Token | the |
Token ID | 262 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
likes | +0.038 |
They | +0.033 |
liked | +0.028 |
fun | +0.025 |
and | +0.025 |
Neg logit contributions | |
erk | -0.091 |
otion | -0.090 |
illa | -0.089 |
ow | -0.089 |
ately | -0.088 |
Token | cake |
Token ID | 12187 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
They | +0.061 |
likes | +0.054 |
and | +0.052 |
with | +0.049 |
| +0.049 |
Neg logit contributions | |
otion | -0.060 |
iqu | -0.059 |
erk | -0.058 |
wen | -0.057 |
unct | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
likes | +0.006 |
They | +0.005 |
liked | +0.003 |
Let | +0.003 |
fun | +0.002 |
Neg logit contributions | |
erk | -0.035 |
ow | -0.035 |
ately | -0.034 |
illa | -0.034 |
otion | -0.034 |
Token | have |
Token ID | 423 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
likes | +0.020 |
They | +0.019 |
and | +0.019 |
with | +0.017 |
nice | +0.016 |
Neg logit contributions | |
ately | -0.036 |
otion | -0.036 |
erk | -0.036 |
iqu | -0.036 |
ow | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
likes | +0.046 |
They | +0.039 |
with | +0.035 |
and | +0.034 |
than | +0.034 |
Neg logit contributions | |
abella | -0.076 |
erk | -0.074 |
hesitation | -0.073 |
wen | -0.071 |
abel | -0.070 |
Token | big |
Token ID | 1263 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
They | +0.075 |
likes | +0.070 |
and | +0.064 |
with | +0.060 |
holes | +0.054 |
Neg logit contributions | |
iqu | -0.191 |
erk | -0.190 |
hesitation | -0.184 |
otion | -0.184 |
ous | -0.181 |
Token | hug |
Token ID | 16225 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
They | +0.159 |
likes | +0.141 |
They | +0.138 |
with | +0.133 |
shapes | +0.130 |
Neg logit contributions | |
erk | -0.168 |
hesitation | -0.165 |
ow | -0.163 |
otion | -0.163 |
ama | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
likes | +0.015 |
and | +0.014 |
They | +0.013 |
with | +0.010 |
liked | +0.008 |
Neg logit contributions | |
iqu | -0.091 |
ately | -0.089 |
otion | -0.089 |
wen | -0.088 |
erk | -0.088 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
likes | +0.020 |
and | +0.019 |
with | +0.016 |
games | +0.015 |
nice | +0.014 |
Neg logit contributions | |
otion | -0.103 |
iqu | -0.101 |
antis | -0.099 |
erk | -0.099 |
wen | -0.099 |
Token | L |
Token ID | 43 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
likes | +0.010 |
games | +0.009 |
fair | +0.009 |
nice | +0.009 |
They | +0.009 |
Neg logit contributions | |
otion | -0.015 |
izz | -0.014 |
ow | -0.014 |
erk | -0.013 |
antis | -0.013 |
Token | ily |
Token ID | 813 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
iqu | +0.035 |
ately | +0.033 |
otion | +0.033 |
used | +0.033 |
ous | +0.032 |
Neg logit contributions | |
and | -0.036 |
likes | -0.036 |
They | -0.035 |
with | -0.034 |
| -0.032 |
Token | they |
Token ID | 484 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
likes | +0.009 |
They | +0.008 |
and | +0.008 |
with | +0.008 |
nice | +0.007 |
Neg logit contributions | |
iqu | -0.018 |
ately | -0.018 |
otion | -0.018 |
erk | -0.018 |
wen | -0.018 |
Token | both |
Token ID | 1111 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
likes | +0.060 |
They | +0.059 |
and | +0.058 |
with | +0.054 |
nice | +0.049 |
Neg logit contributions | |
iqu | -0.121 |
ately | -0.119 |
otion | -0.119 |
wen | -0.118 |
erk | -0.118 |
Token | always |
Token ID | 1464 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
likes | +0.040 |
They | +0.040 |
and | +0.040 |
with | +0.037 |
nice | +0.033 |
Neg logit contributions | |
erk | -0.096 |
ately | -0.095 |
iqu | -0.094 |
ous | -0.094 |
ow | -0.094 |
Token | had |
Token ID | 550 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
likes | +0.017 |
They | +0.017 |
and | +0.016 |
with | +0.015 |
| +0.014 |
Neg logit contributions | |
ately | -0.031 |
iqu | -0.031 |
erk | -0.030 |
otion | -0.030 |
used | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
likes | +0.039 |
They | +0.028 |
and | +0.026 |
boy | +0.026 |
with | +0.025 |
Neg logit contributions | |
ow | -0.069 |
hesitation | -0.069 |
ately | -0.068 |
erk | -0.068 |
iqu | -0.066 |
Token | big |
Token ID | 1263 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
likes | +0.071 |
They | +0.070 |
and | +0.061 |
with | +0.060 |
shapes | +0.052 |
Neg logit contributions | |
iqu | -0.200 |
erk | -0.194 |
hesitation | -0.189 |
ately | -0.186 |
ous | -0.185 |
Token | smile |
Token ID | 8212 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
They | +0.125 |
likes | +0.121 |
with | +0.116 |
shapes | +0.110 |
They | +0.110 |
Neg logit contributions | |
hesitation | -0.181 |
erk | -0.180 |
ow | -0.176 |
tha | -0.171 |
ama | -0.170 |
Token | on |
Token ID | 319 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
and | +0.013 |
likes | +0.012 |
They | +0.012 |
with | +0.011 |
liked | +0.009 |
Neg logit contributions | |
iqu | -0.049 |
otion | -0.048 |
ately | -0.048 |
wen | -0.048 |
erk | -0.047 |
Token | their |
Token ID | 511 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
likes | +0.025 |
and | +0.020 |
liked | +0.019 |
boy | +0.018 |
They | +0.018 |
Neg logit contributions | |
iqu | -0.061 |
ow | -0.060 |
wen | -0.059 |
otion | -0.058 |
ately | -0.058 |
Token | faces |
Token ID | 6698 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ately | +0.018 |
iqu | +0.018 |
unct | +0.018 |
hesitation | +0.017 |
tha | +0.017 |
Neg logit contributions | |
likes | -0.011 |
They | -0.011 |
with | -0.010 |
and | -0.009 |
| -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
likes | +0.015 |
and | +0.014 |
They | +0.014 |
with | +0.011 |
liked | +0.008 |
Neg logit contributions | |
iqu | -0.093 |
otion | -0.091 |
ately | -0.091 |
wen | -0.091 |
erk | -0.090 |
Token | achievement |
Token ID | 13293 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
iqu | +0.023 |
ately | +0.022 |
otion | +0.022 |
erk | +0.022 |
wen | +0.022 |
Neg logit contributions | |
likes | -0.010 |
They | -0.009 |
and | -0.009 |
with | -0.008 |
liked | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
likes | +0.015 |
They | +0.014 |
and | +0.011 |
green | +0.010 |
nice | +0.010 |
Neg logit contributions | |
ately | -0.051 |
ous | -0.050 |
otion | -0.050 |
wen | -0.050 |
erk | -0.050 |
Token | She |
Token ID | 1375 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
likes | +0.006 |
and | +0.006 |
with | +0.006 |
games | +0.005 |
nice | +0.005 |
Neg logit contributions | |
otion | -0.015 |
used | -0.015 |
ately | -0.015 |
iqu | -0.015 |
ous | -0.015 |
Token | had |
Token ID | 550 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
They | +0.042 |
likes | +0.041 |
games | +0.036 |
holes | +0.036 |
nice | +0.035 |
Neg logit contributions | |
ately | -0.066 |
erk | -0.065 |
wen | -0.065 |
ous | -0.064 |
iqu | -0.064 |
Token | a |
Token ID | 257 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
likes | +0.039 |
They | +0.037 |
and | +0.034 |
with | +0.033 |
grass | +0.030 |
Neg logit contributions | |
ately | -0.049 |
wen | -0.049 |
erk | -0.049 |
hesitation | -0.048 |
iqu | -0.048 |
Token | big |
Token ID | 1263 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
They | +0.088 |
likes | +0.084 |
and | +0.074 |
with | +0.071 |
grass | +0.065 |
Neg logit contributions | |
iqu | -0.187 |
erk | -0.180 |
hesitation | -0.180 |
antis | -0.172 |
tha | -0.172 |
Token | smile |
Token ID | 8212 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
They | +0.138 |
likes | +0.129 |
They | +0.125 |
| +0.114 |
with | +0.114 |
Neg logit contributions | |
hesitation | -0.171 |
erk | -0.168 |
iqu | -0.162 |
tha | -0.159 |
otion | -0.156 |
Token | on |
Token ID | 319 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
likes | +0.013 |
and | +0.013 |
They | +0.012 |
with | +0.010 |
liked | +0.008 |
Neg logit contributions | |
iqu | -0.072 |
ately | -0.071 |
otion | -0.071 |
wen | -0.070 |
erk | -0.070 |
Token | her |
Token ID | 607 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
likes | +0.045 |
They | +0.040 |
and | +0.036 |
boy | +0.036 |
liked | +0.036 |
Neg logit contributions | |
otion | -0.061 |
ately | -0.060 |
iqu | -0.059 |
wen | -0.059 |
used | -0.059 |
Token | face |
Token ID | 1986 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
ately | +0.047 |
iqu | +0.046 |
erk | +0.045 |
ous | +0.045 |
otion | +0.045 |
Neg logit contributions | |
likes | -0.023 |
They | -0.023 |
and | -0.020 |
with | -0.019 |
liked | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
and | +0.003 |
likes | +0.003 |
They | +0.002 |
with | +0.002 |
liked | +0.000 |
Neg logit contributions | |
iqu | -0.037 |
otion | -0.036 |
ately | -0.036 |
wen | -0.036 |
erk | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
likes | +0.026 |
They | +0.022 |
liked | +0.017 |
fun | +0.017 |
nice | +0.016 |
Neg logit contributions | |
ow | -0.074 |
erk | -0.072 |
illa | -0.072 |
iqu | -0.072 |
ately | -0.072 |
Token | They |
Token ID | 1119 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
likes | +0.019 |
nice | +0.017 |
games | +0.016 |
fair | +0.016 |
pretty | +0.016 |
Neg logit contributions | |
ous | -0.062 |
ow | -0.060 |
otion | -0.059 |
ama | -0.059 |
utt | -0.058 |
Token | all |
Token ID | 477 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
likes | +0.059 |
They | +0.057 |
and | +0.056 |
with | +0.051 |
nice | +0.047 |
Neg logit contributions | |
iqu | -0.127 |
ately | -0.126 |
otion | -0.125 |
erk | -0.123 |
wen | -0.123 |
Token | had |
Token ID | 550 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
likes | +0.064 |
They | +0.063 |
and | +0.062 |
with | +0.059 |
games | +0.054 |
Neg logit contributions | |
erk | -0.109 |
ous | -0.106 |
ow | -0.105 |
otion | -0.105 |
iqu | -0.104 |
Token | a |
Token ID | 257 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
likes | +0.060 |
They | +0.048 |
girl | +0.045 |
Friends | +0.044 |
boy | +0.042 |
Neg logit contributions | |
ow | -0.070 |
hesitation | -0.069 |
erk | -0.069 |
ately | -0.067 |
illa | -0.064 |
Token | big |
Token ID | 1263 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
They | +0.075 |
likes | +0.073 |
and | +0.065 |
with | +0.060 |
grass | +0.053 |
Neg logit contributions | |
iqu | -0.186 |
erk | -0.178 |
hesitation | -0.173 |
antis | -0.172 |
ama | -0.172 |
Token | party |
Token ID | 2151 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
They | +0.131 |
likes | +0.122 |
They | +0.117 |
with | +0.114 |
shapes | +0.108 |
Neg logit contributions | |
hesitation | -0.168 |
erk | -0.166 |
iqu | -0.162 |
otion | -0.158 |
tha | -0.158 |
Token | to |
Token ID | 284 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
likes | +0.026 |
They | +0.022 |
grass | +0.018 |
green | +0.017 |
holes | +0.016 |
Neg logit contributions | |
ately | -0.076 |
ow | -0.075 |
ous | -0.075 |
erk | -0.075 |
icking | -0.075 |
Token | celebrate |
Token ID | 10648 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
iqu | +0.015 |
ately | +0.015 |
otion | +0.015 |
wen | +0.015 |
erk | +0.015 |
Neg logit contributions | |
likes | -0.006 |
and | -0.006 |
They | -0.006 |
with | -0.005 |
liked | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
likes | +0.023 |
They | +0.019 |
liked | +0.014 |
green | +0.014 |
grass | +0.013 |
Neg logit contributions | |
ately | -0.064 |
erk | -0.063 |
illa | -0.063 |
icking | -0.062 |
wen | -0.062 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
likes | +0.029 |
games | +0.025 |
nice | +0.025 |
fair | +0.024 |
shapes | +0.024 |
Neg logit contributions | |
otion | -0.071 |
ow | -0.071 |
ous | -0.070 |
erk | -0.070 |
izz | -0.069 |
Token | each |
Token ID | 1123 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
likes | +0.019 |
They | +0.013 |
fun | +0.010 |
nice | +0.010 |
green | +0.009 |
Neg logit contributions | |
ately | -0.099 |
ous | -0.093 |
ow | -0.093 |
otion | -0.093 |
erk | -0.092 |
Token | other |
Token ID | 584 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
likes | +0.014 |
They | +0.014 |
and | +0.012 |
with | +0.012 |
fun | +0.011 |
Neg logit contributions | |
ately | -0.035 |
otion | -0.035 |
wen | -0.034 |
erk | -0.034 |
iqu | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
likes | +0.022 |
They | +0.018 |
liked | +0.012 |
fun | +0.011 |
| +0.010 |
Neg logit contributions | |
ately | -0.103 |
ow | -0.102 |
ous | -0.101 |
erk | -0.101 |
icking | -0.100 |
Token | had |
Token ID | 550 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
likes | +0.018 |
They | +0.018 |
and | +0.018 |
with | +0.016 |
nice | +0.015 |
Neg logit contributions | |
iqu | -0.038 |
ately | -0.038 |
otion | -0.038 |
wen | -0.037 |
erk | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
likes | +0.059 |
They | +0.047 |
than | +0.047 |
with | +0.046 |
boy | +0.046 |
Neg logit contributions | |
abella | -0.071 |
erk | -0.069 |
wen | -0.069 |
ow | -0.068 |
hesitation | -0.064 |
Token | big |
Token ID | 1263 |
Feature activation | +6.74e+00 |
Pos logit contributions | |
They | +0.071 |
likes | +0.071 |
and | +0.064 |
with | +0.059 |
liked | +0.050 |
Neg logit contributions | |
iqu | -0.198 |
erk | -0.192 |
hesitation | -0.188 |
ately | -0.188 |
ous | -0.187 |
Token | smile |
Token ID | 8212 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
They | +0.146 |
likes | +0.136 |
with | +0.126 |
They | +0.122 |
and | +0.121 |
Neg logit contributions | |
hesitation | -0.170 |
erk | -0.166 |
iqu | -0.161 |
ow | -0.160 |
otion | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
and | +0.019 |
likes | +0.019 |
They | +0.018 |
with | +0.016 |
liked | +0.013 |
Neg logit contributions | |
iqu | -0.069 |
otion | -0.068 |
ately | -0.068 |
wen | -0.067 |
used | -0.066 |
Token | |
Token ID | 220 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
games | +0.030 |
likes | +0.030 |
fair | +0.029 |
fun | +0.029 |
nice | +0.027 |
Neg logit contributions | |
otion | -0.065 |
ous | -0.063 |
ama | -0.062 |
ately | -0.061 |
ancer | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
likes | +0.002 |
and | +0.001 |
games | +0.001 |
green | +0.001 |
nice | +0.001 |
Neg logit contributions | |
otion | -0.009 |
iqu | -0.009 |
wen | -0.009 |
erk | -0.008 |
ow | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
likes | +0.016 |
fair | +0.012 |
and | +0.012 |
than | +0.012 |
piles | +0.012 |
Neg logit contributions | |
otion | -0.045 |
wen | -0.044 |
izz | -0.044 |
ous | -0.043 |
erk | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
iqu | +0.002 |
ately | +0.002 |
erk | +0.002 |
otion | +0.002 |
ous | +0.002 |
Neg logit contributions | |
likes | -0.001 |
They | -0.001 |
and | -0.001 |
liked | -0.001 |
with | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
likes | +0.013 |
and | +0.011 |
nice | +0.010 |
with | +0.010 |
games | +0.010 |
Neg logit contributions | |
ately | -0.056 |
otion | -0.056 |
iqu | -0.055 |
erk | -0.055 |
ous | -0.055 |
Token | all |
Token ID | 477 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
likes | +0.057 |
They | +0.056 |
and | +0.055 |
with | +0.051 |
nice | +0.046 |
Neg logit contributions | |
iqu | -0.117 |
ately | -0.116 |
otion | -0.115 |
wen | -0.114 |
erk | -0.114 |
Token | had |
Token ID | 550 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
likes | +0.057 |
They | +0.056 |
and | +0.055 |
with | +0.052 |
games | +0.048 |
Neg logit contributions | |
erk | -0.103 |
ately | -0.102 |
ous | -0.101 |
iqu | -0.101 |
ow | -0.101 |
Token | a |
Token ID | 257 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
likes | +0.045 |
They | +0.037 |
with | +0.033 |
and | +0.033 |
boy | +0.030 |
Neg logit contributions | |
hesitation | -0.071 |
ately | -0.069 |
ow | -0.069 |
wen | -0.068 |
iqu | -0.068 |
Token | big |
Token ID | 1263 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
They | +0.082 |
likes | +0.081 |
and | +0.071 |
with | +0.068 |
liked | +0.060 |
Neg logit contributions | |
