053 |
sail | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
blonde | +0.040 |
blush | +0.034 |
brist | +0.033 |
oph | +0.033 |
fru | +0.032 |
Neg logit contributions | |
sailors | -0.034 |
aro | -0.034 |
boat | -0.033 |
boats | -0.032 |
ug | -0.032 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
blonde | +0.060 |
blush | +0.051 |
oph | +0.049 |
brist | +0.048 |
fru | +0.048 |
Neg logit contributions | |
sailors | -0.064 |
aro | -0.064 |
boat | -0.063 |
ug | -0.062 |
boats | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
blonde | +0.053 |
blush | +0.047 |
oph | +0.046 |
brist | +0.046 |
uct | +0.046 |
Neg logit contributions | |
sailors | -0.033 |
boat | -0.032 |
boats | -0.031 |
aro | -0.031 |
ug | -0.030 |
Token | big |
Token ID | 1263 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
aro | +0.048 |
sailors | +0.046 |
ug | +0.045 |
boats | +0.045 |
boats | +0.045 |
Neg logit contributions | |
blonde | -0.042 |
blush | -0.036 |
brist | -0.035 |
pron | -0.034 |
fru | -0.033 |
Token | boat |
Token ID | 8848 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
aro | +0.036 |
captains | +0.033 |
boats | +0.033 |
ug | +0.032 |
sailors | +0.032 |
Neg logit contributions | |
blonde | -0.044 |
blush | -0.040 |
brist | -0.039 |
fru | -0.037 |
makeup | -0.037 |
Token | came |
Token ID | 1625 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
sailors | +0.214 |
sharks | +0.212 |
ug | +0.209 |
aro | +0.208 |
whales | +0.203 |
Neg logit contributions | |
blonde | -0.075 |
unw | -0.073 |
spat | -0.073 |
brow | -0.069 |
brushed | -0.068 |
Token | to |
Token ID | 284 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
aro | +0.061 |
sailors | +0.060 |
boats | +0.059 |
sharks | +0.058 |
boat | +0.058 |
Neg logit contributions | |
blonde | -0.049 |
Her | -0.044 |
brist | -0.041 |
blush | -0.041 |
brow | -0.040 |
Token | save |
Token ID | 3613 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
blonde | +0.007 |
blush | +0.006 |
brist | +0.005 |
oph | +0.005 |
Her | +0.005 |
Neg logit contributions | |
sailors | -0.008 |
boat | -0.007 |
aro | -0.007 |
boats | -0.007 |
sharks | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
blonde | +0.025 |
blush | +0.020 |
brist | +0.019 |
oph | +0.019 |
pron | +0.018 |
Neg logit contributions | |
sailors | -0.033 |
aro | -0.032 |
boats | -0.032 |
boat | -0.031 |
sharks | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
blonde | +0.007 |
blush | +0.006 |
Her | +0.006 |
brist | +0.006 |
makeup | +0.006 |
Neg logit contributions | |
aro | -0.009 |
sailors | -0.008 |
boats | -0.008 |
ug | -0.008 |
boat | -0.008 |
Token | Just |
Token ID | 5703 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
blonde | +0.016 |
blush | +0.014 |
brist | +0.013 |
oph | +0.013 |
Her | +0.013 |
Neg logit contributions | |
sailors | -0.016 |
boat | -0.015 |
aro | -0.015 |
boats | -0.015 |
captains | -0.014 |
Token | then |
Token ID | 788 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
blonde | +0.018 |
blush | +0.015 |
brist | +0.015 |
oph | +0.014 |
Her | +0.014 |
Neg logit contributions | |
sailors | -0.021 |
aro | -0.021 |
captains | -0.020 |
boats | -0.020 |
boat | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
blonde | +0.003 |
blush | +0.003 |
brist | +0.003 |
Her | +0.003 |
oph | +0.003 |
Neg logit contributions | |
sailors | -0.003 |
aro | -0.003 |
boat | -0.003 |
boat | -0.003 |
boats | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
sailors | +0.009 |
boat | +0.008 |
aro | +0.008 |
boats | +0.008 |
sharks | +0.008 |
Neg logit contributions | |
blonde | -0.010 |
blush | -0.008 |
brist | -0.008 |
oph | -0.008 |
Her | -0.008 |
Token | big |
Token ID | 1263 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
aro | +0.052 |
ug | +0.049 |
sailors | +0.049 |
boats | +0.048 |
boats | +0.048 |
Neg logit contributions | |
blonde | -0.042 |
blush | -0.035 |
brist | -0.034 |
pron | -0.033 |
makeup | -0.032 |
Token | boat |
Token ID | 8848 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
aro | +0.053 |
captains | +0.048 |
sailors | +0.048 |
boats | +0.047 |
ug | +0.047 |
Neg logit contributions | |
blonde | -0.050 |
blush | -0.045 |
brist | -0.043 |
makeup | -0.043 |
fru | -0.041 |
Token | came |
Token ID | 1625 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
sailors | +0.207 |
sharks | +0.207 |
aro | +0.202 |
whales | +0.198 |
ug | +0.195 |
Neg logit contributions | |
spat | -0.074 |
blonde | -0.074 |
brushed | -0.069 |
wasn | -0.068 |
brow | -0.067 |
Token | by |
Token ID | 416 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
aro | +0.078 |
sailors | +0.076 |
sharks | +0.075 |
boats | +0.074 |
captains | +0.074 |
Neg logit contributions | |
blonde | -0.052 |
Her | -0.046 |
brow | -0.045 |
brist | -0.042 |
She | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
blonde | +0.009 |
blush | +0.008 |
brist | +0.008 |
Her | +0.007 |
oph | +0.007 |
Neg logit contributions | |
sailors | -0.009 |
aro | -0.009 |
boat | -0.009 |
boats | -0.009 |
captains | -0.009 |
Token | saved |
Token ID | 7448 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
sailors | +0.033 |
ug | +0.031 |
aro | +0.031 |
captains | +0.031 |
boats | +0.031 |
Neg logit contributions | |
blonde | -0.034 |
blush | -0.030 |
brist | -0.029 |
Her | -0.029 |
oph | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
sailors | +0.006 |
boats | +0.006 |
boat | +0.006 |
aro | +0.006 |
sharks | +0.006 |
Neg logit contributions | |
blonde | -0.010 |
blush | -0.009 |
brist | -0.008 |
Her | -0.008 |
oph | -0.008 |
Token | two |
Token ID | 734 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
aro | +0.033 |
sailors | +0.033 |
boat | +0.033 |
boats | +0.033 |
boat | +0.032 |
Neg logit contributions | |
blonde | -0.038 |
blush | -0.032 |
Her | -0.032 |
oph | -0.031 |
brist | -0.031 |
Token | teams |
Token ID | 3466 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
boat | +0.057 |
aro | +0.054 |
boats | +0.052 |
sailors | +0.050 |
afloat | +0.049 |
Neg logit contributions | |
blonde | -0.062 |
blush | -0.050 |
Her | -0.050 |
brist | -0.049 |
brow | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
aro | +0.177 |
sailors | +0.168 |
afloat | +0.167 |
sharks | +0.166 |
boats | +0.165 |
Neg logit contributions | |
blonde | -0.115 |
Her | -0.105 |
blush | -0.097 |
makeup | -0.093 |
She | -0.089 |
Token | The |
Token ID | 383 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
aro | +0.124 |
sailors | +0.124 |
boat | +0.122 |
boat | +0.121 |
ug | +0.119 |
Neg logit contributions | |
blonde | -0.081 |
Her | -0.068 |
blush | -0.062 |
blond | -0.058 |
She | -0.057 |
Token | two |
Token ID | 734 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
aro | +0.120 |
ug | +0.102 |
ull | +0.096 |
boat | +0.092 |
aroo | +0.090 |
Neg logit contributions | |
blonde | -0.129 |
blush | -0.115 |
Her | -0.111 |
makeup | -0.107 |
oph | -0.107 |
Token | teams |
Token ID | 3466 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
aro | +0.147 |
boat | +0.130 |
afloat | +0.130 |
explode | +0.127 |
ferry | +0.125 |
Neg logit contributions | |
blonde | -0.131 |
Her | -0.112 |
blush | -0.110 |
oph | -0.102 |
makeup | -0.102 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
aro | +0.225 |
sailors | +0.213 |
sharks | +0.211 |
ug | +0.209 |
whales | +0.207 |
Neg logit contributions | |
blonde | -0.107 |
blush | -0.095 |
Her | -0.092 |
brushed | -0.081 |
makeup | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
aro | +0.146 |
ug | +0.140 |
boat | +0.140 |
sailors | +0.136 |
afloat | +0.133 |
Neg logit contributions | |
blonde | -0.035 |
Her | -0.024 |
makeup | -0.023 |
blush | -0.021 |
brushed | -0.018 |
Token | have |
Token ID | 423 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
aro | +0.118 |
ug | +0.113 |
sailors | +0.113 |
boats | +0.110 |
sharks | +0.109 |
Neg logit contributions | |
blonde | -0.086 |
blush | -0.082 |
Her | -0.082 |
unw | -0.073 |
makeup | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
aro | +0.121 |
boat | +0.119 |
ug | +0.117 |
boats | +0.112 |
sailors | +0.111 |
Neg logit contributions | |
blonde | -0.082 |
makeup | -0.065 |
blush | -0.063 |
blond | -0.060 |
Her | -0.058 |
Token | bouncing |
Token ID | 30713 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
aro | +0.088 |
ug | +0.083 |
sailors | +0.083 |
ull | +0.077 |
boat | +0.076 |
Neg logit contributions | |
blonde | -0.112 |
pron | -0.102 |
blush | -0.100 |
makeup | -0.098 |
Her | -0.094 |
Token | sad |
Token ID | 6507 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
sailors | +0.043 |
aro | +0.042 |
boat | +0.041 |
boats | +0.041 |
boat | +0.041 |
Neg logit contributions | |
blonde | -0.045 |
blush | -0.039 |
brist | -0.038 |
Her | -0.037 |
oph | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
sailors | +0.039 |
aro | +0.039 |
boat | +0.038 |
captains | +0.037 |
boat | +0.037 |
Neg logit contributions | |
blonde | -0.038 |
blush | -0.034 |
brist | -0.033 |
Her | -0.033 |
makeup | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
sailors | +0.077 |
boat | +0.075 |
aro | +0.074 |
boat | +0.074 |
boats | +0.073 |
Neg logit contributions | |
blonde | -0.077 |
Her | -0.069 |
blush | -0.064 |
brist | -0.064 |
She | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
sailors | +0.079 |
boats | +0.078 |
captains | +0.078 |
boat | +0.078 |
boat | +0.076 |
Neg logit contributions | |
Her | -0.030 |
blonde | -0.028 |
She | -0.023 |
brist | -0.023 |
blush | -0.022 |
Token | A |
Token ID | 32 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
sharks | +0.079 |
sailors | +0.078 |
ship | +0.077 |
boats | +0.077 |
boat | +0.077 |
Neg logit contributions | |
Just | -0.030 |
blonde | -0.030 |
Her | -0.028 |
Her | -0.028 |
brist | -0.028 |
Token | cop |
Token ID | 2243 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
sailors | +0.057 |
aro | +0.056 |
boats | +0.054 |
sharks | +0.053 |
ug | +0.053 |
Neg logit contributions | |
blonde | -0.050 |
blush | -0.044 |
brist | -0.042 |
pron | -0.042 |
oph | -0.040 |
Token | sees |
Token ID | 7224 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
ug | +0.192 |
sailors | +0.191 |
boat | +0.189 |
aro | +0.189 |
ull | +0.184 |
Neg logit contributions | |
blonde | -0.136 |
blush | -0.129 |
Her | -0.123 |
makeup | -0.112 |
unw | -0.109 |
Token | them |
Token ID | 606 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
boat | +0.105 |
afloat | +0.101 |
captains | +0.096 |
sailors | +0.096 |
boats | +0.095 |
Neg logit contributions | |
blonde | -0.077 |
blush | -0.073 |
makeup | -0.073 |
Her | -0.073 |
her | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
sailors | +0.035 |
aro | +0.034 |
boat | +0.033 |
captains | +0.033 |
ug | +0.032 |
Neg logit contributions | |
blonde | -0.027 |
blush | -0.025 |
Her | -0.024 |
brist | -0.023 |
makeup | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
sailors | +0.104 |
captains | +0.099 |
aro | +0.099 |
boat | +0.098 |
boats | +0.098 |
Neg logit contributions | |
blonde | -0.068 |
Her | -0.059 |
blush | -0.055 |
brist | -0.053 |
She | -0.052 |
Token | is |
Token ID | 318 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
sailors | +0.036 |
boat | +0.034 |
aro | +0.034 |
boats | +0.034 |
sharks | +0.034 |
Neg logit contributions | |
blonde | -0.036 |
blush | -0.031 |
brist | -0.030 |
oph | -0.030 |
Her | -0.029 |
Token | castle |
Token ID | 16669 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
blonde | +0.017 |
blush | +0.015 |
brist | +0.014 |
oph | +0.014 |
Her | +0.014 |
Neg logit contributions | |
sailors | -0.015 |
boat | -0.015 |
aro | -0.014 |
boats | -0.014 |
sharks | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
blonde | +0.004 |
blush | +0.004 |
brist | +0.004 |
oph | +0.004 |
Her | +0.004 |
Neg logit contributions | |
sailors | -0.004 |
boat | -0.004 |
aro | -0.004 |
boats | -0.004 |
sharks | -0.004 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
sailors | +0.016 |
aro | +0.015 |