iqu | -0.187 |
erk | -0.180 |
hesitation | -0.177 |
wen | -0.173 |
ama | -0.173 |
Token | party |
Token ID | 2151 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
They | +0.136 |
likes | +0.130 |
with | +0.119 |
They | +0.118 |
and | +0.113 |
Neg logit contributions | |
hesitation | -0.169 |
erk | -0.168 |
iqu | -0.161 |
ow | -0.161 |
otion | -0.159 |
Token | to |
Token ID | 284 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
likes | +0.025 |
They | +0.022 |
grass | +0.017 |
green | +0.016 |
holes | +0.015 |
Neg logit contributions | |
ous | -0.087 |
ately | -0.086 |
erk | -0.085 |
ow | -0.084 |
icking | -0.084 |
Token | celebrate |
Token ID | 10648 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
iqu | +0.010 |
ately | +0.009 |
otion | +0.009 |
wen | +0.009 |
erk | +0.009 |
Neg logit contributions | |
likes | -0.004 |
and | -0.004 |
They | -0.004 |
with | -0.004 |
liked | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
likes | +0.025 |
They | +0.022 |
green | +0.016 |
liked | +0.016 |
holes | +0.015 |
Neg logit contributions | |
ately | -0.070 |
erk | -0.069 |
ous | -0.068 |
illa | -0.068 |
wen | -0.067 |
Token | volcano |
Token ID | 32410 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
They | +0.007 |
likes | +0.007 |
and | +0.007 |
with | +0.006 |
liked | +0.006 |
Neg logit contributions | |
iqu | -0.016 |
otion | -0.015 |
ately | -0.015 |
erk | -0.015 |
antis | -0.015 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
They | +0.032 |
likes | +0.031 |
and | +0.028 |
games | +0.025 |
ball | +0.024 |
Neg logit contributions | |
hesitation | -0.068 |
iqu | -0.068 |
otion | -0.068 |
erk | -0.066 |
ow | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
likes | +0.050 |
They | +0.046 |
proper | +0.036 |
Let | +0.035 |
bases | +0.035 |
Neg logit contributions | |
ous | -0.120 |
otion | -0.119 |
ately | -0.117 |
ow | -0.114 |
hesitation | -0.113 |
Token | She |
Token ID | 1375 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
likes | +0.020 |
and | +0.019 |
with | +0.018 |
games | +0.017 |
nice | +0.016 |
Neg logit contributions | |
otion | -0.055 |
iqu | -0.054 |
ately | -0.053 |
antis | -0.053 |
ow | -0.052 |
Token | had |
Token ID | 550 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
They | +0.048 |
likes | +0.042 |
games | +0.041 |
piles | +0.041 |
with | +0.040 |
Neg logit contributions | |
wen | -0.077 |
erk | -0.077 |
iqu | -0.076 |
ately | -0.076 |
ous | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
likes | +0.036 |
They | +0.035 |
and | +0.033 |
with | +0.029 |
boy | +0.026 |
Neg logit contributions | |
hesitation | -0.064 |
ow | -0.064 |
iqu | -0.063 |
wen | -0.063 |
erk | -0.063 |
Token | big |
Token ID | 1263 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
They | +0.059 |
likes | +0.057 |
and | +0.053 |
with | +0.048 |
liked | +0.038 |
Neg logit contributions | |
iqu | -0.204 |
erk | -0.197 |
otion | -0.196 |
hesitation | -0.195 |
wen | -0.194 |
Token | party |
Token ID | 2151 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
They | +0.145 |
likes | +0.132 |
They | +0.126 |
with | +0.125 |
and | +0.120 |
Neg logit contributions | |
hesitation | -0.162 |
otion | -0.159 |
erk | -0.158 |
ow | -0.157 |
tha | -0.151 |
Token | with |
Token ID | 351 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
likes | +0.019 |
They | +0.019 |
grass | +0.013 |
and | +0.012 |
green | +0.012 |
Neg logit contributions | |
ow | -0.069 |
ately | -0.069 |
otion | -0.068 |
erk | -0.068 |
ous | -0.068 |
Token | her |
Token ID | 607 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
and | +0.010 |
likes | +0.009 |
They | +0.009 |
with | +0.009 |
nice | +0.008 |
Neg logit contributions | |
iqu | -0.027 |
otion | -0.027 |
ately | -0.027 |
wen | -0.026 |
used | -0.026 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
iqu | +0.004 |
ately | +0.004 |
otion | +0.004 |
erk | +0.004 |
wen | +0.004 |
Neg logit contributions | |
likes | -0.002 |
They | -0.002 |
and | -0.002 |
with | -0.002 |
liked | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
likes | +0.020 |
They | +0.019 |
and | +0.016 |
with | +0.013 |
nice | +0.012 |
Neg logit contributions | |
ately | -0.094 |
iqu | -0.094 |
otion | -0.094 |
used | -0.093 |
erk | -0.092 |
Token | Max |
Token ID | 5436 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
iqu | +0.002 |
wen | +0.002 |
ately | +0.002 |
otion | +0.002 |
ous | +0.002 |
Neg logit contributions | |
and | -0.001 |
They | -0.001 |
likes | -0.001 |
with | -0.001 |
| -0.001 |
Token | nod |
Token ID | 18666 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
They | +0.059 |
likes | +0.058 |
with | +0.056 |
and | +0.056 |
games | +0.055 |
Neg logit contributions | |
ow | -0.068 |
iqu | -0.066 |
unct | -0.065 |
erk | -0.065 |
hesitation | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
likes | +0.038 |
They | +0.028 |
games | +0.025 |
grass | +0.023 |
green | +0.021 |
Neg logit contributions | |
ately | -0.202 |
erk | -0.199 |
otion | -0.199 |
ow | -0.198 |
ous | -0.195 |
Token | say |
Token ID | 910 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
likes | +0.026 |
They | +0.025 |
and | +0.024 |
with | +0.023 |
nice | +0.022 |
Neg logit contributions | |
iqu | -0.033 |
ately | -0.032 |
erk | -0.032 |
unct | -0.031 |
otion | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
likes | +0.015 |
They | +0.014 |
and | +0.014 |
with | +0.013 |
liked | +0.011 |
Neg logit contributions | |
iqu | -0.043 |
ately | -0.043 |
otion | -0.042 |
ous | -0.041 |
erk | -0.041 |
Token | " |
Token ID | 366 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
likes | +0.022 |
They | +0.020 |
and | +0.020 |
with | +0.017 |
fun | +0.015 |
Neg logit contributions | |
otion | -0.082 |
iqu | -0.082 |
ately | -0.082 |
ous | -0.081 |
erk | -0.080 |
Token | Deal |
Token ID | 45776 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
and | +0.139 |
They | +0.128 |
piles | +0.125 |
likes | +0.125 |
holes | +0.123 |
Neg logit contributions | |
iqu | -0.157 |
mallow | -0.156 |
ately | -0.154 |
wen | -0.154 |
tha | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
likes | +0.033 |
They | +0.031 |
and | +0.029 |
liked | +0.025 |
with | +0.025 |
Neg logit contributions | |
ately | -0.093 |
ous | -0.092 |
otion | -0.092 |
iqu | -0.092 |
used | -0.092 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
likes | +0.031 |
They | +0.030 |
and | +0.030 |
with | +0.028 |
liked | +0.027 |
Neg logit contributions | |
iqu | -0.034 |
otion | -0.034 |
ately | -0.034 |
erk | -0.033 |
wen | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
likes | +0.017 |
They | +0.017 |
grass | +0.015 |
games | +0.015 |
holes | +0.015 |
Neg logit contributions | |
ous | -0.054 |
ow | -0.053 |
illa | -0.053 |
erk | -0.053 |
ately | -0.053 |
Token | Thank |
Token ID | 6952 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
and | +0.085 |
likes | +0.077 |
different | +0.074 |
nice | +0.074 |
with | +0.074 |
Neg logit contributions | |
ately | -0.135 |
otion | -0.133 |
used | -0.133 |
ous | -0.133 |
iqu | -0.132 |
Token | married |
Token ID | 6405 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
iqu | +0.009 |
ow | +0.009 |
ous | +0.009 |
aro | +0.009 |
ately | +0.009 |
Neg logit contributions | |
likes | -0.005 |
They | -0.005 |
and | -0.004 |
with | -0.004 |
liked | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
likes | +0.010 |
They | +0.010 |
and | +0.007 |
green | +0.007 |
liked | +0.006 |
Neg logit contributions | |
ately | -0.037 |
ous | -0.036 |
ow | -0.036 |
illa | -0.036 |
erk | -0.035 |
Token | They |
Token ID | 1119 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
likes | +0.011 |
and | +0.009 |
with | +0.008 |
nice | +0.008 |
liked | +0.007 |
Neg logit contributions | |
otion | -0.036 |
iqu | -0.036 |
ately | -0.036 |
wen | -0.036 |
erk | -0.035 |
Token | had |
Token ID | 550 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
likes | +0.059 |
They | +0.058 |
and | +0.056 |
with | +0.052 |
nice | +0.047 |
Neg logit contributions | |
iqu | -0.118 |
ately | -0.118 |
otion | -0.117 |
erk | -0.115 |
wen | -0.115 |
Token | a |
Token ID | 257 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
likes | +0.045 |
They | +0.038 |
and | +0.034 |
with | +0.034 |
grass | +0.031 |
Neg logit contributions | |
hesitation | -0.074 |
ow | -0.073 |
erk | -0.072 |
abella | -0.071 |
wen | -0.070 |
Token | big |
Token ID | 1263 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
They | +0.069 |
likes | +0.067 |
and | +0.063 |
with | +0.060 |
shapes | +0.050 |
Neg logit contributions | |
iqu | -0.173 |
hesitation | -0.166 |
erk | -0.165 |
tha | -0.164 |
wen | -0.164 |
Token | party |
Token ID | 2151 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
They | +0.133 |
They | +0.120 |
likes | +0.117 |
with | +0.115 |
Let | +0.110 |
Neg logit contributions | |
hesitation | -0.164 |
tha | -0.159 |
otion | -0.158 |
erk | -0.157 |
ow | -0.156 |
Token | with |
Token ID | 351 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
likes | +0.020 |
They | +0.018 |
grass | +0.014 |
holes | +0.013 |
green | +0.013 |
Neg logit contributions | |
ous | -0.070 |
ow | -0.070 |
ately | -0.070 |
erk | -0.068 |
icking | -0.068 |
Token | their |
Token ID | 511 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
likes | +0.009 |
They | +0.009 |
and | +0.009 |
with | +0.008 |
liked | +0.007 |
Neg logit contributions | |
iqu | -0.026 |
ately | -0.025 |
otion | -0.025 |
wen | -0.025 |
erk | -0.025 |
Token | toys |
Token ID | 14958 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
They | +0.008 |
likes | +0.008 |
and | +0.008 |
with | +0.007 |
liked | +0.006 |
Neg logit contributions | |
iqu | -0.021 |
ately | -0.020 |
aro | -0.020 |
ous | -0.020 |
erk | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
likes | +0.009 |
They | +0.008 |
and | +0.005 |
with | +0.003 |
nice | +0.003 |
Neg logit contributions | |
ately | -0.083 |
iqu | -0.083 |
otion | -0.082 |
ous | -0.082 |
erk | -0.081 |
Token | park |
Token ID | 3952 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
They | +0.036 |
likes | +0.036 |
and | +0.033 |
than | +0.032 |
with | +0.032 |
Neg logit contributions | |
iqu | -0.057 |
wen | -0.055 |
otion | -0.055 |
antis | -0.055 |
unct | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
likes | +0.012 |
They | +0.011 |
and | +0.009 |
nice | +0.008 |
pretty | +0.008 |
Neg logit contributions | |
ow | -0.040 |
ately | -0.040 |
erk | -0.040 |
otion | -0.040 |
aro | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
likes | +0.017 |
and | +0.015 |
with | +0.013 |
nice | +0.010 |
fair | +0.010 |
Neg logit contributions | |
otion | -0.107 |
erk | -0.104 |
iqu | -0.104 |
antis | -0.104 |
ately | -0.104 |
Token | have |
Token ID | 423 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
They | +0.060 |
and | +0.056 |
likes | +0.056 |
with | +0.055 |
games | +0.050 |
Neg logit contributions | |
erk | -0.102 |
otion | -0.101 |
ow | -0.101 |
hesitation | -0.099 |
iqu | -0.099 |
Token | a |
Token ID | 257 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
likes | +0.036 |
They | +0.033 |
with | +0.028 |
shows | +0.028 |
But | +0.026 |
Neg logit contributions | |
hesitation | -0.072 |
ow | -0.068 |
erk | -0.066 |
injuries | -0.066 |
abella | -0.065 |
Token | big |
Token ID | 1263 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
They | +0.065 |
likes | +0.063 |
and | +0.059 |
with | +0.058 |
than | +0.047 |
Neg logit contributions | |
iqu | -0.178 |
erk | -0.175 |
hesitation | -0.173 |
otion | -0.172 |
wen | -0.170 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
They | +0.111 |
with | +0.101 |
likes | +0.100 |
They | +0.094 |
| +0.090 |
Neg logit contributions | |
hesitation | -0.183 |
otion | -0.180 |
erk | -0.180 |
ow | -0.176 |
tha | -0.173 |
Token | taxi |
Token ID | 17536 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
likes | +0.021 |
They | +0.020 |
and | +0.017 |
nice | +0.016 |
with | +0.016 |
Neg logit contributions | |
ately | -0.054 |
otion | -0.053 |
iqu | -0.052 |
ous | -0.052 |
ow | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ow | +0.025 |
ately | +0.025 |
iqu | +0.025 |
ous | +0.025 |
otion | +0.025 |
Neg logit contributions | |
likes | -0.006 |
They | -0.005 |
and | -0.005 |
nice | -0.004 |
with | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
likes | +0.018 |
and | +0.014 |
with | +0.011 |
nice | +0.011 |
fair | +0.010 |
Neg logit contributions | |
otion | -0.102 |
ately | -0.099 |
iqu | -0.098 |
antis | -0.097 |
erk | -0.097 |
Token | are |
Token ID | 389 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
They | +0.052 |
likes | +0.051 |
and | +0.051 |
with | +0.050 |
| +0.044 |
Neg logit contributions | |
iqu | -0.097 |
erk | -0.096 |
otion | -0.096 |
ow | -0.096 |
unct | -0.093 |
Token | ily |
Token ID | 813 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
otion | +0.034 |
ately | +0.033 |
iqu | +0.033 |
wen | +0.032 |
erk | +0.032 |
Neg logit contributions | |
likes | -0.031 |
They | -0.031 |
and | -0.030 |
with | -0.029 |
green | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
They | +0.027 |
likes | +0.023 |
nice | +0.022 |
fun | +0.022 |
games | +0.022 |
Neg logit contributions | |
ately | -0.098 |
ow | -0.097 |
wen | -0.096 |
illa | -0.095 |
erk | -0.095 |
Token | Tom |
Token ID | 4186 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
iqu | +0.020 |
ately | +0.020 |
otion | +0.020 |
wen | +0.019 |
erk | +0.019 |
Neg logit contributions | |
and | -0.012 |
likes | -0.011 |
They | -0.011 |
with | -0.010 |
liked | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
They | +0.045 |
likes | +0.045 |
and | +0.042 |
with | +0.041 |
fun | +0.037 |
Neg logit contributions | |
ately | -0.087 |
iqu | -0.086 |
ow | -0.085 |
erk | -0.085 |
otion | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
likes | +0.042 |
They | +0.035 |
and | +0.031 |
with | +0.030 |
boy | +0.028 |
Neg logit contributions | |
hesitation | -0.078 |
ow | -0.076 |
iqu | -0.074 |
abella | -0.074 |
erk | -0.074 |
Token | big |
Token ID | 1263 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
likes | +0.067 |
They | +0.066 |
and | +0.063 |
with | +0.057 |
liked | +0.047 |
Neg logit contributions | |
iqu | -0.212 |
otion | -0.206 |
ately | -0.204 |
erk | -0.204 |
wen | -0.204 |
Token | , |
Token ID | 11 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
They | +0.141 |
likes | +0.132 |
with | +0.125 |
and | +0.123 |
| +0.117 |
Neg logit contributions | |
hesitation | -0.166 |
otion | -0.165 |
ow | -0.163 |
erk | -0.163 |
iqu | -0.159 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
They | +0.005 |
likes | +0.005 |
and | +0.004 |
with | +0.004 |
| +0.004 |
Neg logit contributions | |
iqu | -0.015 |
ately | -0.015 |
erk | -0.014 |
otion | -0.014 |
ous | -0.014 |
Token | marriage |
Token ID | 4845 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
likes | +0.074 |
They | +0.064 |
holes | +0.057 |
liked | +0.057 |
shapes | +0.056 |
Neg logit contributions | |
ous | -0.093 |
otion | -0.091 |
hesitation | -0.091 |
ately | -0.090 |
ow | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
likes | +0.008 |
They | +0.007 |
and | +0.006 |
green | +0.005 |
grass | +0.005 |
Neg logit contributions | |
ous | -0.032 |
ately | -0.032 |
iqu | -0.031 |
otion | -0.031 |
erk | -0.031 |
Token | They |
Token ID | 1119 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
likes | +0.013 |
and | +0.009 |
with | +0.008 |
nice | +0.008 |
liked | +0.007 |
Neg logit contributions | |
otion | -0.079 |
ately | -0.077 |
iqu | -0.076 |
ous | -0.075 |
antis | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
They | +0.010 |
likes | +0.010 |
and | +0.009 |
nice | +0.009 |
fun | +0.009 |
Neg logit contributions | |
ately | -0.018 |
erk | -0.018 |
ow | -0.018 |
iqu | -0.018 |
wen | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