boat | +0.015 |
boats | +0.015 |
sharks | +0.015 |
Neg logit contributions | |
blonde | -0.011 |
blush | -0.010 |
brist | -0.009 |
oph | -0.009 |
pron | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
sailors | +0.011 |
aro | +0.010 |
boat | +0.010 |
captains | +0.010 |
boat | +0.010 |
Neg logit contributions | |
blonde | -0.012 |
blush | -0.010 |
brist | -0.010 |
Her | -0.010 |
oph | -0.010 |
Token | big |
Token ID | 1263 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
sailors | +0.032 |
aro | +0.031 |
boats | +0.030 |
ug | +0.030 |
captains | +0.029 |
Neg logit contributions | |
blonde | -0.037 |
blush | -0.032 |
brist | -0.031 |
oph | -0.030 |
pron | -0.030 |
Token | truck |
Token ID | 7779 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
sailors | +0.032 |
aro | +0.032 |
captains | +0.031 |
ug | +0.030 |
boats | +0.030 |
Neg logit contributions | |
blonde | -0.039 |
blush | -0.035 |
brist | -0.034 |
makeup | -0.032 |
pron | -0.032 |
Token | drove |
Token ID | 10357 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
sailors | +0.202 |
aro | +0.197 |
ug | +0.193 |
sharks | +0.192 |
captains | +0.190 |
Neg logit contributions | |
blonde | -0.109 |
blush | -0.105 |
Her | -0.100 |
spat | -0.095 |
unw | -0.095 |
Token | up |
Token ID | 510 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
sailors | +0.076 |
aro | +0.073 |
boat | +0.072 |
boats | +0.071 |
sharks | +0.071 |
Neg logit contributions | |
blonde | -0.068 |
blush | -0.058 |
brist | -0.056 |
Her | -0.055 |
oph | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
sailors | +0.060 |
aro | +0.058 |
boat | +0.057 |
captains | +0.057 |
boats | +0.056 |
Neg logit contributions | |
blonde | -0.049 |
blush | -0.041 |
brist | -0.040 |
Her | -0.039 |
oph | -0.039 |
Token | stopped |
Token ID | 5025 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
sailors | +0.029 |
aro | +0.028 |
boat | +0.028 |
boats | +0.027 |
sharks | +0.027 |
Neg logit contributions | |
blonde | -0.028 |
blush | -0.024 |
brist | -0.023 |
oph | -0.023 |
Her | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
boat | +0.048 |
aro | +0.047 |
boats | +0.046 |
sailors | +0.046 |
captains | +0.046 |
Neg logit contributions | |
blonde | -0.040 |
Her | -0.033 |
blush | -0.033 |
brist | -0.032 |
makeup | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
blonde | +0.002 |
blush | +0.002 |
Her | +0.002 |
makeup | +0.002 |
oph | +0.002 |
Neg logit contributions | |
aro | -0.003 |
sailors | -0.003 |
captains | -0.003 |
whales | -0.003 |
sharks | -0.003 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
sailors | +0.056 |
boat | +0.053 |
boats | +0.052 |
aro | +0.052 |
sharks | +0.052 |
Neg logit contributions | |
blonde | -0.055 |
blush | -0.048 |
brist | -0.047 |
oph | -0.045 |
Her | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
boat | +0.071 |
aro | +0.071 |
boats | +0.070 |
sailors | +0.068 |
amer | +0.068 |
Neg logit contributions | |
blonde | -0.039 |
Her | -0.031 |
blush | -0.028 |
brist | -0.027 |
brow | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ug | +0.063 |
ile | +0.062 |
aro | +0.062 |
boats | +0.059 |
boat | +0.058 |
Neg logit contributions | |
blonde | -0.045 |
her | -0.041 |
blush | -0.040 |
Her | -0.038 |
brow | -0.037 |
Token | big |
Token ID | 1263 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
aro | +0.037 |
sailors | +0.036 |
ug | +0.035 |
boats | +0.034 |
boats | +0.034 |
Neg logit contributions | |
blonde | -0.038 |
blush | -0.032 |
brist | -0.031 |
pron | -0.031 |
fru | -0.029 |
Token | truck |
Token ID | 7779 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
aro | +0.038 |
sailors | +0.035 |
captains | +0.034 |
boats | +0.033 |
ug | +0.033 |
Neg logit contributions | |
blonde | -0.043 |
blush | -0.037 |
brist | -0.037 |
makeup | -0.035 |
fru | -0.034 |
Token | drove |
Token ID | 10357 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
sailors | +0.196 |
aro | +0.195 |
sharks | +0.191 |
whales | +0.190 |
captains | +0.186 |
Neg logit contributions | |
blonde | -0.113 |
blush | -0.101 |
unw | -0.098 |
brushed | -0.095 |
spat | -0.094 |
Token | by |
Token ID | 416 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
sailors | +0.096 |
aro | +0.096 |
whales | +0.092 |
sharks | +0.092 |
captains | +0.091 |
Neg logit contributions | |
blonde | -0.069 |
blush | -0.056 |
brow | -0.055 |
brist | -0.055 |
Her | -0.055 |
Token | with |
Token ID | 351 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
sailors | +0.024 |
captains | +0.024 |
aro | +0.024 |
boats | +0.024 |
boat | +0.023 |
Neg logit contributions | |
blonde | -0.016 |
brist | -0.013 |
brow | -0.012 |
blush | -0.012 |
Her | -0.012 |
Token | its |
Token ID | 663 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
aro | +0.113 |
boat | +0.109 |
ug | +0.108 |
sailors | +0.108 |
captains | +0.105 |
Neg logit contributions | |
blonde | -0.093 |
blush | -0.072 |
brist | -0.070 |
Her | -0.070 |
brow | -0.069 |
Token | horn |
Token ID | 12718 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
aro | +0.046 |
ug | +0.044 |
boat | +0.044 |
sailors | +0.043 |
boats | +0.042 |
Neg logit contributions | |
blonde | -0.042 |
Her | -0.034 |
brow | -0.034 |
brist | -0.033 |
blush | -0.033 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
sailors | +0.005 |
boat | +0.005 |
boats | +0.005 |
whales | +0.005 |
sharks | +0.005 |
Neg logit contributions | |
blonde | -0.005 |
Her | -0.004 |
blush | -0.004 |
brist | -0.004 |
makeup | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
sailors | +0.013 |
aro | +0.012 |
boat | +0.012 |
boats | +0.012 |
captains | +0.012 |
Neg logit contributions | |
blonde | -0.010 |
blush | -0.009 |
brist | -0.009 |
Her | -0.009 |
oph | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
sailors | +0.014 |
captains | +0.014 |
boats | +0.013 |
boats | +0.013 |
boat | +0.013 |
Neg logit contributions | |
blonde | -0.008 |
Her | -0.007 |
brist | -0.006 |
oph | -0.006 |
blush | -0.006 |
Token | So |
Token ID | 2396 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
blonde | +0.003 |
brist | +0.002 |
Her | +0.002 |
oph | +0.002 |
blush | +0.002 |
Neg logit contributions | |
sailors | -0.003 |
aro | -0.003 |
boats | -0.003 |
boat | -0.003 |
boats | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
sailors | +0.034 |
captains | +0.033 |
boats | +0.033 |
boat | +0.032 |
aro | +0.032 |
Neg logit contributions | |
blonde | -0.032 |
Her | -0.027 |
brist | -0.026 |
blush | -0.026 |
brow | -0.025 |
Token | ships |
Token ID | 7937 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
ug | +0.095 |
aro | +0.095 |
boat | +0.088 |
boats | +0.087 |
ites | +0.087 |
Neg logit contributions | |
blonde | -0.060 |
Tooth | -0.048 |
me | -0.048 |
makeup | -0.047 |
brist | -0.045 |
Token | started |
Token ID | 2067 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
sharks | +0.154 |
aro | +0.148 |
polar | +0.144 |
whales | +0.141 |
sailors | +0.140 |
Neg logit contributions | |
brushed | -0.128 |
blonde | -0.117 |
chose | -0.116 |
unw | -0.111 |
blush | -0.111 |
Token | their |
Token ID | 511 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
boat | +0.103 |
aro | +0.102 |
ile | +0.102 |
sailors | +0.101 |
boats | +0.100 |
Neg logit contributions | |
blonde | -0.039 |
Her | -0.030 |
blush | -0.025 |
brushed | -0.024 |
brist | -0.024 |
Token | race |
Token ID | 3234 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
ull | +0.061 |
aro | +0.061 |
ile | +0.054 |
boat | +0.053 |
sailors | +0.052 |
Neg logit contributions | |
blonde | -0.080 |
brow | -0.070 |
unw | -0.066 |
Her | -0.064 |
blond | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
aro | +0.127 |
whales | +0.122 |
sharks | +0.118 |
ull | +0.116 |
polar | +0.116 |
Neg logit contributions | |
blonde | -0.064 |
Her | -0.052 |
brow | -0.051 |
unw | -0.048 |
She | -0.048 |
Token | Little |
Token ID | 7703 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
sailors | +0.027 |
aro | +0.026 |
boat | +0.026 |
boat | +0.026 |
boats | +0.026 |
Neg logit contributions | |
blonde | -0.026 |
Her | -0.022 |
blush | -0.021 |
brist | -0.021 |
oph | -0.020 |
Token | now |
Token ID | 783 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
sailors | +0.043 |
aro | +0.041 |
captains | +0.041 |
ug | +0.041 |
boat | +0.040 |
Neg logit contributions | |
blonde | -0.029 |
Her | -0.024 |
blush | -0.024 |
makeup | -0.023 |
brist | -0.023 |
Token | ." |
Token ID | 526 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
sailors | +0.013 |
aro | +0.012 |
boat | +0.012 |
boats | +0.012 |
sharks | +0.012 |
Neg logit contributions | |
blonde | -0.016 |
blush | -0.014 |
brist | -0.013 |
Her | -0.013 |
oph | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
sailors | +0.050 |
boat | +0.048 |
aro | +0.048 |
boats | +0.047 |
sharks | +0.047 |
Neg logit contributions | |
blonde | -0.047 |
blush | -0.041 |
brist | -0.040 |
oph | -0.039 |
Her | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
sailors | +0.052 |
captains | +0.051 |
boats | +0.050 |
boats | +0.050 |
boat | +0.050 |
Neg logit contributions | |
blonde | -0.029 |
Her | -0.026 |
blush | -0.024 |
brist | -0.023 |
oph | -0.022 |
Token | The |
Token ID | 464 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
sailors | +0.059 |
boats | +0.059 |
boat | +0.057 |
whales | +0.057 |
sharks | +0.057 |
Neg logit contributions | |
blonde | -0.037 |
Her | -0.032 |
blush | -0.030 |
brist | -0.030 |
She | -0.028 |
Token | zo |
Token ID | 40565 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
ug | +0.088 |
boat | +0.084 |
afloat | +0.083 |
aro | +0.082 |
boats | +0.081 |
Neg logit contributions | |
blonde | -0.083 |
makeup | -0.078 |
fru | -0.077 |
blush | -0.076 |
brist | -0.076 |
Token | oke |
Token ID | 2088 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
afloat | +0.193 |
raft | +0.185 |
sail | +0.171 |
dock | +0.168 |
sailors | +0.167 |
Neg logit contributions | |
Her | -0.116 |
blush | -0.112 |
blonde | -0.108 |
She | -0.105 |
omm | -0.099 |
Token | eper |
Token ID | 5723 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
afloat | +0.057 |
sail | +0.053 |
boats | +0.052 |
raft | +0.052 |
dock | +0.052 |
Neg logit contributions | |
blonde | -0.086 |
Her | -0.085 |
brist | -0.084 |
omm | -0.083 |
brow | -0.083 |
Token | catches |
Token ID | 17591 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
sailors | +0.095 |
aro | +0.092 |
boat | +0.091 |
boats | +0.090 |
ug | +0.090 |
Neg logit contributions | |
blonde | -0.064 |
blush | -0.059 |
Her | -0.055 |
brist | -0.054 |
oph | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
sailors | +0.054 |
boat | +0.053 |
aro | +0.052 |
captains | +0.052 |
ug | +0.050 |
Neg logit contributions | |
blonde | -0.050 |
blush | -0.045 |
Her | -0.043 |
brist | -0.043 |
oph | -0.043 |
Token | crocod |
Token ID | 37565 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
ug | +0.052 |
aro | +0.049 |
boat | +0.045 |
sailors | +0.044 |
boats | +0.042 |
Neg logit contributions | |
blonde | -0.091 |
fru | -0.088 |
spat | -0.086 |
makeup | -0.085 |
brist | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
sailors | +0.115 |
whales | +0.112 |
aro | +0.109 |
ull | +0.107 |
sharks | +0.107 |
Neg logit contributions | |
blonde | -0.059 |
Her | -0.055 |
She | -0.052 |
blush | -0.045 |
oph | -0.043 |
Token | Spot |
Token ID | 15899 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
sailors | +0.048 |
captains | +0.045 |
aro | +0.044 |
boat | +0.044 |
ug | +0.044 |
Neg logit contributions | |
blonde | -0.050 |
Her | -0.042 |
blush | -0.042 |
brow | -0.040 |
brist | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
sailors | +0.055 |
aro | +0.054 |
boats | +0.052 |
boat | +0.052 |
sharks | +0.051 |
Neg logit contributions | |
blonde | -0.033 |
blush | -0.026 |
Her | -0.026 |
brist | -0.026 |
oph | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
sailors | +0.034 |
aro | +0.032 |
boat | +0.031 |
captains | +0.031 |
boats | +0.031 |
Neg logit contributions | |
blonde | -0.044 |
blush | -0.039 |
Her | -0.038 |
brist | -0.038 |
oph | -0.037 |
Token | other |
Token ID | 584 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
aro | +0.074 |
ug | +0.070 |
sailors | +0.069 |
whales | +0.067 |
ull | +0.067 |
Neg logit contributions | |
blonde | -0.085 |
brist | -0.073 |
blush | -0.071 |
brow | -0.069 |
Her | -0.068 |
Token | dogs |
Token ID | 6844 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
aro | +0.108 |
ull | +0.100 |
afloat | +0.098 |
boat | +0.096 |
sailors | +0.095 |
Neg logit contributions | |
blonde | -0.084 |
She | -0.073 |
Her | -0.068 |
me | -0.067 |
curls | -0.067 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
sailors | +0.210 |
sharks | +0.205 |
ull | +0.204 |
aro | +0.203 |
whales | +0.203 |
Neg logit contributions | |
blonde | -0.100 |
blush | -0.092 |
brushed | -0.087 |
Her | -0.087 |
brow | -0.077 |
Token | very |
Token ID | 845 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
sailors | +0.087 |
whales | +0.086 |
aro | +0.086 |
ull | +0.084 |
whale | +0.081 |
Neg logit contributions | |
blonde | -0.053 |
brow | -0.043 |
blush | -0.043 |
Her | -0.043 |
She | -0.041 |
Token | fast |
Token ID | 3049 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
whales | +0.074 |
ull | +0.073 |
sailors | +0.073 |
crew | +0.069 |
boat | +0.069 |
Neg logit contributions | |
blonde | -0.041 |
brow | -0.040 |
wrink | -0.037 |
unw | -0.034 |
brushed | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
sailors | +0.085 |
aro | +0.084 |
boat | +0.082 |
boat | +0.081 |
captains | +0.080 |
Neg logit contributions | |
blonde | -0.072 |
blush | -0.061 |
brist | -0.059 |
Her | -0.058 |
makeup | -0.056 |
Token | They |
Token ID | 1119 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
sailors | +0.052 |
boat | +0.049 |
aro | +0.049 |
boats | +0.049 |
sharks | +0.048 |
Neg logit contributions | |
blonde | -0.061 |
blush | -0.053 |
brist | -0.052 |
Her | -0.051 |
oph | -0.051 |
Token | cookie |
Token ID | 19751 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
sailors | +0.018 |
aro | +0.017 |
ug | +0.017 |
captains | +0.017 |
boats | +0.017 |
Neg logit contributions | |
blonde | -0.013 |
blush | -0.011 |
brist | -0.010 |
Her | -0.010 |
oph | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
sailors | +0.036 |
aro | +0.034 |
captains | +0.034 |
whales | +0.033 |
ug | +0.033 |
Neg logit contributions | |
blonde | -0.035 |
blush | -0.031 |
brist | -0.030 |
Her | -0.029 |
oph | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
sailors | +0.049 |
aro | +0.046 |
boat | +0.046 |
sharks | +0.046 |
boats | +0.046 |
Neg logit contributions | |
blonde | -0.054 |
blush | -0.048 |
oph | -0.047 |
brist | -0.047 |
pron | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
sailors | +0.065 |
captains | +0.064 |
boats | +0.063 |
boat | +0.062 |
boats | +0.062 |
Neg logit contributions | |
Her | -0.032 |
blonde | -0.032 |
brist | -0.027 |
She | -0.027 |
blush | -0.027 |
Token | The |
Token ID | 464 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
sailors | +0.066 |
boats | +0.066 |
boat | +0.063 |
whales | +0.063 |
captains | +0.062 |
Neg logit contributions | |
blonde | -0.033 |
Her | -0.031 |
Just | -0.030 |
Fe | -0.028 |
uct | -0.028 |
Token | zo |
Token ID | 40565 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
ug | +0.085 |
aro | +0.084 |
boat | +0.071 |
boats | +0.068 |
sailors | +0.063 |
Neg logit contributions | |
pron | -0.094 |
blonde | -0.094 |
fru | -0.090 |
spat | -0.089 |
brist | -0.088 |
Token | oke |
Token ID | 2088 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
afloat | +0.198 |
raft | +0.193 |
dock | +0.171 |
sail | +0.171 |
boats | +0.167 |
Neg logit contributions | |
blush | -0.095 |
Her | -0.095 |
spat | -0.095 |
blonde | -0.093 |
cake | -0.093 |
Token | eper |
Token ID | 5723 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
afloat | +0.079 |
raft | +0.074 |
sail | +0.071 |
dock | +0.071 |
port | +0.070 |
Neg logit contributions | |
brow | -0.092 |
spat | -0.091 |
blonde | -0.090 |
omm | -0.089 |
wrapper | -0.087 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
sailors | +0.105 |
aro | +0.104 |
boats | +0.102 |
boat | +0.101 |
sharks | +0.101 |
Neg logit contributions | |
blonde | -0.052 |
blush | -0.047 |
brushed | -0.044 |
Her | -0.042 |
spat | -0.042 |
Token | what |
Token ID | 644 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
boat | +0.085 |
sailors | +0.085 |
afloat | +0.083 |
ug | +0.083 |
captains | +0.083 |
Neg logit contributions | |
blonde | -0.059 |
blush | -0.056 |
Her | -0.055 |
makeup | -0.054 |
her | -0.053 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
sailors | +0.098 |
aro | +0.095 |
captains | +0.095 |
ug | +0.094 |
boat | +0.094 |
Neg logit contributions | |
blonde | -0.049 |
Her | -0.040 |
blush | -0.039 |
oph | -0.037 |
brushed | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
sailors | +0.031 |
boat | +0.030 |
captains | +0.030 |
boats | +0.030 |
boats | +0.029 |
Neg logit contributions | |
blonde | -0.020 |
Her | -0.017 |
blush | -0.017 |
brist | -0.016 |
oph | -0.016 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
sailors | +0.014 |
boat | +0.013 |
boats | +0.013 |
sharks | +0.013 |
aro | +0.013 |
Neg logit contributions | |
blonde | -0.010 |
blush | -0.008 |
brist | -0.008 |
Her | -0.008 |
oph | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
sailors | +0.035 |
boat | +0.034 |
boats | +0.034 |
captains | +0.034 |
aro | +0.032 |
Neg logit contributions | |
blonde | -0.026 |
Her | -0.021 |
blush | -0.021 |
brist | -0.021 |
makeup | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
sailors | +0.039 |
boat | +0.039 |
boats | +0.038 |
captains | +0.038 |
aro | +0.037 |
Neg logit contributions | |
blonde | -0.036 |
blush | -0.031 |
brist | -0.029 |
Her | -0.029 |
makeup | -0.028 |
Token | big |
Token ID | 1263 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
aro | +0.040 |
sailors | +0.037 |
boats | +0.037 |
ug | +0.037 |
boat | +0.036 |
Neg logit contributions | |
blonde | -0.035 |
pron | -0.029 |
blush | -0.028 |
brist | -0.028 |
fru | -0.027 |
Token | boat |
Token ID | 8848 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
aro | +0.039 |
captains | +0.036 |
boats | +0.036 |
sailors | +0.036 |
ug | +0.035 |
Neg logit contributions | |
blonde | -0.042 |
blush | -0.037 |
brist | -0.036 |
makeup | -0.035 |
fru | -0.035 |
Token | appeared |
Token ID | 4120 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
sailors | +0.235 |
sharks | +0.229 |
ug | +0.223 |
captains | +0.222 |
aro | +0.222 |
Neg logit contributions | |
blonde | -0.051 |
spat | -0.046 |
Her | -0.044 |
brushed | -0.043 |
unw | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
sailors | +0.052 |
aro | +0.052 |
boat | +0.050 |
captains | +0.050 |
boats | +0.049 |
Neg logit contributions | |
blonde | -0.042 |
blush | -0.036 |
brist | -0.036 |
Her | -0.035 |
oph | -0.034 |
Token | It |
Token ID | 632 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
sailors | +0.060 |
aro | +0.058 |
boat | +0.057 |
boat | +0.057 |
captains | +0.057 |
Neg logit contributions | |
blonde | -0.045 |
blush | -0.036 |
brist | -0.036 |
Her | -0.036 |
oph | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
sailors | +0.083 |
aro | +0.082 |
ug | +0.082 |
captains | +0.079 |
boats | +0.079 |
Neg logit contributions | |
blonde | -0.032 |
brushed | -0.025 |
oph | -0.023 |
uct | -0.023 |
fru | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
aro | +0.045 |
sailors | +0.045 |
boat | +0.044 |
ug | +0.043 |
boats | +0.043 |
Neg logit contributions | |
blonde | -0.041 |
brist | -0.033 |
blush | -0.033 |
Her | -0.032 |
brow | -0.031 |
Token | had |
Token ID | 550 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
sailors | +0.145 |
aro | +0.138 |
captains | +0.136 |
ug | +0.136 |
boats | +0.135 |
Neg logit contributions | |
blonde | -0.074 |
blush | -0.059 |
Her | -0.055 |
brist | -0.055 |
brushed | -0.053 |
Token | killed |
Token ID | 2923 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
sailors | +0.086 |
aro | +0.083 |
boat | +0.082 |
boat | +0.081 |
boats | +0.081 |
Neg logit contributions | |
blonde | -0.085 |
blush | -0.072 |
brist | -0.070 |
Her | -0.069 |
oph | -0.067 |
Token | them |
Token ID | 606 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
sailors | +0.052 |
captains | +0.050 |
aro | +0.049 |
boat | +0.048 |
boat | +0.048 |
Neg logit contributions | |
blonde | -0.059 |
blush | -0.050 |
brist | -0.049 |
Her | -0.049 |
oph | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
sailors | +0.027 |
aro | +0.026 |
boat | +0.025 |
captains | +0.025 |
whales | +0.025 |
Neg logit contributions | |
blonde | -0.020 |
Her | -0.017 |
blush | -0.017 |
brist | -0.016 |
makeup | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
sailors | +0.081 |
boat | +0.078 |
aro | +0.078 |
boats | +0.077 |
boat | +0.077 |
Neg logit contributions | |
blonde | -0.068 |
blush | -0.057 |
Her | -0.057 |
brist | -0.055 |
oph | -0.054 |
Token | zo |
Token ID | 40565 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
ug | +0.089 |
aro | +0.085 |
boat | +0.082 |
sailors | +0.078 |
boats | +0.078 |
Neg logit contributions | |
blonde | -0.104 |
blush | -0.091 |
brist | -0.090 |
brow | -0.088 |
makeup | -0.087 |
Token | oke |
Token ID | 2088 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
afloat | +0.185 |
raft | +0.180 |
sail | +0.165 |
dock | +0.161 |
boats | +0.160 |
Neg logit contributions | |
blonde | -0.119 |
Her | -0.109 |
blush | -0.106 |
anna | -0.103 |
spat | -0.101 |
Token | ep |
Token ID | 538 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
afloat | +0.084 |
raft | +0.078 |
sail | +0.078 |
port | +0.077 |
dock | +0.075 |
Neg logit contributions | |
blonde | -0.097 |
brow | -0.094 |
refused | -0.092 |
Her | -0.090 |
spat | -0.090 |
Token | ers |
Token ID | 364 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
sailors | +0.080 |
aro | +0.077 |
boats | +0.076 |
sharks | +0.076 |
boat | +0.076 |
Neg logit contributions | |
blonde | -0.042 |
blush | -0.034 |
brist | -0.034 |
Her | -0.033 |
oph | -0.033 |
Token | shot |
Token ID | 2823 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
sailors | +0.071 |
aro | +0.068 |
boat | +0.067 |
boats | +0.067 |
sharks | +0.066 |
Neg logit contributions | |
blonde | -0.051 |
blush | -0.043 |
brist | -0.041 |
Her | -0.040 |
oph | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
sailors | +0.067 |
aro | +0.065 |
boat | +0.064 |
boat | +0.064 |
captains | +0.064 |
Neg logit contributions | |
blonde | -0.073 |
blush | -0.063 |
brist | -0.062 |
Her | -0.061 |
oph | -0.059 |
Token | you |
Token ID | 345 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
boat | +0.072 |
sailors | +0.071 |
ull | +0.070 |
afloat | +0.069 |
boats | +0.068 |
Neg logit contributions | |
blonde | -0.049 |
Her | -0.041 |
makeup | -0.040 |
blush | -0.040 |
brist | -0.037 |
Token | doing |
Token ID | 1804 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
sailors | +0.007 |
aro | +0.007 |
boat | +0.007 |
boat | +0.007 |
boats | +0.007 |
Neg logit contributions | |
blonde | -0.005 |
blush | -0.004 |
brist | -0.004 |
Her | -0.004 |
oph | -0.004 |
Token | here |
Token ID | 994 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
sailors | +0.019 |
aro | +0.019 |
boat | +0.018 |
captains | +0.018 |
boats | +0.018 |
Neg logit contributions | |
blonde | -0.017 |
blush | -0.015 |
makeup | -0.014 |
brist | -0.014 |
oph | -0.014 |
Token | ?" |
Token ID | 1701 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
sailors | +0.021 |
aro | +0.020 |
boat | +0.019 |
boats | +0.019 |
captains | +0.019 |
Neg logit contributions | |
blonde | -0.023 |
blush | -0.021 |
brist | -0.020 |
oph | -0.020 |
Her | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
sailors | +0.021 |
aro | +0.020 |
boat | +0.020 |
boats | +0.020 |
boat | +0.020 |
Neg logit contributions | |