iqu | +0.041 |
ately | +0.040 |
otion | +0.040 |
wen | +0.040 |
erk | +0.040 |
Neg logit contributions | |
likes | -0.011 |
and | -0.010 |
They | -0.010 |
with | -0.009 |
nice | -0.007 |
Token | mouse |
Token ID | 10211 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
iqu | +0.034 |
otion | +0.034 |
ately | +0.034 |
wen | +0.034 |
used | +0.033 |
Neg logit contributions | |
likes | -0.015 |
and | -0.015 |
They | -0.014 |
with | -0.013 |
nice | -0.012 |
Token | had |
Token ID | 550 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
likes | +0.028 |
They | +0.027 |
and | +0.025 |
with | +0.024 |
nice | +0.024 |
Neg logit contributions | |
ately | -0.046 |
erk | -0.045 |
ow | -0.044 |
iqu | -0.044 |
otion | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
likes | +0.040 |
They | +0.032 |
with | +0.030 |
and | +0.029 |
girl | +0.028 |
Neg logit contributions | |
hesitation | -0.075 |
erk | -0.071 |
ow | -0.070 |
ately | -0.070 |
iqu | -0.069 |
Token | big |
Token ID | 1263 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
They | +0.081 |
likes | +0.078 |
and | +0.073 |
with | +0.072 |
shapes | +0.058 |
Neg logit contributions | |
iqu | -0.192 |
erk | -0.187 |
hesitation | -0.187 |
wen | -0.183 |
tha | -0.180 |
Token | disagreement |
Token ID | 25800 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
They | +0.138 |
They | +0.128 |
likes | +0.126 |
with | +0.126 |
| +0.118 |
Neg logit contributions | |
hesitation | -0.164 |
erk | -0.160 |
ow | -0.157 |
otion | -0.153 |
igh | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
likes | +0.014 |
They | +0.012 |
and | +0.010 |
green | +0.009 |
nice | +0.009 |
Neg logit contributions | |
otion | -0.046 |
ately | -0.046 |
iqu | -0.046 |
ous | -0.046 |
erk | -0.046 |
Token | Then |
Token ID | 3244 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
likes | +0.009 |
nice | +0.007 |
and | +0.007 |
games | +0.007 |
pretty | +0.006 |
Neg logit contributions | |
ately | -0.027 |
otion | -0.027 |
iqu | -0.026 |
antis | -0.026 |
ow | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
iqu | +0.031 |
ately | +0.031 |
otion | +0.031 |
used | +0.030 |
wen | +0.030 |
Neg logit contributions | |
likes | -0.011 |
They | -0.010 |
and | -0.010 |
with | -0.009 |
liked | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
iqu | +0.084 |
wen | +0.082 |
otion | +0.081 |
erk | +0.080 |
ately | +0.080 |
Neg logit contributions | |
and | -0.022 |
They | -0.021 |
with | -0.020 |
likes | -0.018 |
| -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
likes | +0.014 |
They | +0.013 |
and | +0.013 |
with | +0.012 |
liked | +0.010 |
Neg logit contributions | |
iqu | -0.048 |
ately | -0.048 |
otion | -0.047 |
wen | -0.047 |
erk | -0.047 |
Token | strawberry |
Token ID | 41236 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
likes | +0.006 |
They | +0.006 |
and | +0.006 |
with | +0.005 |
liked | +0.005 |
Neg logit contributions | |
iqu | -0.013 |
ately | -0.013 |
otion | -0.013 |
wen | -0.013 |
erk | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
ately | +0.059 |
erk | +0.058 |
ous | +0.057 |
comb | +0.057 |
icking | +0.057 |
Neg logit contributions | |
likes | -0.019 |
They | -0.018 |
liked | -0.013 |
nice | -0.013 |
| -0.012 |
Token | had |
Token ID | 550 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
likes | +0.007 |
They | +0.007 |
and | +0.007 |
with | +0.006 |
nice | +0.005 |
Neg logit contributions | |
ately | -0.020 |
iqu | -0.020 |
ous | -0.020 |
erk | -0.020 |
otion | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
likes | +0.039 |
They | +0.032 |
and | +0.030 |
with | +0.029 |
liked | +0.026 |
Neg logit contributions | |
erk | -0.061 |
wen | -0.061 |
ow | -0.060 |
ately | -0.059 |
iqu | -0.059 |
Token | big |
Token ID | 1263 |
Feature activation | +6.63e+00 |
Pos logit contributions | |
likes | +0.067 |
They | +0.066 |
and | +0.060 |
with | +0.055 |
liked | +0.048 |
Neg logit contributions | |
iqu | -0.184 |
erk | -0.178 |
ous | -0.175 |
wen | -0.175 |
hesitation | -0.174 |
Token | party |
Token ID | 2151 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
They | +0.140 |
likes | +0.136 |
with | +0.123 |
and | +0.121 |
shapes | +0.118 |
Neg logit contributions | |
hesitation | -0.167 |
erk | -0.166 |
iqu | -0.163 |
ow | -0.158 |
otion | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
likes | +0.024 |
They | +0.021 |
grass | +0.016 |
and | +0.016 |
liked | +0.016 |
Neg logit contributions | |
ous | -0.066 |
ately | -0.066 |
erk | -0.065 |
ow | -0.064 |
iqu | -0.064 |
Token | |
Token ID | 220 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
likes | +0.019 |
and | +0.016 |
nice | +0.015 |
games | +0.015 |
with | +0.014 |
Neg logit contributions | |
otion | -0.061 |
ately | -0.060 |
wen | -0.060 |
used | -0.060 |
iqu | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
otion | +0.013 |
iqu | +0.013 |
wen | +0.013 |
ately | +0.013 |
erk | +0.013 |
Neg logit contributions | |
likes | -0.002 |
and | -0.002 |
They | -0.001 |
with | -0.001 |
games | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
likes | +0.009 |
and | +0.007 |
They | +0.007 |
fair | +0.006 |
games | +0.006 |
Neg logit contributions | |
wen | -0.029 |
otion | -0.029 |
aro | -0.029 |
erk | -0.029 |
izz | -0.029 |
Token | back |
Token ID | 736 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
likes | +0.013 |
They | +0.011 |
liked | +0.010 |
and | +0.010 |
shapes | +0.010 |
Neg logit contributions | |
ately | -0.021 |
otion | -0.021 |
ow | -0.021 |
iqu | -0.021 |
erk | -0.021 |
Token | home |
Token ID | 1363 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
likes | +0.013 |
They | +0.012 |
and | +0.011 |
with | +0.010 |
liked | +0.010 |
Neg logit contributions | |
ately | -0.032 |
iqu | -0.032 |
erk | -0.032 |
otion | -0.032 |
wen | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -6.03e-03 |
Pos logit contributions | |
likes | +0.007 |
They | +0.006 |
and | +0.004 |
grass | +0.004 |
green | +0.004 |
Neg logit contributions | |
ately | -0.033 |
erk | -0.033 |
iqu | -0.033 |
ous | -0.033 |
ow | -0.032 |
Token | had |
Token ID | 550 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
iqu | +0.000 |
otion | +0.000 |
wen | +0.000 |
ately | +0.000 |
used | +0.000 |
Neg logit contributions | |
and | -0.000 |
They | -0.000 |
likes | -0.000 |
with | -0.000 |
liked | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
likes | +0.045 |
They | +0.035 |
than | +0.034 |
and | +0.034 |
with | +0.033 |
Neg logit contributions | |
erk | -0.065 |
ow | -0.064 |
abella | -0.064 |
iqu | -0.063 |
wen | -0.062 |
Token | big |
Token ID | 1263 |
Feature activation | +6.63e+00 |
Pos logit contributions | |
likes | +0.054 |
They | +0.053 |
and | +0.050 |
with | +0.044 |
liked | +0.036 |
Neg logit contributions | |
iqu | -0.207 |
erk | -0.201 |
otion | -0.200 |
ately | -0.199 |
wen | -0.199 |
Token | dinner |
Token ID | 8073 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
They | +0.138 |
likes | +0.132 |
with | +0.122 |
and | +0.120 |
shapes | +0.117 |
Neg logit contributions | |
erk | -0.168 |
hesitation | -0.166 |
iqu | -0.164 |
otion | -0.163 |
ow | -0.163 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
likes | +0.017 |
They | +0.015 |
and | +0.012 |
green | +0.011 |
grass | +0.011 |
Neg logit contributions | |
ately | -0.041 |
erk | -0.041 |
ous | -0.040 |
otion | -0.040 |
ow | -0.040 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
likes | +0.017 |
and | +0.016 |
games | +0.014 |
with | +0.014 |
nice | +0.013 |
Neg logit contributions | |
iqu | -0.049 |
otion | -0.048 |
erk | -0.048 |
ous | -0.048 |
antis | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
They | +0.034 |
likes | +0.030 |
games | +0.027 |
with | +0.027 |
nice | +0.026 |
Neg logit contributions | |
wen | -0.075 |
ately | -0.074 |
erk | -0.074 |
ow | -0.074 |
iqu | -0.073 |
Token | his |
Token ID | 465 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
iqu | +0.052 |
ately | +0.051 |
otion | +0.050 |
used | +0.050 |
wen | +0.050 |
Neg logit contributions | |
They | -0.011 |
and | -0.011 |
likes | -0.010 |
with | -0.009 |
| -0.008 |
Token | ute |
Token ID | 1133 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
iqu | +0.071 |
otion | +0.068 |
ately | +0.068 |
wen | +0.067 |
erk | +0.066 |
Neg logit contributions | |
likes | -0.111 |
and | -0.110 |
They | -0.109 |
with | -0.104 |
nice | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
ately | +0.086 |
otion | +0.086 |
ous | +0.085 |
iqu | +0.085 |
erk | +0.084 |
Neg logit contributions | |
likes | -0.018 |
They | -0.016 |
and | -0.013 |
liked | -0.011 |
fun | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
likes | +0.009 |
and | +0.009 |
with | +0.008 |
fun | +0.008 |
nice | +0.008 |
Neg logit contributions | |
ately | -0.022 |
otion | -0.022 |
iqu | -0.022 |
ous | -0.022 |
used | -0.022 |
Token | had |
Token ID | 550 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
They | +0.039 |
likes | +0.039 |
and | +0.036 |
with | +0.034 |
nice | +0.032 |
Neg logit contributions | |
ately | -0.072 |
iqu | -0.072 |
wen | -0.071 |
erk | -0.070 |
used | -0.070 |
Token | a |
Token ID | 257 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
likes | +0.034 |
They | +0.032 |
and | +0.029 |
with | +0.028 |
liked | +0.025 |
Neg logit contributions | |
wen | -0.051 |
ately | -0.051 |
iqu | -0.050 |
erk | -0.050 |
ow | -0.050 |
Token | big |
Token ID | 1263 |
Feature activation | +6.63e+00 |
Pos logit contributions | |
They | +0.072 |
likes | +0.070 |
and | +0.063 |
with | +0.059 |
shapes | +0.051 |
Neg logit contributions | |
iqu | -0.182 |
erk | -0.176 |
wen | -0.174 |
hesitation | -0.174 |
ous | -0.171 |
Token | smile |
Token ID | 8212 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
They | +0.144 |
likes | +0.131 |
They | +0.125 |
with | +0.122 |
shapes | +0.119 |
Neg logit contributions | |
hesitation | -0.163 |
erk | -0.157 |
tha | -0.154 |
iqu | -0.153 |
ow | -0.152 |
Token | on |
Token ID | 319 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
and | +0.020 |
likes | +0.017 |
with | +0.016 |
They | +0.016 |
liked | +0.013 |
Neg logit contributions | |
iqu | -0.070 |
otion | -0.067 |
ately | -0.066 |
wen | -0.066 |
erk | -0.066 |
Token | her |
Token ID | 607 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
likes | +0.043 |
They | +0.038 |
and | +0.035 |
liked | +0.035 |
boy | +0.034 |
Neg logit contributions | |
otion | -0.059 |
ately | -0.057 |
ow | -0.057 |
wen | -0.057 |
iqu | -0.057 |
Token | face |
Token ID | 1986 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
ately | +0.051 |
iqu | +0.051 |
wen | +0.050 |
ous | +0.049 |
erk | +0.049 |
Neg logit contributions | |
likes | -0.024 |
They | -0.023 |
and | -0.021 |
with | -0.020 |
liked | -0.019 |
Token | because |
Token ID | 780 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
and | +0.003 |
with | +0.001 |
likes | +0.001 |
They | +0.001 |
liked | -0.001 |
Neg logit contributions | |
iqu | -0.045 |
otion | -0.044 |
wen | -0.044 |
ately | -0.043 |
aro | -0.043 |
Token | She |
Token ID | 1375 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
likes | +0.023 |
and | +0.021 |
with | +0.017 |
games | +0.017 |
They | +0.016 |
Neg logit contributions | |
iqu | -0.098 |
otion | -0.098 |
wen | -0.097 |
antis | -0.096 |
ately | -0.096 |
Token | says |
Token ID | 1139 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
They | +0.052 |
with | +0.049 |
games | +0.047 |
likes | +0.047 |
and | +0.046 |
Neg logit contributions | |
iqu | -0.095 |
erk | -0.091 |
wen | -0.090 |
otion | -0.089 |
ow | -0.088 |
Token | he |
Token ID | 339 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
iqu | +0.004 |
wen | +0.004 |
ately | +0.004 |
used | +0.004 |
erk | +0.004 |
Neg logit contributions | |
and | -0.002 |
likes | -0.002 |
They | -0.002 |
with | -0.002 |
nice | -0.002 |
Token | has |
Token ID | 468 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
They | +0.018 |
with | +0.016 |
and | +0.016 |
games | +0.015 |
likes | +0.014 |
Neg logit contributions | |
iqu | -0.064 |
erk | -0.063 |
wen | -0.063 |
ow | -0.063 |
otion | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
They | +0.032 |
likes | +0.032 |
and | +0.029 |
with | +0.028 |
games | +0.023 |
Neg logit contributions | |
wen | -0.069 |
iqu | -0.068 |
ately | -0.068 |
erk | -0.068 |
ow | -0.068 |
Token | big |
Token ID | 1263 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
They | +0.079 |
likes | +0.079 |
and | +0.075 |
with | +0.070 |
liked | +0.062 |
Neg logit contributions | |
iqu | -0.179 |
otion | -0.173 |
erk | -0.172 |
wen | -0.172 |
ately | -0.172 |
Token | imagination |
Token ID | 13843 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
They | +0.130 |
likes | +0.122 |
with | +0.115 |
and | +0.112 |
They | +0.109 |
Neg logit contributions | |
hesitation | -0.173 |
otion | -0.173 |
erk | -0.170 |
iqu | -0.169 |
ately | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
likes | +0.001 |
They | +0.001 |
and | +0.001 |
with | +0.001 |
nice | +0.001 |
Neg logit contributions | |
iqu | -0.010 |
ately | -0.010 |
otion | -0.010 |
wen | -0.010 |
erk | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
likes | +0.019 |
and | +0.018 |
They | +0.016 |
with | +0.014 |
nice | +0.012 |
Neg logit contributions | |
iqu | -0.090 |
otion | -0.089 |
ately | -0.089 |
wen | -0.088 |
erk | -0.087 |
Token | says |
Token ID | 1139 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
They | +0.035 |
with | +0.033 |
and | +0.032 |
likes | +0.032 |
nice | +0.031 |
Neg logit contributions | |
iqu | -0.078 |
erk | -0.075 |
wen | -0.074 |
otion | -0.074 |
ow | -0.074 |
Token | he |
Token ID | 339 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
iqu | +0.004 |
wen | +0.003 |
ately | +0.003 |
used | +0.003 |
otion | +0.003 |
Neg logit contributions | |
and | -0.002 |
likes | -0.002 |
They | -0.002 |
with | -0.002 |
nice | -0.002 |
Token | You |
Token ID | 921 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
likes | +0.030 |
and | +0.029 |
They | +0.026 |
with | +0.025 |
nice | +0.022 |
Neg logit contributions | |
iqu | -0.105 |
otion | -0.104 |
ately | -0.104 |
wen | -0.102 |
erk | -0.102 |
Token | can |
Token ID | 460 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
They | +0.034 |
likes | +0.034 |
and | +0.033 |
with | +0.031 |
grass | +0.029 |
Neg logit contributions | |
otion | -0.059 |
iqu | -0.059 |
ately | -0.059 |
ow | -0.058 |
erk | -0.057 |
Token | both |
Token ID | 1111 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
iqu | +0.049 |
otion | +0.048 |
ately | +0.048 |
wen | +0.048 |
erk | +0.047 |
Neg logit contributions | |
likes | -0.022 |
and | -0.021 |
They | -0.021 |
with | -0.019 |
liked | -0.017 |
Token | have |
Token ID | 423 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
They | +0.017 |
likes | +0.017 |
and | +0.016 |
grass | +0.014 |
with | +0.014 |
Neg logit contributions | |
ow | -0.032 |
ous | -0.032 |
ately | -0.031 |
erk | -0.031 |
used | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
likes | +0.029 |
They | +0.028 |
and | +0.024 |
liked | +0.022 |
with | +0.022 |
Neg logit contributions | |
hesitation | -0.052 |
ately | -0.052 |
erk | -0.051 |
wen | -0.051 |
ow | -0.051 |
Token | big |
Token ID | 1263 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
They | +0.086 |
likes | +0.084 |
and | +0.079 |
with | +0.072 |
liked | +0.066 |
Neg logit contributions | |
iqu | -0.182 |
erk | -0.176 |
otion | -0.175 |
ous | -0.174 |
ately | -0.173 |
Token | piece |
Token ID | 3704 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
They | +0.145 |
likes | +0.133 |
They | +0.126 |
with | +0.121 |
and | +0.119 |
Neg logit contributions | |
erk | -0.158 |
hesitation | -0.157 |
otion | -0.156 |
ow | -0.155 |
unct | -0.152 |
Token | ." |
Token ID | 526 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
likes | +0.017 |
They | +0.017 |
liked | +0.014 |
sounds | +0.014 |
grass | +0.014 |
Neg logit contributions | |
ow | -0.027 |
otion | -0.027 |
ous | -0.026 |
ately | -0.026 |
erk | -0.026 |
Token | She |
Token ID | 1375 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
likes | +0.029 |
games | +0.028 |
fair | +0.024 |
nice | +0.024 |
shapes | +0.023 |
Neg logit contributions | |
otion | -0.075 |
antis | -0.074 |
ately | -0.074 |
ama | -0.074 |
iqu | -0.072 |
Token | cut |
Token ID | 2005 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
They | +0.056 |
likes | +0.056 |
and | +0.049 |
fun | +0.048 |
nice | +0.048 |
Neg logit contributions | |
ately | -0.076 |
iqu | -0.075 |
erk | -0.075 |
wen | -0.073 |
otion | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
iqu | +0.029 |
ately | +0.029 |
otion | +0.029 |
wen | +0.028 |
erk | +0.028 |
Neg logit contributions | |
likes | -0.010 |
and | -0.010 |
They | -0.010 |
with | -0.009 |
liked | -0.008 |
Token | chair |
Token ID | 5118 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
They | +0.006 |
They | +0.006 |
likes | +0.006 |
and | +0.005 |
with | +0.005 |
Neg logit contributions | |
erk | -0.007 |
iqu | -0.007 |
ama | -0.007 |
ow | -0.007 |
ately | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
likes | +0.004 |
They | +0.004 |
and | +0.003 |
with | +0.003 |
nice | +0.002 |
Neg logit contributions | |
iqu | -0.019 |
ately | -0.019 |
erk | -0.018 |
otion | -0.018 |
wen | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
likes | +0.008 |
and | +0.007 |
They | +0.007 |
with | +0.006 |
nice | +0.006 |
Neg logit contributions | |
iqu | -0.020 |
ately | -0.020 |
otion | -0.020 |
erk | -0.020 |
used | -0.020 |
Token | had |
Token ID | 550 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
They | +0.031 |
likes | +0.031 |
and | +0.029 |
with | +0.027 |
nice | +0.025 |
Neg logit contributions | |
iqu | -0.058 |
ately | -0.057 |
erk | -0.057 |
wen | -0.056 |
otion | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
likes | +0.028 |
They | +0.027 |
and | +0.025 |
with | +0.023 |
liked | +0.021 |
Neg logit contributions | |
iqu | -0.041 |
ately | -0.041 |
erk | -0.041 |
wen | -0.041 |
hesitation | -0.040 |
Token | big |
Token ID | 1263 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
They | +0.074 |
likes | +0.070 |
and | +0.065 |
with | +0.060 |
liked | +0.051 |
Neg logit contributions | |
iqu | -0.183 |
erk | -0.178 |
hesitation | -0.175 |
wen | -0.174 |
ately | -0.172 |
Token | , |
Token ID | 11 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
They | +0.146 |
likes | +0.130 |
They | +0.125 |
with | +0.122 |
| +0.118 |
Neg logit contributions | |
hesitation | -0.166 |
erk | -0.164 |
iqu | -0.157 |
ow | -0.156 |
otion | -0.154 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
They | +0.004 |
likes | +0.004 |
and | +0.003 |
with | +0.003 |
| +0.003 |
Neg logit contributions | |
iqu | -0.008 |
erk | -0.008 |
ately | -0.008 |
hesitation | -0.008 |
antis | -0.008 |
Token | smile |
Token ID | 8212 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
likes | +0.071 |
They | +0.069 |
They | +0.059 |
liked | +0.058 |
shapes | +0.057 |
Neg logit contributions | |
ous | -0.085 |
hesitation | -0.083 |
erk | -0.083 |
ow | -0.079 |
ately | -0.078 |
Token | on |
Token ID | 319 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
and | +0.024 |
likes | +0.023 |
They | +0.022 |
with | +0.020 |
liked | +0.017 |
Neg logit contributions | |
iqu | -0.075 |
otion | -0.074 |
ately | -0.073 |
wen | -0.073 |
erk | -0.072 |
Token | her |
Token ID | 607 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
likes | +0.027 |
They | +0.024 |
and | +0.023 |
liked | +0.023 |
boy | +0.022 |
Neg logit contributions | |
otion | -0.040 |
iqu | -0.039 |
ow | -0.039 |
used | -0.039 |
unct | -0.038 |
Token | Carl |
Token ID | 8124 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
likes | +0.001 |
and | +0.001 |
They | +0.001 |
with | +0.001 |
nice | +0.001 |
Neg logit contributions | |
iqu | -0.001 |
ately | -0.001 |
aro | -0.001 |
erk | -0.001 |
ous | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
They | +0.017 |
likes | +0.017 |
games | +0.015 |
Let | +0.015 |
grass | +0.015 |
Neg logit contributions | |
ow | -0.053 |
erk | -0.050 |
ately | -0.050 |
hesitation | -0.050 |
owing | -0.050 |
Token | They |
Token ID | 1119 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
likes | +0.020 |
games | +0.018 |
nice | +0.018 |
fair | +0.017 |
and | +0.016 |
Neg logit contributions | |
aro | -0.065 |
otion | -0.063 |
ow | -0.062 |
antis | -0.061 |
iqu | -0.061 |
Token | had |
Token ID | 550 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
likes | +0.067 |
They | +0.063 |
and | +0.061 |
with | +0.058 |
nice | +0.053 |
Neg logit contributions | |
iqu | -0.131 |
ately | -0.131 |
otion | -0.130 |
erk | -0.129 |
wen | -0.129 |
Token | a |
Token ID | 257 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
likes | +0.063 |
They | +0.051 |
with | +0.048 |
and | +0.047 |
girl | +0.047 |
Neg logit contributions | |
ow | -0.085 |
hesitation | -0.085 |
erk | -0.083 |
ver | -0.080 |
ately | -0.080 |
Token | big |
Token ID | 1263 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
likes | +0.075 |
They | +0.074 |
and | +0.066 |
with | +0.063 |
shapes | +0.053 |
Neg logit contributions | |
iqu | -0.196 |
erk | -0.189 |
hesitation | -0.188 |
wen | -0.185 |
tha | -0.184 |
Token | party |
Token ID | 2151 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
They | +0.134 |
likes | +0.127 |
with | +0.121 |
They | +0.115 |
shapes | +0.112 |
Neg logit contributions | |
hesitation | -0.168 |
erk | -0.164 |
ow | -0.156 |
tha | -0.156 |
ama | -0.154 |
Token | to |
Token ID | 284 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
likes | +0.029 |
They | +0.025 |
grass | +0.021 |
green | +0.020 |
holes | +0.020 |
Neg logit contributions | |
ately | -0.087 |
ow | -0.087 |
ous | -0.087 |
icking | -0.086 |
erk | -0.086 |
Token | celebrate |
Token ID | 10648 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
iqu | +0.010 |
otion | +0.009 |
ately | +0.009 |
wen | +0.009 |
used | +0.009 |
Neg logit contributions | |
likes | -0.004 |
and | -0.004 |
They | -0.004 |
with | -0.004 |
nice | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
likes | +0.021 |
They | +0.017 |
green | +0.013 |
and | +0.012 |
liked | +0.012 |
Neg logit contributions | |
ately | -0.070 |
erk | -0.068 |
aro | -0.067 |
iqu | -0.067 |
icking | -0.067 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
likes | +0.019 |
and | +0.015 |
games | +0.015 |
nice | +0.015 |
fair | +0.014 |
Neg logit contributions | |
aro | -0.070 |
otion | -0.069 |
ow | -0.069 |
iqu | -0.068 |
antis | -0.068 |
Token | L |
Token ID | 406 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
likes | +0.021 |
games | +0.016 |
and | +0.015 |
with | +0.013 |
fair | +0.012 |
Neg logit contributions | |
otion | -0.128 |
iqu | -0.128 |
ately | -0.126 |
erk | -0.126 |
wen | -0.125 |
Token | ila |
Token ID | 10102 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
iqu | +0.066 |
used | +0.062 |
hesitation | +0.062 |
unct | +0.061 |
ous | +0.061 |
Neg logit contributions | |
and | -0.102 |
likes | -0.096 |
They | -0.094 |
with | -0.091 |
| -0.088 |
Token | and |
Token ID | 290 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
They | +0.025 |
fun | +0.023 |
nice | +0.021 |
games | +0.021 |
holes | +0.020 |
Neg logit contributions | |
ately | -0.108 |
ow | -0.105 |
ver | -0.104 |
illa | -0.103 |
wen | -0.102 |
Token | R |
Token ID | 371 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
iqu | +0.014 |
otion | +0.013 |
ately | +0.013 |
wen | +0.013 |
used | +0.013 |
Neg logit contributions | |
They | -0.006 |
and | -0.005 |
likes | -0.005 |
with | -0.005 |
each | -0.004 |
Token | ani |
Token ID | 3216 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
iqu | +0.073 |
otion | +0.071 |
used | +0.069 |
wen | +0.068 |
ately | +0.068 |
Neg logit contributions | |
and | -0.133 |
likes | -0.132 |
They | -0.130 |
with | -0.123 |
| -0.118 |
Token | smiled |
Token ID | 13541 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
They | +0.038 |
likes | +0.036 |
fun | +0.034 |
with | +0.034 |
nice | +0.034 |
Neg logit contributions | |
ately | -0.061 |
erk | -0.060 |
ow | -0.060 |
ous | -0.058 |
otion | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
likes | +0.062 |
games | +0.056 |
grass | +0.051 |
bases | +0.046 |
Let | +0.043 |
Neg logit contributions | |
ous | -0.227 |
icking | -0.223 |
ately | -0.219 |
ow | -0.218 |
ver | -0.213 |
Token | hugged |
Token ID | 41130 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
likes | +0.043 |
and | +0.040 |
They | +0.039 |
with | +0.037 |
games | +0.035 |
Neg logit contributions | |
ately | -0.069 |
iqu | -0.068 |
erk | -0.068 |
ous | -0.068 |
ow | -0.067 |
Token | each |
Token ID | 1123 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
likes | +0.021 |
They | +0.019 |
and | +0.019 |
with | +0.015 |
liked | +0.013 |
Neg logit contributions | |
iqu | -0.102 |
ately | -0.101 |
otion | -0.100 |
erk | -0.099 |
wen | -0.099 |
Token | other |
Token ID | 584 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
likes | +0.031 |
They | +0.029 |
with | +0.028 |
and | +0.025 |
liked | +0.025 |
Neg logit contributions | |
hesitation | -0.056 |
ately | -0.055 |
wen | -0.055 |
otion | -0.054 |
illa | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
likes | +0.027 |
They | +0.023 |
liked | +0.019 |
fun | +0.018 |
Let | +0.017 |
Neg logit contributions | |
ow | -0.089 |
ately | -0.088 |
erk | -0.088 |
icking | -0.087 |
ous | -0.087 |
Token | be |
Token ID | 307 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
iqu | +0.009 |
ately | +0.009 |
otion | +0.009 |
wen | +0.009 |
erk | +0.009 |
Neg logit contributions | |
likes | -0.004 |
and | -0.004 |
They | -0.004 |
with | -0.004 |
liked | -0.004 |
Token | enough |
Token ID | 1576 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
iqu | +0.044 |
otion | +0.042 |
erk | +0.042 |
ately | +0.042 |
wen | +0.042 |
Neg logit contributions | |
likes | -0.025 |
They | -0.025 |
and | -0.024 |
with | -0.022 |
| -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
likes | +0.003 |
They | +0.003 |
and | +0.003 |
with | +0.003 |
liked | +0.002 |
Neg logit contributions | |
ately | -0.011 |
iqu | -0.011 |
otion | -0.010 |
erk | -0.010 |
ous | -0.010 |
Token | make |
Token ID | 787 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
wen | +0.064 |
iqu | +0.064 |
otion | +0.064 |
ately | +0.063 |
ous | +0.062 |
Neg logit contributions | |
and | -0.031 |
with | -0.028 |
likes | -0.028 |
They | -0.028 |
nice | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
iqu | +0.048 |
otion | +0.047 |
ately | +0.047 |
wen | +0.046 |
erk | +0.046 |
Neg logit contributions | |
likes | -0.018 |
They | -0.017 |
and | -0.017 |
with | -0.015 |
liked | -0.014 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
iqu | +0.027 |
otion | +0.026 |
ately | +0.026 |
wen | +0.025 |
ous | +0.025 |
Neg logit contributions | |
and | -0.028 |
likes | -0.028 |
They | -0.027 |
with | -0.026 |
nice | -0.025 |
Token | ich |
Token ID | 488 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
otion | +0.237 |
hesitation | +0.233 |
izz | +0.215 |
erk | +0.211 |
abella | +0.211 |
Neg logit contributions | |
and | -0.283 |
with | -0.268 |
likes | -0.268 |
| -0.251 |
They | -0.248 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
iqu | +0.091 |
otion | +0.089 |
erk | +0.089 |
ately | +0.089 |
ow | +0.089 |
Neg logit contributions | |
likes | -0.047 |
They | -0.045 |
and | -0.043 |
with | -0.039 |
liked | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
likes | +0.027 |
They | +0.025 |
and | +0.019 |
nice | +0.019 |
grass | +0.019 |
Neg logit contributions | |
ately | -0.078 |
ous | -0.076 |
erk | -0.076 |
otion | -0.076 |
ow | -0.075 |
Token | so |
Token ID | 523 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
likes | +0.014 |
They | +0.013 |
and | +0.011 |
with | +0.011 |
liked | +0.011 |
Neg logit contributions | |
ately | -0.028 |
hesitation | -0.028 |
iqu | -0.027 |
erk | -0.027 |
used | -0.027 |
Token | he |
Token ID | 339 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
iqu | +0.008 |
otion | +0.008 |
wen | +0.008 |
ately | +0.008 |
erk | +0.008 |
Neg logit contributions | |
and | -0.004 |
likes | -0.004 |
They | -0.004 |
with | -0.004 |
| -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
iqu | +0.049 |
ately | +0.048 |
otion | +0.048 |
wen | +0.048 |
erk | +0.048 |
Neg logit contributions | |
likes | -0.010 |
and | -0.010 |
They | -0.010 |
with | -0.008 |
nice | -0.007 |
Token | zoo |
Token ID | 26626 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
iqu | +0.019 |
otion | +0.019 |
ately | +0.019 |
wen | +0.019 |
erk | +0.019 |
Neg logit contributions | |
likes | -0.006 |
and | -0.006 |
They | -0.005 |
with | -0.005 |
nice | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
ow | +0.077 |
ately | +0.075 |
otion | +0.075 |
erk | +0.074 |
iqu | +0.074 |
Neg logit contributions | |
likes | -0.023 |
They | -0.020 |
nice | -0.015 |
fun | -0.015 |
and | -0.014 |
Token | see |
Token ID | 766 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
iqu | +0.068 |
ately | +0.066 |
wen | +0.066 |
otion | +0.065 |
ous | +0.064 |
Neg logit contributions | |
and | -0.025 |
likes | -0.025 |
They | -0.024 |
with | -0.022 |
nice | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
iqu | +0.014 |
ately | +0.013 |
otion | +0.013 |
wen | +0.013 |
erk | +0.013 |
Neg logit contributions | |
likes | -0.003 |
and | -0.003 |
They | -0.003 |
with | -0.003 |
nice | -0.002 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
iqu | +0.025 |
otion | +0.024 |
ately | +0.024 |
wen | +0.024 |
used | +0.024 |
Neg logit contributions | |
likes | -0.016 |
and | -0.016 |
They | -0.016 |
with | -0.015 |
nice | -0.014 |
Token | ich |
Token ID | 488 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
otion | +0.221 |
hesitation | +0.221 |
erk | +0.210 |
iqu | +0.203 |
izz | +0.199 |
Neg logit contributions | |
and | -0.294 |
with | -0.280 |
likes | -0.277 |
| -0.267 |
They | -0.263 |
Token | . |
Token ID | 13 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
iqu | +0.148 |
ately | +0.146 |
otion | +0.146 |
wen | +0.145 |
erk | +0.144 |
Neg logit contributions | |
likes | -0.024 |
and | -0.023 |
They | -0.022 |
with | -0.018 |
liked | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
ow | +0.013 |
ous | +0.013 |
used | +0.013 |
otion | +0.013 |
ately | +0.013 |
Neg logit contributions | |
likes | -0.006 |
fun | -0.005 |
and | -0.005 |
nice | -0.005 |
with | -0.005 |
Token | observed |
Token ID | 6515 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
likes | +0.008 |
They | +0.008 |
and | +0.008 |
with | +0.007 |
nice | +0.006 |
Neg logit contributions | |
iqu | -0.028 |
ately | -0.027 |
otion | -0.027 |
wen | -0.027 |
erk | -0.027 |
Token | it |
Token ID | 340 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
and | +0.004 |
likes | +0.004 |
They | +0.004 |
with | +0.003 |
nice | +0.002 |
Neg logit contributions | |
iqu | -0.020 |
otion | -0.020 |
ately | -0.020 |
wen | -0.020 |
erk | -0.020 |
Token | Ben |
Token ID | 11696 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
wen | +0.007 |
otion | +0.007 |
abella | +0.007 |
iqu | +0.007 |
antis | +0.007 |
Neg logit contributions | |
likes | -0.005 |
and | -0.005 |
They | -0.005 |
fun | -0.005 |
shapes | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
They | +0.019 |
nice | +0.017 |
fun | +0.017 |
new | +0.017 |
likes | +0.016 |
Neg logit contributions | |
ow | -0.033 |
ately | -0.033 |
used | -0.031 |
erk | -0.031 |
wen | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
and | +0.007 |
They | +0.006 |
likes | +0.006 |
with | +0.005 |
| +0.004 |
Neg logit contributions | |