blonde | -0.024 |
blush | -0.021 |
brist | -0.021 |
Her | -0.020 |
oph | -0.020 |
Token | zo |
Token ID | 40565 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
ug | +0.099 |
afloat | +0.095 |
boats | +0.092 |
boat | +0.092 |
aro | +0.091 |
Neg logit contributions | |
blonde | -0.101 |
Her | -0.092 |
blush | -0.091 |
brist | -0.087 |
makeup | -0.085 |
Token | oke |
Token ID | 2088 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
raft | +0.193 |
afloat | +0.192 |
sail | +0.181 |
boats | +0.180 |
sailors | +0.180 |
Neg logit contributions | |
Her | -0.107 |
blush | -0.106 |
spat | -0.098 |
blonde | -0.097 |
She | -0.097 |
Token | eper |
Token ID | 5723 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
port | +0.083 |
afloat | +0.082 |
sail | +0.081 |
raft | +0.080 |
flood | +0.079 |
Neg logit contributions | |
Her | -0.104 |
brow | -0.102 |
omm | -0.100 |
her | -0.098 |
blush | -0.098 |
Token | asked |
Token ID | 1965 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
sailors | +0.087 |
aro | +0.084 |
boat | +0.084 |
boats | +0.083 |
sharks | +0.083 |
Neg logit contributions | |
blonde | -0.050 |
blush | -0.042 |
Her | -0.040 |
brist | -0.039 |
oph | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
sailors | +0.022 |
aro | +0.021 |
boat | +0.021 |
boat | +0.021 |
captains | +0.021 |
Neg logit contributions | |
blonde | -0.024 |
blush | -0.021 |
Her | -0.020 |
brist | -0.020 |
oph | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
sailors | +0.033 |
boat | +0.032 |
boats | +0.031 |
aro | +0.030 |
sharks | +0.030 |
Neg logit contributions | |
blonde | -0.028 |
blush | -0.024 |
oph | -0.023 |
brist | -0.023 |
uct | -0.022 |
Token | |
Token ID | 220 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
blonde | +0.062 |
blush | +0.062 |
brist | +0.059 |
fru | +0.058 |
pron | +0.057 |
Neg logit contributions | |
boat | -0.030 |
Fin | -0.029 |
sail | -0.028 |
raft | -0.028 |
boats | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
blonde | +0.071 |
blush | +0.064 |
brist | +0.063 |
oph | +0.061 |
fru | +0.059 |
Neg logit contributions | |
sailors | -0.048 |
aro | -0.047 |
ug | -0.047 |
boats | -0.046 |
boat | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
blonde | +0.033 |
blush | +0.030 |
brist | +0.029 |
oph | +0.027 |
fru | +0.027 |
Neg logit contributions | |
sailors | -0.030 |
aro | -0.029 |
boat | -0.029 |
boats | -0.029 |
boat | -0.028 |
Token | â |
Token ID | 22940 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
blonde | +0.052 |
blush | +0.047 |
brist | +0.045 |
fru | +0.044 |
oph | +0.042 |
Neg logit contributions | |
sailors | -0.052 |
boat | -0.051 |
aro | -0.050 |
boat | -0.049 |
boats | -0.049 |
Token | € |
Token ID | 26391 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
blonde | +0.061 |
blush | +0.051 |
brist | +0.048 |
oph | +0.046 |
makeup | +0.045 |
Neg logit contributions | |
boat | -0.074 |
sailors | -0.073 |
ug | -0.072 |
aro | -0.071 |
boat | -0.071 |
Token | � |
Token ID | 129 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
blonde | +0.053 |
blush | +0.047 |
brist | +0.045 |
oph | +0.042 |
Her | +0.041 |
Neg logit contributions | |
sailors | -0.061 |
boat | -0.060 |
boats | -0.059 |
aro | -0.059 |
ug | -0.058 |
Token | � |
Token ID | 241 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
blonde | +0.097 |
blush | +0.086 |
brist | +0.079 |
oph | +0.078 |
fru | +0.076 |
Neg logit contributions | |
sailors | -0.112 |
boat | -0.111 |
boats | -0.111 |
aro | -0.109 |
ug | -0.107 |
Token | Let |
Token ID | 5756 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
blonde | +0.052 |
blush | +0.047 |
oph | +0.045 |
brist | +0.044 |
Her | +0.042 |
Neg logit contributions | |
sailors | -0.066 |
boat | -0.063 |
boat | -0.062 |
aro | -0.060 |
boats | -0.060 |
Token | â |
Token ID | 22940 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
blonde | +0.070 |
blush | +0.060 |
brist | +0.059 |
brow | +0.054 |
pron | +0.054 |
Neg logit contributions | |
boat | -0.071 |
sailors | -0.071 |
boats | -0.069 |
aro | -0.067 |
boat | -0.066 |
Token | € |
Token ID | 26391 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
blonde | +0.048 |
blush | +0.041 |
brist | +0.040 |
oph | +0.039 |
Her | +0.039 |
Neg logit contributions | |
sailors | -0.052 |
aro | -0.049 |
boat | -0.049 |
boat | -0.049 |
boats | -0.049 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
blonde | +0.023 |
blush | +0.020 |
brist | +0.019 |
oph | +0.018 |
Her | +0.018 |
Neg logit contributions | |
sailors | -0.028 |
boat | -0.027 |
aro | -0.027 |
boats | -0.027 |
sharks | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
blonde | +0.027 |
blush | +0.024 |
brist | +0.023 |
oph | +0.022 |
Her | +0.022 |
Neg logit contributions | |
sailors | -0.030 |
boat | -0.029 |
aro | -0.029 |
boats | -0.028 |
ug | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
blonde | +0.032 |
blush | +0.027 |
brist | +0.027 |
oph | +0.026 |
Her | +0.025 |
Neg logit contributions | |
sailors | -0.031 |
aro | -0.030 |
boat | -0.030 |
boats | -0.029 |
sharks | -0.029 |
Token | Sus |
Token ID | 30746 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
blonde | +0.035 |
blush | +0.031 |
brist | +0.030 |
oph | +0.029 |
Her | +0.029 |
Neg logit contributions | |
sailors | -0.038 |
boat | -0.036 |
aro | -0.036 |
boats | -0.036 |
sharks | -0.036 |
Token | ie |
Token ID | 494 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
blonde | +0.081 |
blush | +0.071 |
brist | +0.070 |
Her | +0.068 |
fru | +0.067 |
Neg logit contributions | |
sailors | -0.048 |
ug | -0.046 |
boat | -0.046 |
aro | -0.046 |
boat | -0.044 |
Token | happily |
Token ID | 18177 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
blonde | +0.036 |
blush | +0.031 |
brist | +0.030 |
oph | +0.029 |
Her | +0.028 |
Neg logit contributions | |
sailors | -0.041 |
boat | -0.041 |
aro | -0.040 |
boats | -0.039 |
boat | -0.039 |
Token | ate |
Token ID | 15063 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
sailors | +0.027 |
boat | +0.026 |
aro | +0.026 |
boat | +0.026 |
boats | +0.026 |
Neg logit contributions | |
blonde | -0.020 |
blush | -0.017 |
brist | -0.017 |
Her | -0.016 |
oph | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
blonde | +0.100 |
oph | +0.083 |
blush | +0.083 |
brist | +0.082 |
Her | +0.081 |
Neg logit contributions | |
boat | -0.065 |
boats | -0.065 |
sailors | -0.063 |
sharks | -0.061 |
sail | -0.059 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
blonde | +0.076 |
oph | +0.068 |
blush | +0.066 |
brist | +0.065 |
uct | +0.062 |
Neg logit contributions | |
boat | -0.064 |
sail | -0.060 |
fish | -0.060 |
raft | -0.060 |
boats | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
blonde | +0.057 |
blush | +0.049 |
brist | +0.048 |
oph | +0.047 |
Her | +0.046 |
Neg logit contributions | |
boat | -0.040 |
boat | -0.038 |
boats | -0.038 |
sailors | -0.038 |
aro | -0.037 |
Token | Later |
Token ID | 11450 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
blonde | +0.036 |
blush | +0.033 |
pron | +0.031 |
oph | +0.031 |
brist | +0.031 |
Neg logit contributions | |
sailors | -0.056 |
ug | -0.054 |
aro | -0.054 |
sail | -0.053 |
boat | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
blonde | +0.006 |
blush | +0.006 |
brist | +0.006 |
oph | +0.005 |
Her | +0.005 |
Neg logit contributions | |
sailors | -0.004 |
boat | -0.004 |
aro | -0.004 |
boats | -0.004 |
sharks | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
blonde | +0.065 |
blush | +0.058 |
brist | +0.057 |
Her | +0.056 |
oph | +0.056 |
Neg logit contributions | |
sailors | -0.035 |
boat | -0.033 |
boat | -0.032 |
aro | -0.032 |
boats | -0.032 |
Token | when |
Token ID | 618 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
blonde | +0.031 |
blush | +0.027 |
brist | +0.026 |
oph | +0.026 |
uct | +0.025 |
Neg logit contributions | |
sailors | -0.026 |
boat | -0.025 |
boats | -0.025 |
aro | -0.024 |
ug | -0.024 |
Token | she |
Token ID | 673 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
blonde | +0.024 |
blush | +0.021 |
brist | +0.021 |
oph | +0.020 |
Her | +0.019 |
Neg logit contributions | |
sailors | -0.026 |
boat | -0.025 |
boats | -0.025 |
aro | -0.025 |
sharks | -0.025 |
Token | decided |
Token ID | 3066 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
blonde | +0.026 |
brist | +0.023 |
blush | +0.022 |
Her | +0.021 |
uct | +0.021 |
Neg logit contributions | |
boat | -0.026 |
boats | -0.025 |
sailors | -0.025 |
whales | -0.024 |
sharks | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
blonde | +0.071 |
brist | +0.064 |
brow | +0.061 |
blush | +0.061 |
oph | +0.060 |
Neg logit contributions | |
boat | -0.058 |
boats | -0.057 |
sailors | -0.056 |
aro | -0.054 |
sharks | -0.053 |
Token | share |
Token ID | 2648 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
blonde | +0.025 |
blush | +0.022 |
brist | +0.022 |
oph | +0.021 |
Her | +0.021 |
Neg logit contributions | |
sailors | -0.019 |
aro | -0.018 |
boat | -0.018 |
boats | -0.018 |
sharks | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
blonde | +0.077 |
brow | +0.067 |
omm | +0.065 |
brist | +0.064 |
oph | +0.064 |
Neg logit contributions | |
sailors | -0.077 |
boats | -0.076 |
sharks | -0.075 |
boat | -0.075 |
whales | -0.073 |
Token | with |
Token ID | 351 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
blonde | +0.053 |
blush | +0.046 |
brist | +0.045 |
oph | +0.044 |
Her | +0.044 |
Neg logit contributions | |
sailors | -0.048 |
boat | -0.045 |
aro | -0.045 |
boats | -0.045 |
sharks | -0.044 |
Token | her |
Token ID | 607 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
blonde | +0.011 |
oph | +0.008 |
uct | +0.008 |
pron | +0.008 |
brist | +0.008 |
Neg logit contributions | |
sailors | -0.020 |
aro | -0.020 |
boats | -0.020 |
sharks | -0.020 |
boat | -0.019 |
Token | family |
Token ID | 1641 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
blonde | +0.020 |
blush | +0.018 |
oph | +0.018 |
brist | +0.018 |
Her | +0.017 |
Neg logit contributions | |
sailors | -0.011 |
boat | -0.010 |
boats | -0.010 |
aro | -0.010 |
sharks | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
sailors | +0.004 |
aro | +0.004 |
ug | +0.004 |
sharks | +0.004 |
captains | +0.004 |
Neg logit contributions | |
blonde | -0.004 |
blush | -0.004 |
Her | -0.003 |
brist | -0.003 |
oph | -0.003 |
Token | always |
Token ID | 1464 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
blonde | +0.038 |
blush | +0.033 |
brist | +0.032 |
oph | +0.031 |
Her | +0.031 |
Neg logit contributions | |
sailors | -0.038 |
boat | -0.037 |
aro | -0.036 |
boats | -0.036 |
boat | -0.036 |
Token | keep |
Token ID | 1394 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
blonde | +0.021 |
blush | +0.018 |
oph | +0.018 |
brist | +0.018 |
Her | +0.017 |
Neg logit contributions | |
sailors | -0.016 |
boat | -0.016 |
boats | -0.015 |
captains | -0.015 |
sail | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
blonde | +0.065 |
blush | +0.056 |
oph | +0.055 |
brist | +0.054 |
Her | +0.053 |
Neg logit contributions | |
sailors | -0.071 |
boat | -0.067 |
boats | -0.066 |
aro | -0.065 |
sharks | -0.064 |
Token | violin |
Token ID | 38283 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
blonde | +0.068 |
blush | +0.059 |
oph | +0.058 |
brist | +0.057 |
Her | +0.056 |
Neg logit contributions | |
sailors | -0.069 |
boat | -0.067 |
boats | -0.065 |
captains | -0.063 |
aro | -0.063 |
Token | clean |
Token ID | 3424 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
blonde | +0.049 |
blush | +0.042 |
brist | +0.041 |
Her | +0.040 |
oph | +0.040 |
Neg logit contributions | |
sailors | -0.050 |
aro | -0.048 |
boat | -0.047 |
boats | -0.047 |
sharks | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
blonde | +0.108 |
blush | +0.094 |
brist | +0.092 |
oph | +0.090 |
Her | +0.090 |
Neg logit contributions | |
sailors | -0.098 |
boat | -0.095 |
boats | -0.093 |
boat | -0.092 |
boats | -0.091 |
Token | so |
Token ID | 523 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
blonde | +0.090 |
oph | +0.084 |
blush | +0.080 |
brist | +0.078 |
Her | +0.076 |
Neg logit contributions | |
sailors | -0.089 |
boat | -0.087 |
boats | -0.085 |
sail | -0.082 |
captains | -0.080 |
Token | that |
Token ID | 326 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
blonde | +0.013 |
blush | +0.011 |
brist | +0.010 |
oph | +0.010 |
Her | +0.010 |
Neg logit contributions | |
sailors | -0.020 |
boat | -0.019 |
aro | -0.019 |
boats | -0.019 |
boat | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
blonde | +0.041 |
blush | +0.035 |
brist | +0.034 |
oph | +0.034 |
Her | +0.033 |
Neg logit contributions | |
sailors | -0.044 |
boat | -0.043 |
aro | -0.042 |
boats | -0.042 |
sharks | -0.042 |
Token | could |
Token ID | 714 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
blonde | +0.046 |
blush | +0.039 |
oph | +0.037 |
brist | +0.037 |
Her | +0.035 |
Neg logit contributions | |
sailors | -0.059 |
boat | -0.058 |
boat | -0.056 |
boats | -0.056 |
aro | -0.056 |
Token | play |
Token ID | 711 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
blonde | +0.037 |
blush | +0.032 |
brist | +0.031 |
Her | +0.030 |
oph | +0.030 |
Neg logit contributions | |
sailors | -0.041 |
aro | -0.039 |
sharks | -0.038 |
boat | -0.038 |
boats | -0.038 |
Token | It |
Token ID | 632 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
pron | +0.040 |
cavity | +0.036 |
brushed | +0.035 |
oph | +0.035 |
brist | +0.035 |
Neg logit contributions | |
boats | -0.042 |
Fin | -0.039 |
boat | -0.039 |
sailors | -0.038 |
sail | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
blonde | +0.026 |
brist | +0.023 |
blush | +0.022 |
oph | +0.022 |
brow | +0.021 |
Neg logit contributions | |
boat | -0.025 |
sailors | -0.025 |
boats | -0.025 |
ship | -0.024 |
boat | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
blonde | +0.053 |
oph | +0.049 |
blush | +0.049 |
brist | +0.048 |
uct | +0.048 |
Neg logit contributions | |
sailors | -0.041 |
boats | -0.040 |
boat | -0.039 |
sharks | -0.038 |
sail | -0.037 |
Token | squ |
Token ID | 2809 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
blonde | +0.015 |
blush | +0.013 |
brist | +0.013 |
Her | +0.012 |
oph | +0.012 |
Neg logit contributions | |
sailors | -0.014 |
boat | -0.014 |
boats | -0.013 |
sharks | -0.013 |
captains | -0.013 |
Token | ishy |
Token ID | 49785 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
blonde | +0.028 |
blush | +0.024 |
brist | +0.023 |
Her | +0.023 |
oph | +0.023 |
Neg logit contributions | |
sailors | -0.032 |
boat | -0.031 |
boats | -0.031 |
ug | -0.030 |
aro | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
blonde | +0.058 |
uct | +0.050 |
blush | +0.049 |
Her | +0.049 |
oph | +0.049 |
Neg logit contributions | |
boat | -0.055 |
sailors | -0.054 |
boats | -0.052 |
boat | -0.051 |
sail | -0.051 |
Token | sm |
Token ID | 895 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
blonde | +0.093 |
oph | +0.091 |
omm | +0.086 |
uct | +0.085 |
Her | +0.085 |
Neg logit contributions | |
boat | -0.081 |
sailors | -0.080 |
boats | -0.079 |
sail | -0.076 |
ship | -0.074 |
Token | elly |
Token ID | 6148 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
sailors | +0.001 |
aro | +0.001 |
boat | +0.001 |
boats | +0.001 |
boat | +0.001 |
Neg logit contributions | |
blonde | -0.001 |
blush | -0.001 |
brist | -0.001 |
Her | -0.001 |
oph | -0.001 |
Token | gift |
Token ID | 6979 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
blonde | +0.027 |
blush | +0.023 |
brist | +0.023 |
oph | +0.023 |
uct | +0.023 |
Neg logit contributions | |
sailors | -0.026 |
boat | -0.026 |
boats | -0.025 |
sharks | -0.024 |
aro | -0.024 |
Token | â |
Token ID | 22940 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
sailors | +0.021 |
boat | +0.020 |
aro | +0.020 |
boats | +0.020 |
sharks | +0.019 |
Neg logit contributions | |
blonde | -0.027 |
blush | -0.024 |
brist | -0.023 |
oph | -0.023 |
Her | -0.022 |
Token | € |
Token ID | 26391 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
blonde | +0.061 |
blush | +0.052 |
brist | +0.049 |
oph | +0.046 |
Her | +0.046 |
Neg logit contributions | |
boat | -0.075 |
ug | -0.074 |
sailors | -0.074 |
aro | -0.074 |
boat | -0.073 |
Token | was |
Token ID | 373 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
blonde | +0.006 |
blush | +0.005 |
brist | +0.005 |
oph | +0.005 |
makeup | +0.005 |
Neg logit contributions | |
sailors | -0.007 |
boat | -0.007 |
boats | -0.007 |
aro | -0.006 |
ship | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
sailors | +0.004 |
boat | +0.003 |
aro | +0.003 |
boats | +0.003 |
captains | +0.003 |
Neg logit contributions | |
blonde | -0.002 |
blush | -0.002 |
brist | -0.002 |
oph | -0.002 |
Her | -0.002 |
Token | happy |
Token ID | 3772 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
sailors | +0.001 |
boat | +0.001 |
aro | +0.001 |
boats | +0.001 |
captains | +0.001 |
Neg logit contributions | |
blonde | -0.001 |
blush | -0.001 |
brist | -0.001 |
oph | -0.001 |
Her | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
blonde | +0.002 |
blush | +0.002 |
brist | +0.002 |
oph | +0.002 |
uct | +0.002 |
Neg logit contributions | |
sailors | -0.002 |
boat | -0.002 |
boats | -0.002 |
sharks | -0.002 |
aro | -0.002 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
blonde | +0.024 |
brist | +0.021 |
blush | +0.021 |
oph | +0.021 |
omm | +0.020 |
Neg logit contributions | |
sailors | -0.025 |
boat | -0.024 |
sail | -0.023 |
boats | -0.022 |
captains | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
blonde | +0.056 |
blush | +0.048 |
brist | +0.047 |
oph | +0.047 |
pron | +0.046 |
Neg logit contributions | |
sailors | -0.045 |
boat | -0.043 |
boats | -0.042 |
aro | -0.042 |
sharks | -0.040 |
Token | puppy |
Token ID | 26188 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
blonde | +0.004 |
blush | +0.003 |
brist | +0.003 |
oph | +0.003 |
Her | +0.003 |
Neg logit contributions | |
sailors | -0.004 |
boat | -0.003 |
boats | -0.003 |
boat | -0.003 |
sail | -0.003 |
Token | tight |
Token ID | 5381 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
blonde | +0.010 |
blush | +0.008 |
brist | +0.008 |
oph | +0.008 |
Her | +0.008 |
Neg logit contributions | |
sailors | -0.013 |
boat | -0.012 |
aro | -0.012 |
boats | -0.012 |
sharks | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
blonde | +0.016 |
blush | +0.015 |
oph | +0.015 |
brist | +0.014 |
Her | +0.014 |
Neg logit contributions | |
boat | -0.010 |
sailors | -0.010 |
boats | -0.009 |
boat | -0.009 |
boats | -0.009 |
Token | thanking |
Token ID | 41892 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
blonde | +0.056 |
oph | +0.051 |
blush | +0.049 |
brist | +0.049 |
omm | +0.048 |
Neg logit contributions | |
sailors | -0.055 |
boat | -0.054 |
sail | -0.052 |
boats | -0.051 |
raft | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
blonde | +0.057 |
blush | +0.049 |
brist | +0.048 |
oph | +0.046 |
Her | +0.045 |
Neg logit contributions | |
sailors | -0.053 |
boat | -0.049 |
aro | -0.048 |
boats | -0.048 |
sharks | -0.047 |
Token | right |
Token ID | 826 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
aro | +0.041 |
sailors | +0.041 |
ug | +0.040 |
sharks | +0.038 |
captains | +0.038 |
Neg logit contributions | |
blonde | -0.046 |
blush | -0.039 |
brist | -0.038 |
Her | -0.037 |
makeup | -0.037 |
Token | thing |
Token ID | 1517 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
sailors | +0.009 |
aro | +0.009 |
boats | +0.008 |
boat | +0.008 |
sharks | +0.008 |
Neg logit contributions | |
blonde | -0.011 |
blush | -0.010 |
brist | -0.009 |
oph | -0.009 |
Her | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
sailors | +0.027 |
boat | +0.025 |
aro | +0.025 |
boats | +0.025 |
captains | +0.025 |
Neg logit contributions | |
blonde | -0.022 |
blush | -0.019 |
brist | -0.018 |
Her | -0.018 |
oph | -0.018 |
Token | do |
Token ID | 466 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
blonde | +0.014 |
brist | +0.012 |
blush | +0.012 |
oph | +0.011 |
Her | +0.011 |
Neg logit contributions | |
sailors | -0.009 |
boat | -0.009 |
boats | -0.009 |
aro | -0.008 |
boat | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
blonde | +0.036 |
blush | +0.032 |
brist | +0.031 |
oph | +0.031 |
Her | +0.030 |
Neg logit contributions | |
sailors | -0.026 |
boat | -0.024 |
aro | -0.024 |
boats | -0.024 |
sharks | -0.024 |
Token | So |
Token ID | 1406 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
sailors | +0.017 |
boat | +0.016 |
boats | +0.016 |
aro | +0.016 |
boat | +0.016 |
Neg logit contributions | |
blonde | -0.021 |
blush | -0.019 |
brist | -0.018 |
oph | -0.017 |
pron | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
sailors | +0.014 |
aro | +0.013 |
boat | +0.013 |
boats | +0.013 |
sharks | +0.013 |
Neg logit contributions | |
blonde | -0.018 |
blush | -0.016 |
brist | -0.016 |
Her | -0.016 |
oph | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
sailors | +0.009 |
aro | +0.008 |
boat | +0.008 |
boats | +0.008 |
sharks | +0.008 |
Neg logit contributions | |
blonde | -0.012 |
blush | -0.011 |
brist | -0.010 |
Her | -0.010 |
oph | -0.010 |
Token | said |
Token ID | 531 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
sailors | +0.011 |
boat | +0.010 |
boats | +0.010 |
aro | +0.010 |
captains | +0.010 |
Neg logit contributions | |
blonde | -0.008 |
blush | -0.007 |
brist | -0.007 |
Her | -0.006 |
oph | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
blonde | +0.016 |
blush | +0.015 |
brist | +0.014 |
oph | +0.014 |
Her | +0.014 |
Neg logit contributions | |
sailors | -0.013 |
boat | -0.012 |
aro | -0.012 |
boats | -0.012 |
sharks | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
blonde | +0.063 |
oph | +0.054 |
blush | +0.052 |
brist | +0.050 |
makeup | +0.048 |
Neg logit contributions | |
sailors | -0.069 |
boat | -0.066 |
aro | -0.064 |
sail | -0.063 |
boats | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
blonde | +0.017 |
blush | +0.015 |
brist | +0.015 |
oph | +0.014 |
Her | +0.014 |
Neg logit contributions | |
sailors | -0.017 |
boat | -0.016 |
boats | -0.016 |
aro | -0.016 |
sharks | -0.016 |
Token | Dad |
Token ID | 17415 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
sailors | +0.015 |
boat | +0.014 |
boats | +0.014 |
sharks | +0.013 |
whales | +0.013 |
Neg logit contributions | |
blonde | -0.020 |
blush | -0.017 |
brist | -0.017 |
oph | -0.016 |
Her | -0.016 |
Token | too |
Token ID | 1165 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
sailors | +0.014 |
boat | +0.013 |
boats | +0.013 |
sharks | +0.013 |
aro | +0.013 |
Neg logit contributions | |
blonde | -0.018 |
blush | -0.015 |
brist | -0.015 |
oph | -0.015 |
Her | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
blonde | +0.010 |
blush | +0.009 |
brist | +0.009 |
Her | +0.009 |
oph | +0.009 |
Neg logit contributions | |
sailors | -0.009 |
aro | -0.009 |
boat | -0.009 |
boat | -0.009 |
boats | -0.009 |
Token | They |
Token ID | 1119 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
sailors | +0.066 |
boat | +0.061 |
boats | +0.061 |
sharks | +0.060 |
aro | +0.059 |
Neg logit contributions | |
blonde | -0.098 |
blush | -0.088 |
brist | -0.086 |
oph | -0.084 |
uct | -0.081 |
Token | go |
Token ID | 467 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
sailors | +0.044 |
aro | +0.043 |
ug | +0.041 |
sharks | +0.041 |
boats | +0.041 |
Neg logit contributions | |
blonde | -0.052 |
blush | -0.048 |
brist | -0.046 |
Her | -0.045 |
oph | -0.044 |
Token | inside |
Token ID | 2641 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
sailors | +0.025 |
aro | +0.025 |
sharks | +0.025 |
whales | +0.025 |
ug | +0.025 |
Neg logit contributions | |
blonde | -0.016 |
blush | -0.014 |
Her | -0.014 |
brist | -0.013 |
makeup | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
sailors | +0.000 |
boat | +0.000 |