iqu | -0.035 |
otion | -0.035 |
ately | -0.034 |
used | -0.034 |
wen | -0.034 |
Token | touch |
Token ID | 3638 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
iqu | +0.085 |
otion | +0.083 |
ately | +0.083 |
wen | +0.082 |
erk | +0.081 |
Neg logit contributions | |
and | -0.035 |
likes | -0.035 |
They | -0.034 |
with | -0.031 |
nice | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
iqu | +0.001 |
otion | +0.001 |
wen | +0.001 |
ately | +0.001 |
ous | +0.001 |
Neg logit contributions | |
and | -0.000 |
They | -0.000 |
likes | -0.000 |
with | -0.000 |
green | -0.000 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
iqu | +0.037 |
otion | +0.036 |
ately | +0.036 |
erk | +0.035 |
wen | +0.035 |
Neg logit contributions | |
and | -0.042 |
likes | -0.042 |
They | -0.040 |
with | -0.039 |
nice | -0.038 |
Token | ich |
Token ID | 488 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
hesitation | +0.248 |
otion | +0.246 |
izz | +0.228 |
erk | +0.226 |
abella | +0.224 |
Neg logit contributions | |
and | -0.273 |
with | -0.258 |
likes | -0.252 |
| -0.240 |
They | -0.231 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
iqu | +0.132 |
wen | +0.131 |
otion | +0.128 |
ately | +0.128 |
used | +0.126 |
Neg logit contributions | |
and | -0.026 |
likes | -0.021 |
with | -0.021 |
They | -0.021 |
nice | -0.014 |
Token | but |
Token ID | 475 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
iqu | +0.003 |
ately | +0.003 |
otion | +0.003 |
ow | +0.003 |
erk | +0.003 |
Neg logit contributions | |
likes | -0.001 |
They | -0.001 |
and | -0.001 |
with | -0.001 |
liked | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
iqu | +0.119 |
ous | +0.114 |
otion | +0.114 |
wen | +0.113 |
used | +0.112 |
Neg logit contributions | |
and | -0.032 |
likes | -0.029 |
They | -0.028 |
with | -0.027 |
liked | -0.024 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
otion | +0.064 |
iqu | +0.062 |
used | +0.061 |
ately | +0.061 |
wen | +0.060 |
Neg logit contributions | |
and | -0.033 |
likes | -0.033 |
They | -0.029 |
green | -0.029 |
with | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
iqu | +0.045 |
ately | +0.044 |
wen | +0.044 |
otion | +0.044 |
erk | +0.043 |
Neg logit contributions | |
and | -0.018 |
likes | -0.018 |
They | -0.017 |
with | -0.016 |
nice | -0.014 |
Token | let |
Token ID | 1309 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
iqu | +0.092 |
otion | +0.090 |
wen | +0.089 |
ately | +0.089 |
ous | +0.088 |
Neg logit contributions | |
and | -0.055 |
likes | -0.051 |
with | -0.051 |
They | -0.051 |
nice | -0.046 |
Token | him |
Token ID | 683 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
iqu | +0.070 |
ately | +0.068 |
otion | +0.068 |
wen | +0.067 |
erk | +0.067 |
Neg logit contributions | |
likes | -0.046 |
and | -0.045 |
They | -0.045 |
with | -0.042 |
nice | -0.038 |
Token | touch |
Token ID | 3638 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
iqu | +0.107 |
ately | +0.105 |
otion | +0.105 |
wen | +0.104 |
erk | +0.103 |
Neg logit contributions | |
likes | -0.052 |
and | -0.051 |
They | -0.051 |
with | -0.046 |
liked | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
iqu | +0.009 |
otion | +0.009 |
wen | +0.009 |
ately | +0.008 |
used | +0.008 |
Neg logit contributions | |
and | -0.002 |
They | -0.001 |
likes | -0.001 |
with | -0.001 |
| -0.001 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
iqu | +0.011 |
otion | +0.011 |
ately | +0.011 |
wen | +0.010 |
erk | +0.010 |
Neg logit contributions | |
likes | -0.015 |
and | -0.015 |
They | -0.014 |
with | -0.014 |
nice | -0.013 |
Token | ich |
Token ID | 488 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
otion | +0.242 |
hesitation | +0.239 |
izz | +0.221 |
abella | +0.218 |
erk | +0.217 |
Neg logit contributions | |
and | -0.271 |
with | -0.253 |
likes | -0.251 |
| -0.241 |
They | -0.231 |
Token | . |
Token ID | 13 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
iqu | +0.178 |
wen | +0.175 |
ately | +0.173 |
otion | +0.173 |
used | +0.170 |
Neg logit contributions | |
and | -0.028 |
likes | -0.023 |
They | -0.022 |
with | -0.020 |
nice | -0.012 |
Token | His |
Token ID | 2399 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
likes | +0.007 |
and | +0.006 |
fun | +0.006 |
games | +0.006 |
with | +0.006 |
Neg logit contributions | |
ately | -0.009 |
ow | -0.009 |
otion | -0.009 |
iqu | -0.009 |
erk | -0.009 |
Token | dad |
Token ID | 9955 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
otion | +0.045 |
iqu | +0.045 |
used | +0.044 |
ately | +0.044 |
ous | +0.043 |
Neg logit contributions | |
and | -0.030 |
likes | -0.029 |
They | -0.028 |
with | -0.026 |
nice | -0.025 |
Token | said |
Token ID | 531 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
and | +0.012 |
likes | +0.012 |
They | +0.011 |
with | +0.011 |
liked | +0.010 |
Neg logit contributions | |
iqu | -0.025 |
otion | -0.025 |
ately | -0.025 |
wen | -0.025 |
ous | -0.024 |
Token | me |
Token ID | 502 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
likes | +0.004 |
They | +0.003 |
games | +0.003 |
with | +0.003 |
liked | +0.003 |
Neg logit contributions | |
wen | -0.010 |
ow | -0.010 |
ately | -0.010 |
iqu | -0.010 |
ama | -0.010 |
Token | introduce |
Token ID | 10400 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
iqu | +0.099 |
otion | +0.098 |
wen | +0.097 |
ately | +0.097 |
antis | +0.094 |
Neg logit contributions | |
and | -0.047 |
likes | -0.044 |
They | -0.043 |
with | -0.042 |
nice | -0.037 |
Token | you |
Token ID | 345 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
likes | +0.012 |
and | +0.012 |
They | +0.011 |
with | +0.010 |
nice | +0.009 |
Neg logit contributions | |
iqu | -0.027 |
otion | -0.026 |
ately | -0.026 |
wen | -0.026 |
erk | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
likes | +0.010 |
They | +0.009 |
and | +0.008 |
liked | +0.007 |
with | +0.007 |
Neg logit contributions | |
iqu | -0.025 |
ow | -0.025 |
ately | -0.025 |
wen | -0.025 |
used | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
iqu | +0.008 |
otion | +0.008 |
ately | +0.008 |
wen | +0.008 |
erk | +0.008 |
Neg logit contributions | |
and | -0.002 |
likes | -0.001 |
They | -0.001 |
with | -0.001 |
nice | -0.001 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
otion | +0.011 |
iqu | +0.011 |
ately | +0.011 |
used | +0.011 |
erk | +0.011 |
Neg logit contributions | |
and | -0.013 |
likes | -0.013 |
They | -0.012 |
nice | -0.012 |
with | -0.012 |
Token | ich |
Token ID | 488 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
hesitation | +0.246 |
otion | +0.238 |
erk | +0.217 |
izz | +0.214 |
iqu | +0.212 |
Neg logit contributions | |
and | -0.265 |
with | -0.247 |
likes | -0.239 |
| -0.231 |
They | -0.220 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ately | +0.095 |
iqu | +0.095 |
ow | +0.095 |
otion | +0.094 |
ous | +0.094 |
Neg logit contributions | |
likes | -0.027 |
They | -0.025 |
and | -0.023 |
with | -0.020 |
fun | -0.019 |
Token | This |
Token ID | 770 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
They | +0.017 |
likes | +0.017 |
and | +0.016 |
with | +0.015 |
| +0.013 |
Neg logit contributions | |
iqu | -0.049 |
ately | -0.048 |
otion | -0.048 |
wen | -0.048 |
erk | -0.048 |
Token | is |
Token ID | 318 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
iqu | +0.022 |
otion | +0.022 |
ately | +0.022 |
wen | +0.021 |
erk | +0.021 |
Neg logit contributions | |
likes | -0.019 |
They | -0.019 |
and | -0.019 |
with | -0.018 |
liked | -0.017 |
Token | M |
Token ID | 337 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
iqu | +0.032 |
ately | +0.032 |
otion | +0.032 |
wen | +0.032 |
erk | +0.031 |
Neg logit contributions | |
likes | -0.009 |
and | -0.009 |
They | -0.008 |
with | -0.007 |
nice | -0.006 |
Token | if |
Token ID | 611 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
iqu | +0.131 |
wen | +0.130 |
ately | +0.129 |
otion | +0.127 |
unct | +0.126 |
Neg logit contributions | |
and | -0.048 |
likes | -0.044 |
They | -0.044 |
with | -0.043 |
| -0.036 |
Token | they |
Token ID | 484 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
iqu | +0.101 |
wen | +0.097 |
otion | +0.096 |
erk | +0.096 |
ately | +0.095 |
Neg logit contributions | |
and | -0.038 |
They | -0.037 |
with | -0.036 |
likes | -0.036 |
| -0.032 |
Token | could |
Token ID | 714 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
iqu | +0.029 |
wen | +0.029 |
otion | +0.029 |
ately | +0.028 |
used | +0.028 |
Neg logit contributions | |
likes | -0.015 |
and | -0.015 |
They | -0.014 |
with | -0.013 |
liked | -0.012 |
Token | see |
Token ID | 766 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
iqu | +0.123 |
wen | +0.119 |
ately | +0.118 |
otion | +0.116 |
ous | +0.115 |
Neg logit contributions | |
and | -0.051 |
with | -0.046 |
They | -0.045 |
likes | -0.042 |
| -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
iqu | +0.020 |
ately | +0.020 |
otion | +0.019 |
wen | +0.019 |
used | +0.019 |
Neg logit contributions | |
likes | -0.006 |
and | -0.006 |
They | -0.005 |
with | -0.005 |
nice | -0.004 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
iqu | +0.023 |
ately | +0.023 |
otion | +0.023 |
wen | +0.022 |
used | +0.022 |
Neg logit contributions | |
likes | -0.021 |
and | -0.021 |
They | -0.020 |
with | -0.019 |
nice | -0.019 |
Token | ich |
Token ID | 488 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
otion | +0.232 |
hesitation | +0.230 |
erk | +0.215 |
izz | +0.215 |
iqu | +0.211 |
Neg logit contributions | |
and | -0.271 |
likes | -0.253 |
with | -0.249 |
| -0.235 |
They | -0.232 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
iqu | +0.168 |
wen | +0.167 |
ately | +0.165 |
otion | +0.162 |
antis | +0.161 |
Neg logit contributions | |
and | -0.026 |
likes | -0.021 |
They | -0.020 |
with | -0.020 |
nice | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
likes | +0.010 |
and | +0.009 |
games | +0.008 |
nice | +0.008 |
fun | +0.007 |
Neg logit contributions | |
otion | -0.038 |
ately | -0.038 |
ow | -0.037 |
used | -0.037 |
iqu | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
otion | +0.036 |
wen | +0.035 |
iqu | +0.035 |
ately | +0.035 |
erk | +0.035 |
Neg logit contributions | |
likes | -0.006 |
and | -0.004 |
They | -0.004 |
games | -0.003 |
with | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
used | +0.058 |
aro | +0.057 |
otion | +0.056 |
wen | +0.056 |
izz | +0.055 |
Neg logit contributions | |
likes | -0.022 |
and | -0.019 |
They | -0.019 |
fun | -0.017 |
games | -0.017 |
Token | apple |
Token ID | 17180 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
iqu | +0.004 |
ately | +0.004 |
otion | +0.004 |
used | +0.004 |
hesitation | +0.004 |
Neg logit contributions | |
They | -0.003 |
likes | -0.003 |
and | -0.003 |
with | -0.003 |
liked | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
ately | +0.135 |
otion | +0.134 |
iqu | +0.134 |
erk | +0.133 |
ow | +0.133 |
Neg logit contributions | |
likes | -0.025 |
They | -0.020 |
and | -0.014 |
liked | -0.013 |
fun | -0.012 |
Token | slowly |
Token ID | 6364 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
iqu | +0.026 |
ately | +0.026 |
erk | +0.025 |
used | +0.025 |
otion | +0.025 |
Neg logit contributions | |
likes | -0.015 |
They | -0.014 |
and | -0.014 |
with | -0.012 |
nice | -0.012 |
Token | approached |
Token ID | 10448 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
iqu | +0.014 |
ately | +0.014 |
otion | +0.014 |
wen | +0.014 |
erk | +0.014 |
Neg logit contributions | |
likes | -0.009 |
and | -0.009 |
They | -0.009 |
with | -0.008 |
liked | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
iqu | +0.029 |
ately | +0.029 |
otion | +0.029 |
wen | +0.028 |
used | +0.028 |
Neg logit contributions | |
likes | -0.010 |
They | -0.010 |
and | -0.010 |
with | -0.009 |
liked | -0.008 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
iqu | +0.043 |
ately | +0.043 |
otion | +0.042 |
wen | +0.042 |
erk | +0.041 |
Neg logit contributions | |
likes | -0.030 |
They | -0.030 |
and | -0.029 |
with | -0.027 |
liked | -0.025 |
Token | ich |
Token ID | 488 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
otion | +0.214 |
hesitation | +0.202 |
izz | +0.186 |
iqu | +0.186 |
erk | +0.185 |
Neg logit contributions | |
and | -0.295 |
likes | -0.280 |
with | -0.274 |
They | -0.268 |
| -0.262 |
Token | . |
Token ID | 13 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
iqu | +0.136 |
ately | +0.135 |
otion | +0.134 |
erk | +0.133 |
used | +0.132 |
Neg logit contributions | |
likes | -0.026 |
They | -0.024 |
and | -0.023 |
with | -0.018 |
liked | -0.016 |
Token | |
Token ID | 220 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
used | +0.021 |
ately | +0.021 |
iqu | +0.021 |
ow | +0.021 |
otion | +0.020 |
Neg logit contributions | |
likes | -0.010 |
and | -0.009 |
nice | -0.009 |
pretty | -0.008 |
games | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
iqu | +0.050 |
otion | +0.050 |
ately | +0.050 |
wen | +0.049 |
erk | +0.049 |
Neg logit contributions | |
likes | -0.006 |
and | -0.004 |
They | -0.004 |
with | -0.003 |
nice | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
wen | +0.034 |
otion | +0.034 |
ately | +0.034 |
iqu | +0.034 |
used | +0.034 |
Neg logit contributions | |
likes | -0.005 |
and | -0.004 |
They | -0.004 |
with | -0.003 |
liked | -0.002 |
Token | went |
Token ID | 1816 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
likes | +0.031 |
and | +0.031 |
They | +0.030 |
with | +0.028 |
liked | +0.026 |
Neg logit contributions | |
iqu | -0.054 |
otion | -0.053 |
ately | -0.053 |
wen | -0.052 |
erk | -0.052 |
Token | outside |
Token ID | 2354 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
iqu | +0.015 |
ately | +0.015 |
otion | +0.015 |
erk | +0.015 |
wen | +0.015 |
Neg logit contributions | |
likes | -0.006 |
They | -0.005 |
and | -0.005 |
with | -0.004 |
liked | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
likes | +0.018 |
They | +0.014 |
nice | +0.011 |
liked | +0.010 |
fun | +0.010 |
Neg logit contributions | |
ately | -0.070 |
erk | -0.069 |
ow | -0.069 |
otion | -0.068 |
ous | -0.068 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
iqu | +0.020 |
otion | +0.020 |
wen | +0.020 |
ately | +0.019 |
ous | +0.019 |
Neg logit contributions | |
and | -0.006 |
They | -0.006 |
likes | -0.005 |
with | -0.005 |
liked | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
and | +0.002 |
They | +0.002 |
likes | +0.002 |
with | +0.001 |
nice | +0.001 |
Neg logit contributions | |
iqu | -0.008 |
ately | -0.008 |
otion | -0.008 |
wen | -0.008 |
used | -0.008 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
iqu | +0.023 |
otion | +0.023 |
ately | +0.023 |
used | +0.022 |
erk | +0.022 |
Neg logit contributions | |
and | -0.031 |
likes | -0.031 |
They | -0.030 |
with | -0.029 |
nice | -0.028 |
Token | ich |
Token ID | 488 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
hesitation | +0.219 |
otion | +0.217 |
erk | +0.207 |
iqu | +0.200 |
abella | +0.194 |
Neg logit contributions | |
and | -0.278 |
likes | -0.259 |
with | -0.255 |
| -0.243 |
They | -0.238 |
Token | walking |
Token ID | 6155 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
iqu | +0.106 |
ately | +0.104 |
otion | +0.104 |
wen | +0.103 |
erk | +0.102 |
Neg logit contributions | |
likes | -0.026 |
and | -0.026 |
They | -0.025 |
with | -0.021 |
liked | -0.018 |
Token | around |
Token ID | 1088 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
likes | +0.006 |
They | +0.005 |
and | +0.005 |
fun | +0.004 |
nice | +0.004 |
Neg logit contributions | |
ow | -0.011 |
iqu | -0.011 |
used | -0.011 |
ately | -0.011 |
erk | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
likes | +0.019 |
They | +0.016 |
and | +0.013 |
nice | +0.012 |
with | +0.011 |
Neg logit contributions | |
ately | -0.062 |
otion | -0.062 |
used | -0.061 |
erk | -0.061 |
iqu | -0.061 |
Token | " |
Token ID | 366 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ous | +0.005 |
iqu | +0.005 |
ately | +0.005 |
otion | +0.005 |
used | +0.005 |
Neg logit contributions | |
likes | -0.002 |
and | -0.002 |
nice | -0.002 |
fun | -0.002 |
with | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
iqu | +0.059 |
ately | +0.059 |
otion | +0.058 |
wen | +0.057 |
erk | +0.057 |
Neg logit contributions | |
and | -0.032 |
likes | -0.032 |
They | -0.031 |
with | -0.030 |
nice | -0.027 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
iqu | +0.009 |
otion | +0.008 |
erk | +0.008 |
used | +0.008 |
ous | +0.008 |
Neg logit contributions | |
likes | -0.004 |
They | -0.004 |
and | -0.003 |
with | -0.003 |
grass | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
likes | +0.019 |
They | +0.016 |
liked | +0.013 |
and | +0.013 |
nice | +0.013 |
Neg logit contributions | |
ately | -0.045 |
ous | -0.044 |
iqu | -0.044 |
otion | -0.043 |
wen | -0.043 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
iqu | +0.027 |
ately | +0.027 |
ous | +0.027 |
used | +0.027 |
erk | +0.026 |
Neg logit contributions | |
likes | -0.017 |
They | -0.016 |
and | -0.016 |
with | -0.014 |
| -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
iqu | +0.073 |
otion | +0.071 |
ately | +0.071 |
wen | +0.071 |
erk | +0.070 |
Neg logit contributions | |
likes | -0.030 |
and | -0.030 |
They | -0.029 |
with | -0.027 |
nice | -0.024 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
iqu | +0.048 |
otion | +0.047 |
ately | +0.047 |
wen | +0.046 |
erk | +0.046 |
Neg logit contributions | |
likes | -0.023 |
and | -0.022 |
They | -0.022 |
with | -0.020 |
nice | -0.018 |
Token | ich |
Token ID | 488 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
otion | +0.237 |
hesitation | +0.213 |
izz | +0.213 |
erk | +0.209 |
unct | +0.189 |
Neg logit contributions | |
and | -0.265 |
with | -0.248 |
likes | -0.247 |
| -0.228 |
They | -0.226 |
Token | what |
Token ID | 644 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
iqu | +0.115 |
wen | +0.115 |
otion | +0.113 |
ately | +0.113 |
izz | +0.110 |
Neg logit contributions | |
and | -0.052 |
They | -0.048 |
likes | -0.048 |
with | -0.047 |
| -0.041 |
Token | was |
Token ID | 373 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
iqu | +0.024 |
otion | +0.023 |
ately | +0.023 |
erk | +0.023 |
ous | +0.023 |
Neg logit contributions | |
likes | -0.011 |
They | -0.011 |
and | -0.010 |
with | -0.009 |
nice | -0.008 |
Token | happening |
Token ID | 5836 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
iqu | +0.069 |
ately | +0.068 |
otion | +0.067 |
wen | +0.067 |
erk | +0.066 |
Neg logit contributions | |
and | -0.054 |
likes | -0.053 |
They | -0.052 |
with | -0.051 |
nice | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
iqu | +0.007 |
ately | +0.007 |
otion | +0.007 |
wen | +0.006 |
erk | +0.006 |
Neg logit contributions | |
likes | -0.001 |
They | -0.001 |
and | -0.001 |
with | -0.001 |
liked | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
likes | +0.014 |
and | +0.011 |
games | +0.010 |
fair | +0.009 |
toy | +0.009 |
Neg logit contributions | |
otion | -0.071 |
ately | -0.070 |
erk | -0.068 |
iqu | -0.068 |
antis | -0.068 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
likes | +0.027 |
and | +0.027 |
They | +0.026 |
liked | +0.023 |
with | +0.023 |
Neg logit contributions | |
iqu | -0.069 |
otion | -0.069 |
ately | -0.067 |
wen | -0.067 |
ous | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
and | +0.004 |
They | +0.004 |
likes | +0.004 |
with | +0.004 |
nice | +0.003 |
Neg logit contributions | |
iqu | -0.021 |
otion | -0.021 |
ately | -0.020 |
wen | -0.020 |
used | -0.020 |
Token | see |
Token ID | 766 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
iqu | +0.055 |
ately | +0.054 |
otion | +0.054 |
wen | +0.053 |
erk | +0.053 |
Neg logit contributions | |
likes | -0.027 |
and | -0.027 |
They | -0.027 |
with | -0.025 |
nice | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
and | +0.005 |
likes | +0.005 |
They | +0.004 |
with | +0.004 |
nice | +0.003 |
Neg logit contributions | |
iqu | -0.018 |
ately | -0.018 |
otion | -0.018 |
wen | -0.018 |
used | -0.017 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
iqu | +0.020 |
ately | +0.020 |
otion | +0.020 |
wen | +0.019 |
erk | +0.019 |
Neg logit contributions | |
likes | -0.012 |
and | -0.012 |
They | -0.011 |
with | -0.011 |
nice | -0.010 |
Token | ich |
Token ID | 488 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
otion | +0.232 |
hesitation | +0.231 |
izz | +0.216 |
erk | +0.215 |
abella | +0.211 |
Neg logit contributions | |
and | -0.269 |
likes | -0.251 |
with | -0.244 |
| -0.230 |
They | -0.225 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
iqu | +0.114 |
wen | +0.112 |
ately | +0.111 |
otion | +0.111 |
used | +0.109 |
Neg logit contributions | |
and | -0.032 |
likes | -0.031 |
They | -0.029 |
with | -0.027 |
nice | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
likes | +0.016 |
games | +0.013 |
and | +0.013 |
fair | +0.012 |
nice | +0.012 |
Neg logit contributions | |
otion | -0.070 |
ately | -0.069 |
ow | -0.068 |
erk | -0.068 |
used | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
iqu | +0.014 |
otion | +0.014 |
ately | +0.014 |
wen | +0.014 |
erk | +0.014 |
Neg logit contributions | |
likes | -0.002 |
and | -0.001 |
They | -0.001 |
with | -0.001 |
liked | -0.001 |
Token | They |
Token ID | 2990 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
iqu | +0.042 |
wen | +0.041 |
otion | +0.041 |
ately | +0.041 |
used | +0.041 |
Neg logit contributions | |
likes | -0.013 |
and | -0.012 |
They | -0.011 |
with | -0.010 |
games | -0.009 |
Token | want |
Token ID | 765 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
likes | +0.019 |
and | +0.019 |
They | +0.019 |
with | +0.017 |
nice | +0.015 |
Neg logit contributions | |
iqu | -0.041 |
otion | -0.040 |
ately | -0.040 |
wen | -0.040 |
erk | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
likes | +0.007 |
They | +0.006 |
and | +0.006 |
with | +0.005 |
liked | +0.005 |
Neg logit contributions | |
iqu | -0.023 |
ately | -0.023 |
otion | -0.023 |
wen | -0.023 |
erk | -0.023 |
Token | see |
Token ID | 766 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
iqu | +0.061 |
ately | +0.060 |
otion | +0.060 |
wen | +0.059 |
erk | +0.058 |
Neg logit contributions | |
likes | -0.027 |
and | -0.027 |
They | -0.026 |
with | -0.024 |
nice | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
likes | +0.010 |
They | +0.009 |
and | +0.009 |
with | +0.008 |
liked | +0.008 |
Neg logit contributions | |
iqu | -0.025 |
ately | -0.024 |
otion | -0.024 |
wen | -0.024 |
erk | -0.024 |
Token | big |
Token ID | 1263 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
likes | +0.002 |
and | +0.002 |
They | +0.002 |
with | +0.002 |
liked | +0.002 |
Neg logit contributions | |
iqu | -0.005 |
ately | -0.005 |
otion | -0.005 |
wen | -0.005 |
erk | -0.005 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
They | +0.018 |
likes | +0.018 |
with | +0.016 |
and | +0.016 |
| +0.015 |
Neg logit contributions | |
otion | -0.032 |
ous | -0.032 |
iqu | -0.032 |
ately | -0.032 |
hesitation | -0.031 |
Token | ich |
Token ID | 488 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
hesitation | +0.230 |
otion | +0.227 |
izz | +0.216 |
erk | +0.213 |
abella | +0.209 |
Neg logit contributions | |
and | -0.262 |
likes | -0.246 |
with | -0.244 |
| -0.223 |
They | -0.222 |
Token | with |
Token ID | 351 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
iqu | +0.112 |
otion | +0.111 |
ately | +0.111 |
erk | +0.109 |
wen | +0.109 |
Neg logit contributions | |
likes | -0.025 |
They | -0.023 |
and | -0.023 |
with | -0.019 |
liked | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
likes | +0.003 |
They | +0.003 |
and | +0.003 |
with | +0.003 |
liked | +0.002 |
Neg logit contributions | |
iqu | -0.009 |
otion | -0.009 |
ately | -0.009 |
erk | -0.009 |
used | -0.009 |
Token | long |
Token ID | 890 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
likes | +0.029 |
and | +0.028 |
They | +0.027 |
with | +0.025 |
nice | +0.024 |
Neg logit contributions | |
iqu | -0.056 |
otion | -0.055 |
ately | -0.055 |
wen | -0.054 |
used | -0.054 |
Token | neck |
Token ID | 7393 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
likes | +0.025 |
They | +0.024 |
and | +0.024 |
with | +0.022 |
nice | +0.020 |
Neg logit contributions | |
iqu | -0.048 |
ately | -0.047 |
otion | -0.047 |
wen | -0.047 |
erk | -0.046 |
Token | be |
Token ID | 307 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
likes | +0.003 |
They | +0.003 |
and | +0.003 |
with | +0.002 |
liked | +0.002 |
Neg logit contributions | |
iqu | -0.007 |
otion | -0.007 |
ately | -0.007 |
erk | -0.007 |
wen | -0.007 |
Token | funny |
Token ID | 8258 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
iqu | +0.042 |
otion | +0.041 |
wen | +0.041 |
ately | +0.041 |
erk | +0.041 |
Neg logit contributions | |
likes | -0.013 |
They | -0.013 |
and | -0.012 |
with | -0.011 |
liked | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
likes | +0.024 |
They | +0.023 |
and | +0.016 |
| +0.015 |
liked | +0.015 |
Neg logit contributions | |
iqu | -0.098 |
ous | -0.098 |
ately | -0.098 |
erk | -0.097 |
otion | -0.097 |
Token | tease |
Token ID | 34691 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
iqu | +0.055 |
ately | +0.054 |
otion | +0.054 |
wen | +0.054 |
used | +0.053 |
Neg logit contributions | |
likes | -0.025 |
and | -0.025 |
They | -0.024 |
with | -0.022 |
liked | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
likes | +0.011 |
They | +0.011 |
and | +0.010 |
with | +0.009 |
liked | +0.009 |
Neg logit contributions | |
iqu | -0.022 |
ately | -0.022 |
otion | -0.021 |
wen | -0.021 |
used | -0.021 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
iqu | +0.008 |
ately | +0.007 |
otion | +0.007 |
wen | +0.007 |
erk | +0.007 |
Neg logit contributions | |
likes | -0.006 |
They | -0.006 |
and | -0.006 |
with | -0.005 |
liked | -0.005 |
Token | ich |
Token ID | 488 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
otion | +0.219 |
hesitation | +0.212 |
izz | +0.194 |
iqu | +0.193 |
erk | +0.192 |
Neg logit contributions | |
and | -0.282 |
likes | -0.266 |
with | -0.265 |
They | -0.251 |
| -0.249 |
Token | , |
Token ID | 11 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
iqu | +0.085 |
ately | +0.084 |
otion | +0.084 |
erk | +0.083 |
used | +0.083 |
Neg logit contributions | |
likes | -0.016 |
They | -0.014 |
and | -0.014 |
with | -0.011 |
liked | -0.009 |
Token | so |
Token ID | 523 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
likes | +0.000 |
They | +0.000 |
and | +0.000 |
with | +0.000 |
nice | +0.000 |
Neg logit contributions | |
iqu | -0.001 |
otion | -0.001 |
ately | -0.001 |
erk | -0.001 |
wen | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
iqu | +0.015 |
otion | +0.015 |
ately | +0.015 |
wen | +0.015 |
erk | +0.015 |
Neg logit contributions | |
and | -0.008 |
They | -0.008 |
likes | -0.008 |
with | -0.007 |
| -0.007 |
Token | prepared |
Token ID | 5597 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
iqu | +0.006 |
ately | +0.006 |
otion | +0.006 |
wen | +0.006 |
erk | +0.006 |
Neg logit contributions | |
likes | -0.003 |
They | -0.003 |
and | -0.003 |
with | -0.003 |
nice | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
izz | +0.016 |
abella | +0.015 |
ama | +0.014 |
ules | +0.014 |
ister | +0.014 |
Neg logit contributions | |
likes | -0.009 |
games | -0.008 |
toy | -0.008 |
shapes | -0.008 |
sounds | -0.008 |
Token | Can |
Token ID | 6090 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
likes | +0.029 |
and | +0.028 |
They | +0.028 |
with | +0.025 |
nice | +0.023 |
Neg logit contributions | |
iqu | -0.053 |
otion | -0.053 |
ately | -0.052 |
wen | -0.052 |
used | -0.051 |
Token | we |
Token ID | 356 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
iqu | +0.074 |
wen | +0.073 |
otion | +0.072 |
erk | +0.072 |
ately | +0.071 |
Neg logit contributions | |
and | -0.033 |
likes | -0.033 |
They | -0.033 |
with | -0.031 |
| -0.028 |
Token | ride |
Token ID | 6594 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
iqu | +0.048 |
otion | +0.048 |
wen | +0.047 |
ately | +0.047 |
erk | +0.045 |
Neg logit contributions | |
and | -0.021 |
They | -0.020 |
likes | -0.020 |
with | -0.019 |
| -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
iqu | +0.005 |
ately | +0.005 |
otion | +0.005 |
used | +0.005 |
erk | +0.005 |
Neg logit contributions | |
likes | -0.002 |
They | -0.001 |
and | -0.001 |
with | -0.001 |
liked | -0.001 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
iqu | +0.018 |
otion | +0.017 |
ately | +0.017 |
erk | +0.017 |
used | +0.017 |
Neg logit contributions | |
and | -0.024 |
likes | -0.024 |
They | -0.023 |
with | -0.023 |
nice | -0.022 |
Token | ich |
Token ID | 488 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
otion | +0.221 |
hesitation | +0.213 |
erk | +0.202 |
izz | +0.197 |
iqu | +0.196 |
Neg logit contributions | |
and | -0.271 |
likes | -0.256 |
with | -0.254 |
They | -0.240 |
| -0.238 |
Token | , |
Token ID | 11 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
iqu | +0.120 |
otion | +0.117 |
ately | +0.117 |
wen | +0.116 |
erk | +0.114 |
Neg logit contributions | |
and | -0.051 |
likes | -0.051 |
They | -0.049 |
with | -0.046 |
liked | -0.040 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
otion | +0.010 |
iqu | +0.010 |
ately | +0.010 |
ous | +0.009 |
erk | +0.009 |
Neg logit contributions | |
likes | -0.008 |
They | -0.008 |
and | -0.008 |
with | -0.007 |
liked | -0.007 |
Token | ?" |
Token ID | 1701 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
otion | +0.012 |
iqu | +0.012 |
ately | +0.011 |
erk | +0.011 |
ous | +0.011 |
Neg logit contributions | |
likes | -0.010 |
They | -0.010 |
and | -0.010 |
with | -0.009 |
grass | -0.009 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
otion | +0.024 |
ately | +0.024 |
hesitation | +0.024 |
used | +0.023 |
izz | +0.023 |
Neg logit contributions | |
likes | -0.016 |
and | -0.014 |
games | -0.013 |
They | -0.013 |
with | -0.013 |
Token | Before |
Token ID | 8421 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
wen | +0.027 |
ules | +0.026 |
erk | +0.026 |
antis | +0.026 |
ow | +0.026 |
Neg logit contributions | |
likes | -0.015 |
and | -0.014 |
They | -0.014 |
with | -0.012 |
green | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
iqu | +0.060 |
otion | +0.058 |
erk | +0.057 |
ately | +0.057 |
wen | +0.057 |
Neg logit contributions | |
and | -0.018 |
They | -0.018 |
with | -0.015 |
| -0.014 |
fun | -0.014 |
Token | race |
Token ID | 3234 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
iqu | +0.059 |
otion | +0.058 |
ately | +0.057 |
erk | +0.057 |
wen | +0.057 |
Neg logit contributions | |
and | -0.026 |
nice | -0.025 |
likes | -0.024 |
fun | -0.024 |
fair | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
iqu | +0.074 |
wen | +0.071 |
otion | +0.071 |
erk | +0.071 |
ately | +0.070 |
Neg logit contributions | |
and | -0.016 |
They | -0.015 |
likes | -0.014 |
with | -0.013 |
liked | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
iqu | +0.130 |
otion | +0.126 |
wen | +0.126 |
erk | +0.124 |
ately | +0.123 |
Neg logit contributions | |
and | -0.027 |
They | -0.026 |
with | -0.023 |
likes | -0.021 |
| -0.018 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
iqu | +0.070 |
otion | +0.069 |
ately | +0.068 |
wen | +0.067 |
erk | +0.067 |
Neg logit contributions | |
and | -0.041 |
likes | -0.039 |
They | -0.038 |
nice | -0.037 |
with | -0.036 |
Token | ich |
Token ID | 488 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
hesitation | +0.217 |
otion | +0.211 |
erk | +0.201 |
iqu | +0.195 |
izz | +0.188 |
Neg logit contributions | |