boats | +0.000 |
aro | +0.000 |
sharks | +0.000 |
Neg logit contributions | |
blonde | -0.000 |
blush | -0.000 |
brist | -0.000 |
oph | -0.000 |
Her | -0.000 |
Token | play |
Token ID | 711 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
sailors | +0.037 |
boat | +0.035 |
aro | +0.035 |
boats | +0.034 |
sharks | +0.034 |
Neg logit contributions | |
blonde | -0.049 |
blush | -0.044 |
brist | -0.043 |
oph | -0.042 |
Her | -0.042 |
Token | with |
Token ID | 351 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
blonde | +0.003 |
blush | +0.002 |
brist | +0.002 |
Her | +0.002 |
oph | +0.002 |
Neg logit contributions | |
sailors | -0.003 |
aro | -0.003 |
boat | -0.003 |
boat | -0.003 |
boats | -0.003 |
Token | their |
Token ID | 511 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
sailors | +0.041 |
boat | +0.040 |
aro | +0.040 |
ug | +0.039 |
captains | +0.038 |
Neg logit contributions | |
blonde | -0.063 |
blush | -0.056 |
Her | -0.054 |
brist | -0.054 |
makeup | -0.054 |
Token | so |
Token ID | 523 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
blonde | +0.008 |
blush | +0.007 |
oph | +0.007 |
brist | +0.007 |
Her | +0.007 |
Neg logit contributions | |
sailors | -0.008 |
boat | -0.008 |
boats | -0.008 |
aro | -0.008 |
captains | -0.008 |
Token | pleased |
Token ID | 10607 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
blonde | +0.024 |
blush | +0.022 |
oph | +0.022 |
brist | +0.022 |
Her | +0.020 |
Neg logit contributions | |
sailors | -0.021 |
boat | -0.020 |
aro | -0.020 |
boats | -0.019 |
captains | -0.019 |
Token | with |
Token ID | 351 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
blonde | +0.009 |
blush | +0.007 |
brist | +0.007 |
oph | +0.007 |
Her | +0.007 |
Neg logit contributions | |
sailors | -0.008 |
boat | -0.007 |
aro | -0.007 |
boats | -0.007 |
sharks | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
sailors | +0.008 |
aro | +0.008 |
sharks | +0.008 |
boat | +0.008 |
boats | +0.008 |
Neg logit contributions | |
blonde | -0.004 |
oph | -0.004 |
brist | -0.004 |
blush | -0.004 |
amas | -0.003 |
Token | spark |
Token ID | 9009 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
blonde | +0.031 |
blush | +0.026 |
brist | +0.026 |
oph | +0.025 |
Her | +0.025 |
Neg logit contributions | |
sailors | -0.032 |
boat | -0.031 |
aro | -0.030 |
boats | -0.030 |
sharks | -0.030 |
Token | ly |
Token ID | 306 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
blonde | +0.027 |
blush | +0.022 |
brist | +0.022 |
oph | +0.022 |
Her | +0.022 |
Neg logit contributions | |
sailors | -0.035 |
boat | -0.035 |
boats | -0.034 |
boat | -0.034 |
aro | -0.034 |
Token | seat |
Token ID | 5852 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
blonde | +0.037 |
oph | +0.032 |
blush | +0.032 |
Her | +0.031 |
brist | +0.031 |
Neg logit contributions | |
sailors | -0.039 |
boat | -0.039 |
boats | -0.037 |
boat | -0.037 |
sail | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
blonde | +0.015 |
blush | +0.013 |
brist | +0.013 |
oph | +0.013 |
Her | +0.013 |
Neg logit contributions | |
sailors | -0.013 |
boat | -0.013 |
aro | -0.012 |
boats | -0.012 |
boat | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
blonde | +0.021 |
brist | +0.018 |
oph | +0.018 |
blush | +0.017 |
Her | +0.017 |
Neg logit contributions | |
sailors | -0.026 |
boat | -0.025 |
boats | -0.025 |
aro | -0.024 |
captains | -0.024 |
Token | block |
Token ID | 2512 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
blonde | +0.040 |
blush | +0.035 |
oph | +0.035 |
brist | +0.034 |
Her | +0.033 |
Neg logit contributions | |
sailors | -0.039 |
boat | -0.039 |
boats | -0.038 |
aro | -0.037 |
sail | -0.036 |
Token | decorations |
Token ID | 39011 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
sailors | +0.009 |
boat | +0.009 |
aro | +0.008 |
boats | +0.008 |
boat | +0.008 |
Neg logit contributions | |
blonde | -0.008 |
blush | -0.006 |
brist | -0.006 |
oph | -0.006 |
Her | -0.006 |
Token | says |
Token ID | 1139 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
blonde | +0.034 |
oph | +0.031 |
pron | +0.030 |
blush | +0.028 |
uct | +0.028 |
Neg logit contributions | |
boats | -0.020 |
sailors | -0.020 |
boat | -0.020 |
sharks | -0.019 |
sail | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
blonde | +0.006 |
blush | +0.005 |
brist | +0.005 |
Her | +0.005 |
oph | +0.005 |
Neg logit contributions | |
sailors | -0.006 |
aro | -0.005 |
boat | -0.005 |
captains | -0.005 |
boats | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
sailors | +0.047 |
boat | +0.046 |
aro | +0.045 |
boats | +0.044 |
sharks | +0.044 |
Neg logit contributions | |
blonde | -0.049 |
blush | -0.043 |
brist | -0.042 |
oph | -0.042 |
makeup | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
sailors | +0.039 |
boat | +0.037 |
aro | +0.037 |
captains | +0.036 |
boats | +0.036 |
Neg logit contributions | |
blonde | -0.028 |
Her | -0.023 |
blush | -0.023 |
brist | -0.023 |
oph | -0.022 |
Token | " |
Token ID | 1 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
sailors | +0.011 |
aro | +0.011 |
boat | +0.011 |
boats | +0.010 |
sharks | +0.010 |
Neg logit contributions | |
blonde | -0.009 |
blush | -0.008 |
brist | -0.007 |
Her | -0.007 |
oph | -0.007 |
Token | Can |
Token ID | 6090 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
blonde | +0.023 |
blush | +0.018 |
oph | +0.018 |
Her | +0.018 |
brist | +0.018 |
Neg logit contributions | |
sailors | -0.034 |
aro | -0.032 |
boat | -0.032 |
boat | -0.032 |
captains | -0.032 |
Token | I |
Token ID | 314 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
blonde | +0.023 |
blush | +0.021 |
Her | +0.020 |
brist | +0.020 |
oph | +0.020 |
Neg logit contributions | |
sailors | -0.017 |
boat | -0.015 |
aro | -0.015 |
captains | -0.015 |
boat | -0.015 |
Token | have |
Token ID | 423 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
blonde | +0.036 |
blush | +0.032 |
brist | +0.031 |
oph | +0.031 |
Her | +0.030 |
Neg logit contributions | |
sailors | -0.025 |
boat | -0.024 |
aro | -0.024 |
boats | -0.024 |
boat | -0.023 |
Token | one |
Token ID | 530 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
sailors | +0.014 |
boat | +0.013 |
aro | +0.013 |
boats | +0.013 |
sharks | +0.013 |
Neg logit contributions | |
blonde | -0.016 |
blush | -0.014 |
brist | -0.014 |
oph | -0.014 |
Her | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
sailors | +0.011 |
boat | +0.010 |
aro | +0.010 |
boats | +0.010 |
boat | +0.010 |
Neg logit contributions | |
blonde | -0.015 |
blush | -0.013 |
brist | -0.013 |
oph | -0.012 |
Her | -0.012 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
sailors | +0.005 |
boat | +0.004 |
boats | +0.004 |
sharks | +0.004 |
aro | +0.004 |
Neg logit contributions | |
blonde | -0.004 |
blush | -0.004 |
brist | -0.004 |
oph | -0.004 |
Her | -0.004 |
Token | ams |
Token ID | 4105 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
sailors | +0.010 |
boat | +0.010 |
aro | +0.009 |
boats | +0.009 |
sharks | +0.009 |
Neg logit contributions | |
blonde | -0.013 |
blush | -0.012 |
brist | -0.012 |
oph | -0.011 |
Her | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
sailors | +0.017 |
aro | +0.017 |
boat | +0.016 |
boats | +0.016 |
captains | +0.016 |
Neg logit contributions | |
blonde | -0.019 |
blush | -0.016 |
brist | -0.016 |
Her | -0.016 |
oph | -0.016 |
Token | You |
Token ID | 921 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
sailors | +0.016 |
boat | +0.015 |
aro | +0.015 |
boats | +0.015 |
sharks | +0.015 |
Neg logit contributions | |
blonde | -0.012 |
blush | -0.010 |
brist | -0.010 |
Her | -0.010 |
oph | -0.010 |
Token | will |
Token ID | 481 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
sailors | +0.037 |
aro | +0.037 |
boats | +0.036 |
ug | +0.035 |
boat | +0.035 |
Neg logit contributions | |
blonde | -0.033 |
blush | -0.029 |
brushed | -0.028 |
brist | -0.027 |
Her | -0.027 |
Token | not |
Token ID | 407 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
sailors | +0.016 |
aro | +0.015 |
boat | +0.015 |
boats | +0.015 |
ug | +0.015 |
Neg logit contributions | |
blonde | -0.016 |
blush | -0.014 |
brist | -0.013 |
Her | -0.013 |
oph | -0.013 |
Token | go |
Token ID | 467 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
sailors | +0.058 |
aro | +0.058 |
boats | +0.055 |
ug | +0.055 |
boats | +0.054 |
Neg logit contributions | |
blonde | -0.056 |
blush | -0.052 |
brist | -0.048 |
Her | -0.047 |
brushed | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
sailors | +0.038 |
aro | +0.037 |
boat | +0.036 |
ug | +0.036 |
boat | +0.036 |
Neg logit contributions | |
blonde | -0.029 |
blush | -0.025 |
makeup | -0.023 |
Her | -0.023 |
brist | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
boat | +0.024 |
boats | +0.023 |
sailors | +0.023 |
aro | +0.023 |
ug | +0.023 |
Neg logit contributions | |
blonde | -0.023 |
blush | -0.020 |
Her | -0.020 |
makeup | -0.019 |
brist | -0.019 |
Token | park |
Token ID | 3952 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
sailors | +0.007 |
aro | +0.007 |
ug | +0.007 |
boat | +0.007 |
boats | +0.007 |
Neg logit contributions | |
blonde | -0.007 |
blush | -0.006 |
brist | -0.006 |
Her | -0.006 |
oph | -0.006 |
Token | today |
Token ID | 1909 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
sailors | +0.009 |
aro | +0.009 |
ug | +0.008 |
captains | +0.008 |
boat | +0.008 |
Neg logit contributions | |
blonde | -0.007 |
blush | -0.006 |
oph | -0.006 |
Her | -0.006 |
brist | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
blonde | +0.012 |
blush | +0.011 |
brist | +0.010 |
oph | +0.010 |
Her | +0.010 |
Neg logit contributions | |
sailors | -0.009 |
boat | -0.009 |
aro | -0.009 |
boats | -0.009 |
sharks | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
sailors | +0.023 |
aro | +0.021 |
boat | +0.021 |
boats | +0.021 |
captains | +0.021 |
Neg logit contributions | |
blonde | -0.029 |
blush | -0.025 |
Her | -0.025 |
brist | -0.025 |
oph | -0.024 |
Token | friend |
Token ID | 1545 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
boat | +0.014 |
aro | +0.014 |
boats | +0.014 |
sailors | +0.014 |
ug | +0.014 |
Neg logit contributions | |
blonde | -0.014 |
blush | -0.013 |
brist | -0.012 |
Her | -0.012 |
makeup | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
sailors | +0.050 |
boat | +0.049 |
aro | +0.049 |
boats | +0.048 |
ug | +0.048 |
Neg logit contributions | |
blonde | -0.043 |
Her | -0.041 |
blush | -0.039 |
oph | -0.037 |
makeup | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
sailors | +0.013 |
aro | +0.012 |
boat | +0.012 |
ug | +0.012 |
boats | +0.012 |
Neg logit contributions | |
blonde | -0.013 |
blush | -0.011 |
Her | -0.011 |
brist | -0.011 |
makeup | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
sailors | +0.022 |
aro | +0.022 |
ug | +0.021 |
boats | +0.021 |
boats | +0.021 |
Neg logit contributions | |
blonde | -0.022 |
blush | -0.019 |
brist | -0.018 |
Her | -0.018 |
makeup | -0.017 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
aro | +0.057 |
sailors | +0.055 |
ug | +0.053 |
boat | +0.052 |
boats | +0.052 |
Neg logit contributions | |
blonde | -0.052 |
blush | -0.046 |
Her | -0.044 |
brist | -0.044 |
makeup | -0.043 |
Token | named |
Token ID | 3706 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
sailors | +0.049 |
captains | +0.046 |
boats | +0.045 |
sharks | +0.045 |
fishermen | +0.045 |
Neg logit contributions | |
blonde | -0.054 |
Her | -0.053 |
blush | -0.051 |
makeup | -0.047 |
brist | -0.046 |
Token | Sally |
Token ID | 25737 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
blonde | +0.005 |
blush | +0.004 |
Her | +0.004 |
brist | +0.004 |
oph | +0.004 |
Neg logit contributions | |
sailors | -0.004 |
boat | -0.004 |
aro | -0.004 |
boat | -0.004 |
boats | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
blonde | +0.001 |
blush | +0.001 |
Her | +0.001 |
brist | +0.001 |
makeup | +0.001 |
Neg logit contributions | |
sailors | -0.001 |
aro | -0.001 |
captains | -0.001 |
boat | -0.001 |
sharks | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
blonde | +0.002 |
blush | +0.001 |
brist | +0.001 |
oph | +0.001 |
pron | +0.001 |
Neg logit contributions | |
sailors | -0.002 |
boat | -0.001 |
boats | -0.001 |
sharks | -0.001 |
whales | -0.001 |
Token | help |
Token ID | 1037 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
sailors | +0.019 |
aro | +0.018 |
boats | +0.018 |
boat | +0.018 |
boat | +0.018 |
Neg logit contributions | |
blonde | -0.022 |
blush | -0.020 |
Her | -0.020 |
makeup | -0.019 |
brist | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
sailors | +0.023 |
boat | +0.022 |
boat | +0.022 |
boats | +0.022 |
aro | +0.022 |
Neg logit contributions | |
blonde | -0.023 |
blush | -0.020 |
brist | -0.020 |
oph | -0.019 |
Her | -0.019 |
Token | there |
Token ID | 612 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
sailors | +0.007 |
aro | +0.007 |
boat | +0.007 |
ug | +0.007 |
boat | +0.007 |
Neg logit contributions | |
blonde | -0.008 |
blush | -0.007 |
brist | -0.007 |
Her | -0.007 |
oph | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
sailors | +0.004 |
aro | +0.003 |
boat | +0.003 |
boats | +0.003 |
sharks | +0.003 |
Neg logit contributions | |
blonde | -0.003 |
blush | -0.003 |
brist | -0.003 |
Her | -0.003 |
oph | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
blonde | +0.038 |
blush | +0.035 |
brist | +0.034 |
oph | +0.034 |
Her | +0.033 |
Neg logit contributions | |
sailors | -0.029 |
boat | -0.028 |
boats | -0.028 |
sharks | -0.027 |
whales | -0.026 |
Token | surprise |
Token ID | 5975 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
blonde | +0.036 |
blush | +0.031 |
Her | +0.031 |
brist | +0.031 |
oph | +0.030 |
Neg logit contributions | |
sailors | -0.035 |
boat | -0.034 |
boats | -0.033 |
sharks | -0.032 |
captains | -0.032 |
Token | for |
Token ID | 329 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
sailors | +0.034 |
aro | +0.033 |
boat | +0.032 |
boats | +0.032 |
captains | +0.032 |
Neg logit contributions | |
blonde | -0.035 |
blush | -0.031 |
brist | -0.030 |
oph | -0.029 |
Her | -0.029 |
Token | Peter |
Token ID | 5613 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
sailors | +0.054 |
boat | +0.051 |
aro | +0.051 |
boats | +0.051 |
boat | +0.050 |
Neg logit contributions | |
blonde | -0.058 |
blush | -0.050 |
brist | -0.048 |
Her | -0.048 |
oph | -0.048 |
Token | - |
Token ID | 532 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
blonde | +0.004 |
blush | +0.004 |
brist | +0.004 |
oph | +0.003 |
Her | +0.003 |
Neg logit contributions | |
sailors | -0.004 |
boat | -0.004 |
aro | -0.004 |
boats | -0.004 |
sharks | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
blonde | +0.023 |
blush | +0.020 |
brist | +0.020 |
oph | +0.019 |
Her | +0.019 |
Neg logit contributions | |
sailors | -0.020 |
boat | -0.019 |
boats | -0.019 |
aro | -0.019 |
sharks | -0.019 |
Token | big |
Token ID | 1263 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
blonde | +0.020 |
blush | +0.018 |
brist | +0.017 |
Her | +0.017 |
oph | +0.017 |
Neg logit contributions | |
boat | -0.021 |
sailors | -0.020 |
boats | -0.019 |
sharks | -0.019 |
sail | -0.019 |
Token | delicious |
Token ID | 12625 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
sailors | +0.004 |
aro | +0.004 |
boat | +0.003 |
boats | +0.003 |
sharks | +0.003 |
Neg logit contributions | |
blonde | -0.004 |
blush | -0.003 |
brist | -0.003 |
oph | -0.003 |
Her | -0.003 |
Token | excited |
Token ID | 6568 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
boat | +0.038 |
aro | +0.038 |
sailors | +0.038 |
boats | +0.038 |
boat | +0.037 |
Neg logit contributions | |
blonde | -0.024 |
Her | -0.020 |
blush | -0.018 |
brist | -0.018 |
fru | -0.018 |
Token | ! |
Token ID | 0 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
blonde | +0.030 |
blush | +0.026 |
brist | +0.026 |
brow | +0.024 |
pron | +0.024 |
Neg logit contributions | |
sailors | -0.020 |
boat | -0.019 |
boats | -0.019 |
sharks | -0.019 |
whales | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
blonde | +0.036 |
pron | +0.034 |
ited | +0.033 |
cavity | +0.032 |
brist | +0.031 |
Neg logit contributions | |
boats | -0.037 |
Fin | -0.037 |
crane | -0.036 |
boat | -0.035 |
bridge | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
sailors | +0.019 |
boat | +0.018 |
boats | +0.018 |
captains | +0.018 |
sharks | +0.018 |
Neg logit contributions | |
blonde | -0.016 |
blush | -0.014 |
brist | -0.013 |
oph | -0.013 |
Her | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
blonde | +0.047 |
blush | +0.041 |
brist | +0.040 |
oph | +0.040 |
Her | +0.039 |
Neg logit contributions | |
sailors | -0.038 |
boat | -0.036 |
aro | -0.036 |
boats | -0.036 |
sharks | -0.035 |
Token | her |
Token ID | 607 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
blonde | +0.038 |
brist | +0.030 |
oph | +0.030 |
blush | +0.030 |
fru | +0.029 |
Neg logit contributions | |
sailors | -0.046 |
boats | -0.044 |
boat | -0.043 |
aro | -0.043 |
whales | -0.043 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ug | +0.043 |
boat | +0.043 |
aro | +0.043 |
boats | +0.042 |
sailors | +0.041 |
Neg logit contributions | |
blonde | -0.029 |
blush | -0.026 |
Her | -0.026 |
makeup | -0.024 |
brist | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
blonde | +0.078 |
blush | +0.069 |
brist | +0.067 |
oph | +0.066 |
Her | +0.065 |
Neg logit contributions | |
sailors | -0.059 |
boat | -0.056 |
aro | -0.055 |
boats | -0.055 |
sharks | -0.054 |
Token | " |
Token ID | 366 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
blonde | +0.056 |
oph | +0.049 |
blush | +0.047 |
brist | +0.047 |
uct | +0.043 |
Neg logit contributions | |
sailors | -0.061 |
boat | -0.059 |
aro | -0.057 |
boats | -0.056 |
whales | -0.055 |
Token | Look |
Token ID | 8567 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
blonde | +0.012 |
blush | +0.010 |
brist | +0.010 |
oph | +0.010 |
Her | +0.010 |
Neg logit contributions | |
sailors | -0.015 |
boat | -0.015 |
aro | -0.015 |
boats | -0.014 |
sharks | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
blonde | +0.106 |
blush | +0.091 |
brist | +0.091 |
oph | +0.087 |
Her | +0.087 |
Neg logit contributions | |
sailors | -0.079 |
boat | -0.076 |
aro | -0.075 |
boats | -0.074 |
sharks | -0.072 |
Token | very |
Token ID | 845 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
sailors | +0.020 |
aro | +0.019 |
boat | +0.019 |
boat | +0.019 |
boats | +0.019 |
Neg logit contributions | |
blonde | -0.019 |
blush | -0.017 |
brist | -0.016 |
oph | -0.016 |
Her | -0.016 |
Token | popular |
Token ID | 2968 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
sailors | +0.015 |
aro | +0.015 |
boat | +0.015 |
ug | +0.015 |
boats | +0.015 |
Neg logit contributions | |
blonde | -0.013 |
blush | -0.010 |
fru | -0.010 |
brist | -0.010 |
oph | -0.010 |
Token | among |
Token ID | 1871 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
sailors | +0.015 |
aro | +0.015 |
boat | +0.015 |
boat | +0.014 |
captains | +0.014 |
Neg logit contributions | |
blonde | -0.016 |
blush | -0.014 |
brist | -0.014 |
oph | -0.013 |
Her | -0.013 |
Token | their |
Token ID | 511 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
sailors | +0.026 |
boat | +0.025 |
boat | +0.025 |
captains | +0.024 |
boats | +0.024 |
Neg logit contributions | |
blonde | -0.034 |
blush | -0.030 |
Her | -0.029 |
brist | -0.029 |
oph | -0.029 |
Token | friends |
Token ID | 2460 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
blonde | +0.013 |
blush | +0.012 |
brist | +0.011 |
Her | +0.011 |
oph | +0.011 |
Neg logit contributions | |
sailors | -0.014 |
aro | -0.013 |
boat | -0.013 |
boat | -0.013 |
boats | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
sailors | +0.028 |
aro | +0.026 |
boat | +0.026 |
sharks | +0.026 |
captains | +0.026 |
Neg logit contributions | |
blonde | -0.028 |
blush | -0.025 |
Her | -0.024 |
brist | -0.023 |
oph | -0.023 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
sailors | +0.050 |
boat | +0.048 |
aro | +0.048 |
boats | +0.047 |
sharks | +0.047 |
Neg logit contributions | |
blonde | -0.041 |
blush | -0.035 |
brist | -0.034 |
oph | -0.033 |
Her | -0.033 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
sailors | +0.016 |
aro | +0.016 |
boat | +0.016 |
boats | +0.015 |
sharks | +0.015 |
Neg logit contributions | |
blonde | -0.015 |
blush | -0.013 |
brist | -0.013 |
oph | -0.013 |
Her | -0.012 |
Token | upon |
Token ID | 2402 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
sailors | +0.064 |
captains | +0.061 |
aro | +0.061 |
boat | +0.061 |
boats | +0.060 |
Neg logit contributions | |
blonde | -0.024 |
Her | -0.019 |
blush | -0.018 |
oph | -0.017 |
brist | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
blonde | +0.017 |
blush | +0.016 |
brist | +0.015 |
oph | +0.015 |
Her | +0.015 |
Neg logit contributions | |
sailors | -0.014 |
boat | -0.014 |
sharks | -0.013 |
boats | -0.013 |
aro | -0.013 |
Token | time |
Token ID | 640 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
blonde | +0.030 |
blush | +0.026 |
brist | +0.025 |
Her | +0.024 |
oph | +0.024 |
Neg logit contributions | |
sailors | -0.036 |
boat | -0.035 |
boats | -0.035 |
sharks | -0.034 |
aro | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
sailors | +0.015 |
captains | +0.014 |
aro | +0.014 |
whales | +0.014 |
boat | +0.014 |
Neg logit contributions | |
blonde | -0.013 |
blush | -0.011 |
brist | -0.010 |
Her | -0.010 |
makeup | -0.010 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
blonde | +0.004 |
blush | +0.004 |
oph | +0.004 |
brist | +0.004 |
pron | +0.003 |
Neg logit contributions | |
boat | -0.003 |
sailors | -0.003 |
boats | -0.003 |
ug | -0.003 |
sharks | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
sailors | +0.024 |
boat | +0.023 |
boats | +0.023 |
aro | +0.023 |
captains | +0.023 |
Neg logit contributions | |
blonde | -0.020 |
Her | -0.016 |
brist | -0.016 |
blush | -0.016 |
oph | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
aro | +0.019 |
sailors | +0.019 |
boats | +0.019 |
captains | +0.019 |
boat | +0.019 |
Neg logit contributions | |
blonde | -0.017 |
blush | -0.014 |
brist | -0.014 |
Her | -0.014 |
brow | -0.013 |
Token | big |
Token ID | 1263 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
aro | +0.030 |
sailors | +0.028 |
boats | +0.028 |
ug | +0.027 |
boats | +0.027 |
Neg logit contributions | |
blonde | -0.027 |
brist | -0.022 |
pron | -0.022 |
blush | -0.022 |
fru | -0.021 |
Token | wave |
Token ID | 6769 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
aro | +0.033 |
sailors | +0.030 |
captains | +0.030 |
boats | +0.029 |
ug | +0.029 |
Neg logit contributions | |
blonde | -0.033 |
blush | -0.028 |
brist | -0.028 |
fru | -0.027 |
makeup | -0.026 |
Token | came |
Token ID | 1625 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
sailors | +0.178 |
captains | +0.172 |
aro | +0.171 |
boats | +0.171 |
afloat | +0.170 |
Neg logit contributions | |
blonde | -0.053 |
blush | -0.047 |
brushed | -0.043 |
spat | -0.042 |
Her | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
aro | +0.058 |
sailors | +0.058 |
boats | +0.056 |
captains | +0.056 |
sharks | +0.056 |
Neg logit contributions | |
blonde | -0.037 |
Her | -0.032 |
brist | -0.030 |
brow | -0.029 |
blush | -0.029 |
Token | hit |
Token ID | 2277 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
sailors | +0.038 |
ug | +0.038 |
captains | +0.037 |
aro | +0.037 |
boats | +0.037 |
Neg logit contributions | |
blonde | -0.027 |
brushed | -0.025 |
blush | -0.023 |
brist | -0.023 |
fru | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
sailors | +0.016 |
captains | +0.016 |
aro | +0.015 |
boat | +0.015 |
boats | +0.015 |
Neg logit contributions | |
blonde | -0.019 |
brist | -0.016 |
blush | -0.016 |
Her | -0.016 |
brow | -0.015 |
Token | boat |