and | -0.276 |
likes | -0.267 |
with | -0.261 |
| -0.247 |
They | -0.244 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
iqu | +0.060 |
ately | +0.059 |
otion | +0.058 |
wen | +0.058 |
erk | +0.058 |
Neg logit contributions | |
likes | -0.028 |
They | -0.028 |
and | -0.027 |
with | -0.025 |
nice | -0.023 |
Token | embarrassed |
Token ID | 21100 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
likes | +0.003 |
They | +0.003 |
and | +0.003 |
with | +0.003 |
liked | +0.002 |
Neg logit contributions | |
iqu | -0.006 |
otion | -0.006 |
ately | -0.006 |
erk | -0.006 |
wen | -0.006 |
Token | because |
Token ID | 780 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
likes | +0.026 |
They | +0.023 |
and | +0.019 |
with | +0.018 |
liked | +0.018 |
Neg logit contributions | |
ately | -0.075 |
otion | -0.075 |
iqu | -0.074 |
ous | -0.074 |
erk | -0.073 |
Token | he |
Token ID | 339 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
iqu | +0.097 |
unct | +0.091 |
arse | +0.091 |
ately | +0.090 |
istent | +0.089 |
Neg logit contributions | |
and | -0.029 |
with | -0.026 |
They | -0.021 |
| -0.019 |
big | -0.019 |
Token | if |
Token ID | 611 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
iqu | +0.107 |
wen | +0.106 |
ately | +0.103 |
otion | +0.102 |
unct | +0.102 |
Neg logit contributions | |
and | -0.052 |
likes | -0.046 |
They | -0.046 |
with | -0.045 |
| -0.039 |
Token | he |
Token ID | 339 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
iqu | +0.100 |
otion | +0.098 |
erk | +0.097 |
wen | +0.097 |
izz | +0.096 |
Neg logit contributions | |
and | -0.035 |
with | -0.033 |
They | -0.032 |
likes | -0.031 |
nice | -0.028 |
Token | could |
Token ID | 714 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
iqu | +0.055 |
otion | +0.054 |
wen | +0.053 |
ately | +0.053 |
used | +0.052 |
Neg logit contributions | |
likes | -0.029 |
and | -0.028 |
They | -0.026 |
with | -0.025 |
liked | -0.024 |
Token | borrow |
Token ID | 8804 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
iqu | +0.110 |
ately | +0.107 |
otion | +0.107 |
wen | +0.106 |
antis | +0.104 |
Neg logit contributions | |
and | -0.051 |
with | -0.045 |
likes | -0.045 |
They | -0.044 |
| -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
iqu | +0.002 |
ately | +0.002 |
otion | +0.002 |
ow | +0.002 |
used | +0.002 |
Neg logit contributions | |
likes | -0.001 |
They | -0.001 |
and | -0.001 |
liked | -0.001 |
with | -0.001 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
iqu | +0.004 |
ately | +0.004 |
otion | +0.004 |
wen | +0.004 |
erk | +0.004 |
Neg logit contributions | |
and | -0.004 |
likes | -0.004 |
They | -0.004 |
with | -0.004 |
nice | -0.004 |
Token | ich |
Token ID | 488 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
hesitation | +0.236 |
otion | +0.223 |
erk | +0.203 |
unct | +0.200 |
izz | +0.197 |
Neg logit contributions | |
and | -0.251 |
with | -0.238 |
likes | -0.236 |
| -0.216 |
They | -0.208 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
iqu | +0.136 |
otion | +0.134 |
ately | +0.133 |
wen | +0.133 |
used | +0.131 |
Neg logit contributions | |
and | -0.024 |
likes | -0.023 |
They | -0.021 |
with | -0.019 |
nice | -0.013 |
Token | |
Token ID | 220 |
Feature activation | -7.65e-04 |
Pos logit contributions | |
likes | +0.002 |
and | +0.001 |
nice | +0.001 |
games | +0.001 |
fun | +0.001 |
Neg logit contributions | |
used | -0.005 |
ous | -0.005 |
ately | -0.005 |
ow | -0.004 |
iqu | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
iqu | +0.000 |
ately | +0.000 |
otion | +0.000 |
wen | +0.000 |
erk | +0.000 |
Neg logit contributions | |
likes | -0.000 |
and | -0.000 |
They | -0.000 |
with | -0.000 |
liked | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
wen | +0.005 |
ately | +0.005 |
iqu | +0.005 |
otion | +0.005 |
erk | +0.004 |
Neg logit contributions | |
likes | -0.001 |
They | -0.001 |
and | -0.001 |
with | -0.000 |
games | -0.000 |
Token | I |
Token ID | 314 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
iqu | +0.032 |
wen | +0.031 |
otion | +0.031 |
erk | +0.031 |
ules | +0.031 |
Neg logit contributions | |
and | -0.015 |
likes | -0.014 |
They | -0.013 |
with | -0.013 |
nice | -0.011 |
Token | want |
Token ID | 765 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
likes | +0.010 |
and | +0.010 |
They | +0.010 |
with | +0.009 |
liked | +0.009 |
Neg logit contributions | |
iqu | -0.016 |
otion | -0.016 |
ately | -0.016 |
ous | -0.016 |
wen | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
and | +0.007 |
likes | +0.007 |
They | +0.006 |
with | +0.006 |
nice | +0.005 |
Neg logit contributions | |
iqu | -0.031 |
otion | -0.030 |
ately | -0.030 |
wen | -0.030 |
erk | -0.030 |
Token | ride |
Token ID | 6594 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
iqu | +0.053 |
otion | +0.052 |
ately | +0.051 |
wen | +0.050 |
erk | +0.050 |
Neg logit contributions | |
and | -0.023 |
likes | -0.022 |
They | -0.021 |
with | -0.021 |
| -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
likes | +0.004 |
They | +0.004 |
and | +0.004 |
with | +0.003 |
liked | +0.003 |
Neg logit contributions | |
iqu | -0.012 |
ately | -0.012 |
otion | -0.011 |
used | -0.011 |
wen | -0.011 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
iqu | +0.013 |
otion | +0.012 |
ately | +0.012 |
erk | +0.012 |
wen | +0.012 |
Neg logit contributions | |
likes | -0.018 |
and | -0.018 |
They | -0.017 |
with | -0.017 |
nice | -0.016 |
Token | ich |
Token ID | 488 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
otion | +0.219 |
hesitation | +0.215 |
erk | +0.200 |
iqu | +0.198 |
izz | +0.195 |
Neg logit contributions | |
and | -0.272 |
with | -0.253 |
likes | -0.252 |
| -0.242 |
They | -0.239 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
iqu | +0.084 |
ately | +0.084 |
otion | +0.083 |
wen | +0.082 |
erk | +0.082 |
Neg logit contributions | |
likes | -0.024 |
They | -0.023 |
and | -0.022 |
with | -0.019 |
nice | -0.017 |
Token | Ben |
Token ID | 3932 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
likes | +0.006 |
and | +0.005 |
than | +0.005 |
games | +0.005 |
shapes | +0.005 |
Neg logit contributions | |
ately | -0.007 |
otion | -0.007 |
hesitation | -0.007 |
izz | -0.007 |
iqu | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
likes | +0.017 |
They | +0.016 |
and | +0.014 |
fun | +0.014 |
games | +0.013 |
Neg logit contributions | |
ately | -0.030 |
ow | -0.030 |
erk | -0.029 |
iqu | -0.029 |
wen | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
iqu | +0.019 |
ately | +0.019 |
otion | +0.019 |
wen | +0.019 |
erk | +0.019 |
Neg logit contributions | |
likes | -0.003 |
and | -0.003 |
They | -0.003 |
with | -0.002 |
liked | -0.002 |
Token | ," |
Token ID | 553 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
iqu | +0.009 |
otion | +0.009 |
ately | +0.009 |
used | +0.009 |
erk | +0.009 |
Neg logit contributions | |
likes | -0.003 |
They | -0.003 |
and | -0.003 |
with | -0.003 |
liked | -0.003 |
Token | Doug |
Token ID | 15115 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
iqu | +0.015 |
otion | +0.014 |
ately | +0.014 |
wen | +0.014 |
erk | +0.014 |
Neg logit contributions | |
likes | -0.009 |
and | -0.009 |
They | -0.009 |
with | -0.008 |
liked | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
iqu | +0.035 |
otion | +0.034 |
ately | +0.034 |
wen | +0.033 |
ous | +0.033 |
Neg logit contributions | |
and | -0.017 |
likes | -0.017 |
They | -0.016 |
with | -0.015 |
liked | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
iqu | +0.064 |
wen | +0.063 |
otion | +0.063 |
ately | +0.063 |
erk | +0.062 |
Neg logit contributions | |
and | -0.012 |
They | -0.010 |
likes | -0.010 |
with | -0.010 |
nice | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
iqu | +0.131 |
ately | +0.124 |
wen | +0.124 |
otion | +0.123 |
erk | +0.122 |
Neg logit contributions | |
and | -0.044 |
They | -0.041 |
likes | -0.040 |
with | -0.039 |
| -0.035 |
Token | ostr |
Token ID | 42387 |
Feature activation | -9.94e+00 |
Pos logit contributions | |
iqu | +0.067 |
otion | +0.066 |
ately | +0.065 |
wen | +0.064 |
erk | +0.063 |
Neg logit contributions | |
and | -0.059 |
likes | -0.058 |
They | -0.056 |
with | -0.054 |
nice | -0.053 |
Token | ich |
Token ID | 488 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
otion | +0.225 |
hesitation | +0.221 |
izz | +0.200 |
erk | +0.193 |
ancer | +0.192 |
Neg logit contributions | |
and | -0.263 |
with | -0.246 |
likes | -0.245 |
| -0.234 |
They | -0.225 |
Token | . |
Token ID | 13 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
iqu | +0.147 |
wen | +0.147 |
otion | +0.146 |
ately | +0.145 |
izz | +0.142 |
Neg logit contributions | |
and | -0.021 |
with | -0.016 |
likes | -0.015 |
They | -0.015 |
| -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
iqu | +0.027 |
ately | +0.027 |
used | +0.027 |
otion | +0.027 |
erk | +0.027 |
Neg logit contributions | |
likes | -0.008 |
and | -0.007 |
They | -0.007 |
with | -0.006 |
games | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
wen | +0.056 |
iqu | +0.056 |
ately | +0.056 |
used | +0.056 |
otion | +0.056 |
Neg logit contributions | |
likes | -0.010 |
and | -0.007 |
They | -0.007 |
games | -0.006 |
with | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
used | +0.064 |
wen | +0.061 |
ately | +0.061 |
iqu | +0.061 |
antis | +0.060 |
Neg logit contributions | |
likes | -0.026 |
They | -0.023 |
and | -0.023 |
fun | -0.021 |
games | -0.021 |
Token | his |
Token ID | 465 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
iqu | +0.093 |
wen | +0.090 |
ous | +0.088 |
ately | +0.088 |
erk | +0.086 |
Neg logit contributions | |
and | -0.030 |
likes | -0.028 |
They | -0.028 |
with | -0.026 |
liked | -0.022 |
Token | favorite |
Token ID | 4004 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
iqu | +0.065 |
otion | +0.065 |
ately | +0.064 |
wen | +0.063 |
used | +0.063 |
Neg logit contributions | |
likes | -0.037 |
and | -0.036 |
They | -0.035 |
with | -0.033 |
liked | -0.030 |
Token | animal |
Token ID | 5044 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
likes | +0.002 |
They | +0.002 |
and | +0.002 |
with | +0.002 |
fun | +0.001 |
Neg logit contributions | |
otion | -0.004 |
ately | -0.004 |
iqu | -0.004 |
erk | -0.004 |
wen | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
iqu | +0.112 |
otion | +0.111 |
ately | +0.111 |
erk | +0.110 |
wen | +0.109 |
Neg logit contributions | |
likes | -0.033 |
They | -0.032 |
and | -0.031 |
with | -0.026 |
fun | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ately | +0.103 |
iqu | +0.103 |
otion | +0.101 |
used | +0.101 |
wen | +0.100 |
Neg logit contributions | |
and | -0.032 |
likes | -0.031 |
They | -0.030 |
with | -0.028 |
nice | -0.024 |
Token | ostr |
Token ID | 42387 |
Feature activation | -9.93e+00 |
Pos logit contributions | |
likes | +0.020 |
and | +0.020 |
They | +0.019 |
with | +0.018 |
nice | +0.017 |
Neg logit contributions | |
ately | -0.038 |
otion | -0.038 |
iqu | -0.038 |
used | -0.037 |
wen | -0.036 |
Token | ich |
Token ID | 488 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
hesitation | +0.232 |
otion | +0.223 |
erk | +0.208 |
abella | +0.206 |
izz | +0.204 |
Neg logit contributions | |
and | -0.254 |
with | -0.244 |
likes | -0.244 |
| -0.219 |
They | -0.216 |
Token | . |
Token ID | 13 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
iqu | +0.106 |
ately | +0.105 |
otion | +0.105 |
wen | +0.104 |
used | +0.103 |
Neg logit contributions | |
likes | -0.017 |
and | -0.017 |
They | -0.016 |
with | -0.013 |
nice | -0.009 |
Token | The |
Token ID | 383 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
likes | +0.005 |
and | +0.004 |
games | +0.004 |
fun | +0.004 |
with | +0.004 |
Neg logit contributions | |
otion | -0.013 |
iqu | -0.013 |
antis | -0.013 |
ately | -0.013 |
erk | -0.013 |
Token | ostr |
Token ID | 42387 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
iqu | +0.004 |
ately | +0.004 |
otion | +0.004 |
wen | +0.004 |
used | +0.004 |
Neg logit contributions | |
likes | -0.005 |
and | -0.005 |
They | -0.005 |
with | -0.005 |
nice | -0.005 |
Token | ich |
Token ID | 488 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
hesitation | +0.219 |
otion | +0.207 |
erk | +0.195 |
iqu | +0.193 |
izz | +0.189 |
Neg logit contributions | |
and | -0.271 |
likes | -0.268 |
with | -0.256 |
They | -0.239 |
| -0.239 |
Token | ily |
Token ID | 813 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
iqu | +0.050 |
used | +0.047 |
ous | +0.046 |
ately | +0.046 |
wen | +0.046 |
Neg logit contributions | |
and | -0.034 |
likes | -0.033 |
They | -0.032 |
with | -0.030 |
liked | -0.028 |
Token | wanted |
Token ID | 2227 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
They | +0.046 |
likes | +0.042 |
games | +0.041 |
nice | +0.041 |
fun | +0.040 |
Neg logit contributions | |
ow | -0.060 |
iqu | -0.059 |
ately | -0.059 |
erk | -0.059 |
wen | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
and | +0.006 |
likes | +0.006 |
They | +0.006 |
with | +0.005 |
fun | +0.004 |
Neg logit contributions | |
iqu | -0.029 |
otion | -0.029 |
ately | -0.029 |
wen | -0.029 |
used | -0.028 |
Token | feed |
Token ID | 3745 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
iqu | +0.085 |
otion | +0.083 |
ately | +0.083 |
wen | +0.082 |
erk | +0.081 |
Neg logit contributions | |
and | -0.037 |
likes | -0.037 |
They | -0.036 |
with | -0.033 |
nice | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
iqu | +0.074 |
wen | +0.071 |
ous | +0.071 |
ately | +0.071 |
otion | +0.071 |
Neg logit contributions | |
and | -0.012 |
with | -0.009 |
They | -0.008 |
likes | -0.007 |
| -0.006 |
Token | ostr |
Token ID | 42387 |
Feature activation | -9.93e+00 |
Pos logit contributions | |
iqu | +0.041 |
otion | +0.040 |
ately | +0.040 |
used | +0.039 |
erk | +0.039 |
Neg logit contributions | |
and | -0.055 |
likes | -0.054 |
They | -0.053 |
with | -0.051 |
nice | -0.049 |
Token | ich |
Token ID | 488 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
otion | +0.231 |
hesitation | +0.224 |
izz | +0.210 |
erk | +0.206 |
iqu | +0.203 |
Neg logit contributions | |
and | -0.262 |
with | -0.241 |
likes | -0.240 |
| -0.231 |
They | -0.225 |
Token | too |
Token ID | 1165 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
iqu | +0.108 |
otion | +0.108 |
ately | +0.108 |
erk | +0.107 |
ow | +0.106 |
Neg logit contributions | |
likes | -0.024 |
They | -0.022 |
and | -0.020 |
with | -0.016 |
liked | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
and | +0.007 |
likes | +0.007 |
They | +0.007 |
with | +0.005 |
nice | +0.004 |
Neg logit contributions | |
iqu | -0.044 |
otion | -0.044 |
ately | -0.044 |
wen | -0.043 |
erk | -0.043 |
Token | She |
Token ID | 1375 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
likes | +0.020 |
games | +0.019 |
and | +0.018 |
nice | +0.018 |
fun | +0.018 |
Neg logit contributions | |
ately | -0.043 |
ow | -0.042 |
iqu | -0.042 |
otion | -0.042 |
used | -0.042 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
likes | +0.042 |
They | +0.042 |
and | +0.041 |
with | +0.039 |
nice | +0.036 |
Neg logit contributions | |
iqu | -0.077 |
ately | -0.076 |
wen | -0.075 |
erk | -0.075 |
otion | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
iqu | +0.039 |
otion | +0.038 |
ately | +0.038 |
wen | +0.038 |
erk | +0.037 |
Neg logit contributions | |
and | -0.013 |
They | -0.013 |
likes | -0.012 |
with | -0.011 |
| -0.010 |
Token | race |
Token ID | 3234 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
iqu | +0.062 |
otion | +0.060 |
ately | +0.060 |
wen | +0.059 |
erk | +0.059 |
Neg logit contributions | |
and | -0.032 |
likes | -0.031 |
nice | -0.030 |
green | -0.029 |
fun | -0.029 |
Token | started |
Token ID | 2067 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
iqu | +0.062 |
ately | +0.061 |
otion | +0.061 |
wen | +0.060 |
erk | +0.060 |