Token ID | 8848 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
aro | +0.023 |
ug | +0.021 |
boats | +0.020 |
boat | +0.018 |
ull | +0.018 |
Neg logit contributions | |
blonde | -0.034 |
brist | -0.031 |
brow | -0.031 |
spat | -0.029 |
fru | -0.029 |
Token | one |
Token ID | 530 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
sailors | +0.024 |
boat | +0.023 |
aro | +0.023 |
boats | +0.023 |
sharks | +0.023 |
Neg logit contributions | |
blonde | -0.034 |
blush | -0.030 |
brist | -0.030 |
oph | -0.029 |
Her | -0.029 |
Token | day |
Token ID | 1110 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
sailors | +0.049 |
aro | +0.048 |
captains | +0.047 |
boats | +0.046 |
boats | +0.046 |
Neg logit contributions | |
blonde | -0.059 |
blush | -0.052 |
Her | -0.051 |
brist | -0.050 |
oph | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
sailors | +0.024 |
boat | +0.022 |
aro | +0.022 |
sharks | +0.022 |
boats | +0.022 |
Neg logit contributions | |
blonde | -0.035 |
blush | -0.031 |
brist | -0.030 |
oph | -0.030 |
Her | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
sailors | +0.069 |
aro | +0.066 |
boat | +0.066 |
boats | +0.065 |
captains | +0.064 |
Neg logit contributions | |
blonde | -0.068 |
blush | -0.059 |
brist | -0.057 |
Her | -0.056 |
oph | -0.056 |
Token | small |
Token ID | 1402 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
aro | +0.026 |
sailors | +0.026 |
ug | +0.025 |
boats | +0.025 |
boats | +0.025 |
Neg logit contributions | |
blonde | -0.025 |
blush | -0.021 |
brist | -0.020 |
Her | -0.019 |
makeup | -0.019 |
Token | animal |
Token ID | 5044 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
aro | +0.044 |
sailors | +0.043 |
captains | +0.041 |
boats | +0.041 |
ug | +0.040 |
Neg logit contributions | |
blonde | -0.054 |
blush | -0.047 |
brist | -0.046 |
Her | -0.044 |
makeup | -0.044 |
Token | came |
Token ID | 1625 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
sailors | +0.162 |
ug | +0.156 |
afloat | +0.155 |
captains | +0.155 |
boats | +0.154 |
Neg logit contributions | |
blonde | -0.082 |
Her | -0.073 |
blush | -0.071 |
makeup | -0.063 |
spat | -0.062 |
Token | along |
Token ID | 1863 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
sailors | +0.068 |
aro | +0.065 |
boat | +0.065 |
boats | +0.064 |
captains | +0.064 |
Neg logit contributions | |
blonde | -0.048 |
blush | -0.040 |
Her | -0.040 |
brist | -0.039 |
oph | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
sailors | +0.042 |
aro | +0.040 |
captains | +0.040 |
boat | +0.039 |
boats | +0.039 |
Neg logit contributions | |
blonde | -0.035 |
Her | -0.030 |
blush | -0.029 |
brist | -0.029 |
oph | -0.028 |
Token | It |
Token ID | 632 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
boat | +0.040 |
sailors | +0.040 |
sharks | +0.039 |
boats | +0.038 |
sail | +0.038 |
Neg logit contributions | |
blonde | -0.042 |
blush | -0.039 |
brist | -0.038 |
oph | -0.037 |
pron | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
sailors | +0.023 |
boat | +0.023 |
boats | +0.023 |
aro | +0.022 |
sharks | +0.022 |
Neg logit contributions | |
blonde | -0.019 |
blush | -0.017 |
brist | -0.016 |
oph | -0.016 |
Her | -0.015 |
Token | One |
Token ID | 3198 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
sailors | +0.033 |
boat | +0.031 |
aro | +0.031 |
sharks | +0.030 |
boats | +0.030 |
Neg logit contributions | |
blonde | -0.023 |
Her | -0.019 |
oph | -0.019 |
blush | -0.018 |
brist | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
aro | +0.039 |
sailors | +0.038 |
captains | +0.037 |
boats | +0.037 |
boats | +0.035 |
Neg logit contributions | |
blonde | -0.029 |
Her | -0.027 |
blush | -0.025 |
pron | -0.025 |
oph | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
sailors | +0.043 |
boat | +0.041 |
aro | +0.041 |
boat | +0.040 |
boats | +0.040 |
Neg logit contributions | |
blonde | -0.037 |
blush | -0.033 |
Her | -0.032 |
oph | -0.030 |
brist | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
sailors | +0.046 |
aro | +0.045 |
boat | +0.044 |
boat | +0.044 |
ug | +0.044 |
Neg logit contributions | |
blonde | -0.053 |
blush | -0.047 |
Her | -0.046 |
oph | -0.045 |
brist | -0.045 |
Token | two |
Token ID | 734 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
aro | +0.072 |
ug | +0.071 |
sailors | +0.070 |
boat | +0.067 |
sharks | +0.067 |
Neg logit contributions | |
blonde | -0.076 |
blush | -0.068 |
Her | -0.066 |
makeup | -0.064 |
brist | -0.064 |
Token | friends |
Token ID | 2460 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
aro | +0.115 |
boat | +0.113 |
afloat | +0.112 |
dock | +0.107 |
sailors | +0.107 |
Neg logit contributions | |
blonde | -0.114 |
Her | -0.105 |
blush | -0.103 |
oph | -0.098 |
makeup | -0.095 |
Token | started |
Token ID | 2067 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
aro | +0.176 |
sailors | +0.174 |
boats | +0.171 |
sharks | +0.170 |
boat | +0.169 |
Neg logit contributions | |
blonde | -0.086 |
blush | -0.075 |
Her | -0.073 |
oph | -0.066 |
makeup | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
sailors | +0.064 |
aro | +0.061 |
boat | +0.061 |
boats | +0.060 |
boat | +0.060 |
Neg logit contributions | |
blonde | -0.042 |
blush | -0.035 |
brist | -0.034 |
Her | -0.033 |
oph | -0.033 |
Token | quarrel |
Token ID | 41998 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
sailors | +0.032 |
aro | +0.030 |
boat | +0.029 |
boat | +0.029 |
sharks | +0.029 |
Neg logit contributions | |
blonde | -0.043 |
blush | -0.038 |
brist | -0.037 |
Her | -0.036 |
oph | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
sailors | +0.050 |
aro | +0.047 |
boat | +0.047 |
captains | +0.046 |
whales | +0.046 |
Neg logit contributions | |
blonde | -0.044 |
blush | -0.039 |
Her | -0.038 |
brist | -0.038 |
makeup | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
sailors | +0.035 |
boat | +0.033 |
aro | +0.033 |
boats | +0.032 |
sharks | +0.032 |
Neg logit contributions | |
blonde | -0.048 |
blush | -0.043 |
brist | -0.042 |
oph | -0.041 |
Her | -0.040 |
Token | They |
Token ID | 1119 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
boats | +0.020 |
sailors | +0.020 |
boat | +0.019 |
sharks | +0.019 |
fishermen | +0.018 |
Neg logit contributions | |
blonde | -0.029 |
blush | -0.027 |
brist | -0.026 |
oph | -0.026 |
uct | -0.026 |
Token | said |
Token ID | 531 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
aro | +0.130 |
ug | +0.129 |
boats | +0.122 |
boat | +0.120 |
afloat | +0.117 |
Neg logit contributions | |
blonde | -0.059 |
blush | -0.050 |
brushed | -0.050 |
spat | -0.045 |
unw | -0.044 |
Token | he |
Token ID | 339 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
boat | +0.042 |
sailors | +0.041 |
boats | +0.040 |
afloat | +0.040 |
aro | +0.040 |
Neg logit contributions | |
blonde | -0.037 |
Her | -0.032 |
blush | -0.032 |
makeup | -0.029 |
brist | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
blonde | +0.005 |
blush | +0.004 |
brist | +0.004 |
Her | +0.004 |
oph | +0.004 |
Neg logit contributions | |
sailors | -0.009 |
aro | -0.009 |
boat | -0.008 |
boats | -0.008 |
ug | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
boat | +0.081 |
ug | +0.080 |
aro | +0.079 |
boats | +0.077 |
boat | +0.075 |
Neg logit contributions | |
blonde | -0.059 |
makeup | -0.049 |
blush | -0.048 |
Her | -0.047 |
her | -0.045 |
Token | little |
Token ID | 1310 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
aro | +0.114 |
ug | +0.114 |
boats | +0.101 |
boat | +0.100 |
afloat | +0.097 |
Neg logit contributions | |
blonde | -0.092 |
pron | -0.088 |
fru | -0.082 |
makeup | -0.080 |
l | -0.079 |
Token | snack |
Token ID | 26906 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
aro | +0.131 |
ug | +0.121 |
boat | +0.114 |
boats | +0.110 |
ull | +0.110 |
Neg logit contributions | |
blonde | -0.128 |
fru | -0.116 |
spat | -0.109 |
blush | -0.109 |
makeup | -0.108 |
Token | for |
Token ID | 329 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
aro | +0.066 |
sailors | +0.065 |
captains | +0.063 |
ug | +0.062 |
boats | +0.061 |
Neg logit contributions | |
blonde | -0.043 |
blush | -0.040 |
makeup | -0.038 |
oph | -0.038 |
Her | -0.037 |
Token | them |
Token ID | 606 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
boat | +0.069 |
aro | +0.067 |
sailors | +0.067 |
boats | +0.066 |
boat | +0.065 |
Neg logit contributions | |
blonde | -0.074 |
blush | -0.065 |
Her | -0.063 |
makeup | -0.061 |
brist | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
sailors | +0.052 |
aro | +0.051 |
boat | +0.049 |
ug | +0.049 |
boat | +0.049 |
Neg logit contributions | |
blonde | -0.048 |
blush | -0.042 |
Her | -0.041 |
brist | -0.039 |
makeup | -0.039 |
Token | Ben |
Token ID | 3932 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
sailors | +0.031 |
boats | +0.031 |
boat | +0.030 |
sharks | +0.030 |
captains | +0.028 |
Neg logit contributions | |
blonde | -0.047 |
blush | -0.042 |
brist | -0.042 |
oph | -0.039 |
uct | -0.039 |
Token | One |
Token ID | 3198 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
blonde | +0.032 |
blush | +0.028 |
brist | +0.028 |
oph | +0.027 |
Her | +0.026 |
Neg logit contributions | |
sailors | -0.027 |
boat | -0.026 |
boats | -0.025 |
aro | -0.025 |
sharks | -0.025 |
Token | day |
Token ID | 1110 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
blonde | +0.010 |
Her | +0.008 |
blush | +0.008 |
brist | +0.008 |
brushed | +0.008 |
Neg logit contributions | |
sailors | -0.010 |
captains | -0.010 |
aro | -0.010 |
boats | -0.009 |
boats | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
blonde | +0.021 |
blush | +0.019 |
brist | +0.019 |
uct | +0.019 |
oph | +0.019 |
Neg logit contributions | |
sailors | -0.012 |
boat | -0.011 |
sharks | -0.011 |
boats | -0.011 |
aro | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
blonde | +0.038 |
uct | +0.035 |
brist | +0.035 |
oph | +0.034 |
blush | +0.032 |
Neg logit contributions | |
boat | -0.033 |
sharks | -0.033 |
sailors | -0.033 |
boats | -0.032 |
they | -0.030 |
Token | big |
Token ID | 1263 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
aro | +0.029 |
sailors | +0.029 |
ug | +0.028 |
boat | +0.028 |
boats | +0.028 |
Neg logit contributions | |
blonde | -0.027 |
blush | -0.024 |
brist | -0.022 |
pron | -0.022 |
Her | -0.022 |
Token | truck |
Token ID | 7779 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
aro | +0.017 |
sailors | +0.017 |
captains | +0.017 |
boats | +0.016 |
ug | +0.016 |
Neg logit contributions | |
blonde | -0.021 |
blush | -0.019 |
brist | -0.018 |
makeup | -0.018 |
fru | -0.017 |
Token | stops |
Token ID | 9911 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
sailors | +0.208 |
afloat | +0.207 |
ug | +0.204 |
aro | +0.204 |
sharks | +0.196 |
Neg logit contributions | |
Her | -0.079 |
blonde | -0.077 |
She | -0.073 |
blush | -0.072 |
spat | -0.068 |
Token | in |
Token ID | 287 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
sailors | +0.020 |
aro | +0.020 |
captains | +0.019 |
boat | +0.019 |
boat | +0.019 |
Neg logit contributions | |
blonde | -0.019 |
brist | -0.017 |
blush | -0.017 |
Her | -0.016 |
makeup | -0.016 |
Token | front |
Token ID | 2166 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
blonde | +0.013 |
blush | +0.011 |
brist | +0.011 |
oph | +0.011 |
Her | +0.011 |
Neg logit contributions | |
sailors | -0.009 |
boat | -0.008 |
boats | -0.008 |
aro | -0.008 |
sharks | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
sailors | +0.027 |
aro | +0.025 |
captains | +0.025 |
sharks | +0.024 |
boat | +0.024 |
Neg logit contributions | |
blonde | -0.042 |
blush | -0.038 |
Her | -0.038 |
brist | -0.037 |
makeup | -0.035 |
Token | their |
Token ID | 511 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
sailors | +0.007 |
boats | +0.007 |
boat | +0.007 |
sharks | +0.007 |
whales | +0.007 |
Neg logit contributions | |
blonde | -0.007 |
blush | -0.006 |
brist | -0.006 |
oph | -0.006 |
uct | -0.006 |