Neg logit contributions | |
likes | -0.020 |
and | -0.019 |
They | -0.019 |
with | -0.017 |
liked | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
iqu | +0.028 |
otion | +0.027 |
ately | +0.027 |
wen | +0.027 |
erk | +0.027 |
Neg logit contributions | |
and | -0.008 |
They | -0.007 |
likes | -0.007 |
with | -0.006 |
| -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
iqu | +0.101 |
wen | +0.098 |
otion | +0.097 |
ately | +0.097 |
erk | +0.097 |
Neg logit contributions | |
and | -0.022 |
They | -0.021 |
likes | -0.019 |
with | -0.019 |
| -0.014 |
Token | ostr |
Token ID | 42387 |
Feature activation | -9.91e+00 |
Pos logit contributions | |
iqu | +0.057 |
otion | +0.056 |
ately | +0.055 |
wen | +0.055 |
erk | +0.054 |
Neg logit contributions | |
and | -0.046 |
likes | -0.044 |
nice | -0.042 |
They | -0.042 |
green | -0.041 |
Token | ich |
Token ID | 488 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
hesitation | +0.217 |
otion | +0.214 |
erk | +0.203 |
iqu | +0.196 |
izz | +0.191 |
Neg logit contributions | |
and | -0.267 |
likes | -0.256 |
with | -0.251 |
| -0.235 |
They | -0.231 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ately | +0.035 |
iqu | +0.035 |
erk | +0.034 |
wen | +0.034 |
ow | +0.034 |
Neg logit contributions | |
They | -0.019 |
likes | -0.018 |
and | -0.016 |
nice | -0.015 |
with | -0.015 |
Token | faster |
Token ID | 5443 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
likes | +0.025 |
They | +0.020 |
shapes | +0.019 |
liked | +0.019 |
draws | +0.018 |
Neg logit contributions | |
ow | -0.034 |
used | -0.033 |
ous | -0.032 |
ately | -0.032 |
hesitation | -0.032 |
Token | than |
Token ID | 621 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
likes | +0.015 |
They | +0.014 |
pretty | +0.010 |
nice | +0.009 |
This | +0.009 |
Neg logit contributions | |
ately | -0.050 |
ge | -0.046 |
ow | -0.046 |
iously | -0.046 |
hesitation | -0.046 |
Token | he |
Token ID | 339 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
iqu | +0.063 |
wen | +0.058 |
otion | +0.058 |
used | +0.057 |
ama | +0.057 |
Neg logit contributions | |
and | -0.050 |
with | -0.045 |
They | -0.043 |
likes | -0.042 |
fun | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
likes | +0.009 |
They | +0.009 |
and | +0.009 |
with | +0.008 |
nice | +0.007 |
Neg logit contributions | |
iqu | -0.026 |
ately | -0.025 |
otion | -0.025 |
wen | -0.025 |
erk | -0.025 |
Token | scared |
Token ID | 12008 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
iqu | +0.052 |
ately | +0.052 |
otion | +0.051 |
wen | +0.050 |
used | +0.050 |
Neg logit contributions | |
likes | -0.025 |
and | -0.025 |
They | -0.024 |
with | -0.022 |
nice | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
likes | +0.026 |
They | +0.022 |
liked | +0.018 |
games | +0.018 |
grass | +0.017 |
Neg logit contributions | |
otion | -0.076 |
ately | -0.076 |
iqu | -0.075 |
ous | -0.074 |
ow | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
likes | +0.018 |
and | +0.015 |
games | +0.013 |
with | +0.012 |
shapes | +0.011 |
Neg logit contributions | |
iqu | -0.075 |
otion | -0.075 |
ately | -0.074 |
erk | -0.074 |
antis | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
likes | +0.001 |
and | +0.001 |
They | +0.001 |
with | +0.001 |
games | +0.001 |
Neg logit contributions | |
iqu | -0.008 |
otion | -0.008 |
wen | -0.008 |
ately | -0.008 |
erk | -0.008 |
Token | They |
Token ID | 2990 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
wen | +0.031 |
izz | +0.030 |
iqu | +0.030 |
erk | +0.030 |
ama | +0.030 |
Neg logit contributions | |
likes | -0.015 |
and | -0.013 |
They | -0.012 |
shapes | -0.012 |
games | -0.012 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
and | +0.051 |
They | +0.047 |
likes | +0.047 |
with | +0.044 |
liked | +0.043 |
Neg logit contributions | |
iqu | -0.110 |
otion | -0.109 |
ous | -0.107 |
used | -0.107 |
wen | -0.106 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
iqu | +0.046 |
wen | +0.045 |
otion | +0.044 |
ately | +0.044 |
used | +0.044 |
Neg logit contributions | |
and | -0.020 |
They | -0.019 |
likes | -0.019 |
with | -0.017 |
nice | -0.015 |
Token | why |
Token ID | 1521 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
iqu | +0.016 |
otion | +0.016 |
ately | +0.016 |
erk | +0.015 |
wen | +0.015 |
Neg logit contributions | |
likes | -0.006 |
They | -0.006 |
and | -0.006 |
with | -0.005 |
fun | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
used | +0.066 |
iqu | +0.065 |
unct | +0.064 |
ately | +0.063 |
wen | +0.062 |
Neg logit contributions | |
and | -0.028 |
They | -0.025 |
with | -0.024 |
likes | -0.023 |
liked | -0.021 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
iqu | +0.086 |
otion | +0.085 |
ately | +0.085 |
wen | +0.084 |
used | +0.084 |
Neg logit contributions | |
likes | -0.018 |
and | -0.018 |
They | -0.015 |
with | -0.013 |
liked | -0.013 |
Token | are |
Token ID | 389 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
They | +0.047 |
and | +0.044 |
with | +0.043 |
likes | +0.042 |
| +0.040 |
Neg logit contributions | |
iqu | -0.073 |
erk | -0.073 |
otion | -0.072 |
ow | -0.072 |
illa | -0.070 |
Token | the |
Token ID | 262 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
likes | +0.006 |
They | +0.006 |
and | +0.005 |
with | +0.005 |
| +0.004 |
Neg logit contributions | |
iqu | -0.014 |
otion | -0.014 |
erk | -0.014 |
hesitation | -0.014 |
wen | -0.014 |
Token | best |
Token ID | 1266 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
They | +0.058 |
likes | +0.058 |
and | +0.056 |
with | +0.052 |
liked | +0.048 |
Neg logit contributions | |
iqu | -0.099 |
otion | -0.095 |
ately | -0.095 |
wen | -0.095 |
erk | -0.094 |
Token | costumes |
Token ID | 24138 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
likes | +0.017 |
They | +0.015 |
and | +0.014 |
liked | +0.012 |
with | +0.012 |
Neg logit contributions | |
otion | -0.045 |
iqu | -0.045 |
ous | -0.045 |
ately | -0.045 |
erk | -0.044 |
Token | ever |
Token ID | 1683 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
likes | +0.032 |
They | +0.032 |
grass | +0.028 |
green | +0.027 |
and | +0.027 |
Neg logit contributions | |
ous | -0.048 |
otion | -0.047 |
ately | -0.047 |
ow | -0.046 |
erk | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
They | +0.003 |
likes | +0.003 |
and | +0.003 |
with | +0.002 |
nice | +0.002 |
Neg logit contributions | |
ately | -0.014 |
iqu | -0.014 |
otion | -0.014 |
ous | -0.014 |
erk | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
likes | +0.019 |
and | +0.016 |
with | +0.013 |
games | +0.013 |
nice | +0.012 |
Neg logit contributions | |
otion | -0.115 |
ately | -0.113 |
iqu | -0.113 |
antis | -0.112 |
erk | -0.112 |
Token | thank |
Token ID | 5875 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
They | +0.063 |
and | +0.059 |
with | +0.059 |
likes | +0.058 |
| +0.054 |
Neg logit contributions | |
erk | -0.100 |
iqu | -0.100 |
ow | -0.099 |
otion | -0.099 |
hesitation | -0.097 |
Token | their |
Token ID | 511 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
iqu | +0.118 |
wen | +0.115 |
otion | +0.114 |
erk | +0.114 |
ately | +0.113 |
Neg logit contributions | |
and | -0.034 |
They | -0.034 |
with | -0.032 |
likes | -0.030 |
| -0.027 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
iqu | +0.016 |
ately | +0.016 |
otion | +0.016 |
wen | +0.016 |
erk | +0.016 |
Neg logit contributions | |
likes | -0.014 |
and | -0.014 |
They | -0.013 |
with | -0.013 |
liked | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
likes | +0.003 |
They | +0.002 |
and | +0.000 |
with | -0.000 |
fun | -0.001 |
Neg logit contributions | |
ately | -0.046 |
iqu | -0.046 |
erk | -0.045 |
otion | -0.045 |
wen | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
iqu | +0.064 |
otion | +0.063 |
ately | +0.063 |
wen | +0.062 |
erk | +0.062 |
Neg logit contributions | |
likes | -0.025 |
and | -0.023 |
They | -0.023 |
with | -0.019 |
liked | -0.019 |
Token | tower |
Token ID | 10580 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
otion | +0.014 |
iqu | +0.014 |
antis | +0.014 |
ous | +0.014 |
used | +0.014 |
Neg logit contributions | |
They | -0.010 |
likes | -0.009 |
and | -0.009 |
with | -0.008 |
liked | -0.008 |
Token | like |
Token ID | 588 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ately | +0.059 |
ous | +0.058 |
otion | +0.058 |
ow | +0.058 |
erk | +0.057 |
Neg logit contributions | |
likes | -0.023 |
They | -0.023 |
and | -0.020 |
nice | -0.019 |
grass | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
likes | +0.016 |
They | +0.015 |
and | +0.014 |
liked | +0.013 |
with | +0.012 |
Neg logit contributions | |
aro | -0.032 |
ous | -0.032 |
otion | -0.032 |
ately | -0.031 |
ow | -0.031 |
Token | 's |
Token ID | 338 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
They | +0.006 |
likes | +0.006 |
and | +0.005 |
grass | +0.005 |
with | +0.005 |
Neg logit contributions | |
ous | -0.012 |
ow | -0.012 |
otion | -0.012 |
used | -0.011 |
iqu | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
iqu | +0.026 |
ous | +0.026 |
otion | +0.026 |
ow | +0.026 |
ately | +0.025 |
Neg logit contributions | |
likes | -0.013 |
They | -0.012 |
and | -0.011 |
liked | -0.010 |
with | -0.010 |
Token | king |
Token ID | 5822 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
They | +0.050 |
likes | +0.049 |
and | +0.047 |
with | +0.042 |
liked | +0.038 |
Neg logit contributions | |
iqu | -0.115 |
ous | -0.112 |
otion | -0.111 |
erk | -0.111 |
antis | -0.110 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
ow | +0.015 |
ous | +0.015 |
otion | +0.015 |
ately | +0.014 |
erk | +0.014 |
Neg logit contributions | |
They | -0.006 |
likes | -0.006 |
and | -0.005 |
grass | -0.005 |
with | -0.005 |
Token | he |
Token ID | 339 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
likes | +0.001 |
nice | +0.000 |
and | +0.000 |
fair | +0.000 |
pretty | +0.000 |
Neg logit contributions | |
ow | -0.001 |
ately | -0.001 |
iqu | -0.001 |
aro | -0.001 |
otion | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
likes | +0.017 |
They | +0.017 |
and | +0.016 |
with | +0.015 |
nice | +0.014 |
Neg logit contributions | |
ately | -0.026 |
iqu | -0.026 |
ow | -0.026 |
erk | -0.025 |
wen | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
iqu | +0.003 |
ately | +0.003 |
otion | +0.003 |
wen | +0.003 |
erk | +0.003 |
Neg logit contributions | |
likes | -0.001 |
and | -0.001 |
They | -0.001 |
with | -0.000 |
liked | -0.000 |
Token | all |
Token ID | 477 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
likes | +0.010 |
They | +0.009 |
and | +0.007 |
shapes | +0.007 |
green | +0.007 |
Neg logit contributions | |
ately | -0.024 |
otion | -0.023 |
ous | -0.023 |
erk | -0.023 |
wen | -0.023 |
Token | day |
Token ID | 1110 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
likes | +0.027 |
They | +0.027 |
and | +0.026 |
piles | +0.023 |
with | +0.022 |
Neg logit contributions | |
ow | -0.043 |
erk | -0.042 |
otion | -0.042 |
ous | -0.041 |
aro | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
likes | +0.001 |
They | +0.001 |
and | +0.001 |
with | +0.001 |
liked | +0.001 |
Neg logit contributions | |
ately | -0.002 |
iqu | -0.002 |
otion | -0.002 |
ous | -0.002 |
wen | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
likes | +0.010 |
and | +0.009 |
with | +0.009 |
games | +0.008 |
nice | +0.008 |
Neg logit contributions | |
otion | -0.037 |
ow | -0.037 |
wen | -0.036 |
erk | -0.036 |
ous | -0.036 |
Token | had |
Token ID | 550 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
likes | +0.035 |
They | +0.035 |
and | +0.034 |
with | +0.031 |
nice | +0.029 |
Neg logit contributions | |
iqu | -0.065 |
ately | -0.064 |
otion | -0.064 |
wen | -0.064 |
erk | -0.064 |
Token | a |
Token ID | 257 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
likes | +0.025 |
They | +0.024 |
and | +0.021 |
with | +0.019 |
girl | +0.019 |
Neg logit contributions | |
ow | -0.039 |
erk | -0.039 |
hesitation | -0.038 |
wen | -0.038 |
iqu | -0.037 |
Token | lot |
Token ID | 1256 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
They | +0.054 |
likes | +0.050 |
and | +0.047 |
with | +0.045 |
shapes | +0.038 |
Neg logit contributions | |
iqu | -0.153 |
erk | -0.146 |
hesitation | -0.145 |
ama | -0.144 |
antis | -0.143 |
Token | of |
Token ID | 286 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
iqu | +0.024 |
ately | +0.024 |
otion | +0.024 |
ow | +0.024 |
erk | +0.023 |
Neg logit contributions | |
likes | -0.017 |
They | -0.017 |
and | -0.015 |
with | -0.014 |
liked | -0.014 |
Token | toys |
Token ID | 14958 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
likes | +0.023 |
They | +0.022 |
and | +0.020 |
with | +0.018 |
liked | +0.014 |
Neg logit contributions | |
iqu | -0.102 |
otion | -0.101 |
erk | -0.101 |
hesitation | -0.100 |
ow | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | +2.20e-03 |
Pos logit contributions | |
They | +0.010 |
likes | +0.010 |
and | +0.007 |
shapes | +0.007 |
sounds | +0.007 |
Neg logit contributions | |
ately | -0.031 |
ow | -0.031 |
otion | -0.031 |
erk | -0.031 |
iqu | -0.030 |
Token | treats |
Token ID | 18432 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
likes | +0.000 |
They | +0.000 |
and | +0.000 |
with | +0.000 |
nice | +0.000 |
Neg logit contributions | |
iqu | -0.000 |
ately | -0.000 |
otion | -0.000 |
wen | -0.000 |
erk | -0.000 |
Token | himself |
Token ID | 2241 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
likes | +0.011 |
They | +0.009 |
liked | +0.008 |
games | +0.008 |
and | +0.008 |
Neg logit contributions | |
ately | -0.017 |
aro | -0.017 |
izz | -0.017 |
iqu | -0.017 |
otion | -0.017 |
Token | clean |
Token ID | 3424 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
iqu | +0.032 |
icking | +0.031 |
erk | +0.031 |
otion | +0.031 |
ow | +0.031 |
Neg logit contributions | |
They | -0.015 |
likes | -0.015 |
| -0.012 |
and | -0.011 |
liked | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
likes | +0.011 |
They | +0.009 |
liked | +0.008 |
| +0.008 |
fun | +0.007 |
Neg logit contributions | |
ately | -0.026 |
otion | -0.025 |
icking | -0.025 |
erk | -0.025 |
iqu | -0.025 |
Token | He |
Token ID | 679 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
likes | +0.011 |
and | +0.010 |
games | +0.009 |
with | +0.009 |
nice | +0.009 |
Neg logit contributions | |
iqu | -0.024 |
ately | -0.023 |
otion | -0.023 |
erk | -0.023 |
wen | -0.023 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
They | +0.033 |
likes | +0.032 |
with | +0.028 |
and | +0.028 |
nice | +0.027 |
Neg logit contributions | |
iqu | -0.046 |
ately | -0.046 |
erk | -0.046 |
wen | -0.045 |
izz | -0.044 |
Token | much |
Token ID | 881 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
likes | +0.033 |
They | +0.030 |
and | +0.026 |
games | +0.026 |
shapes | +0.025 |
Neg logit contributions | |
otion | -0.059 |
iqu | -0.058 |
hesitation | -0.058 |
izz | -0.057 |
erk | -0.056 |
Token | better |
Token ID | 1365 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
likes | +0.063 |
They | +0.062 |
games | +0.055 |
liked | +0.053 |
and | +0.051 |
Neg logit contributions | |
iqu | -0.067 |
hesitation | -0.067 |
otion | -0.063 |
izz | -0.062 |
icking | -0.061 |
Token | ! |
Token ID | 0 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
likes | +0.010 |
They | +0.010 |
and | +0.008 |
with | +0.007 |
nice | +0.007 |
Neg logit contributions | |
ately | -0.039 |
iqu | -0.039 |
otion | -0.038 |
erk | -0.038 |
used | -0.038 |
Token | |
Token ID | 220 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
likes | +0.025 |
and | +0.024 |
games | +0.022 |
with | +0.021 |
nice | +0.021 |
Neg logit contributions | |
iqu | -0.047 |
ately | -0.046 |
erk | -0.046 |
wen | -0.046 |
otion | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
likes | +0.001 |
and | +0.001 |
They | +0.000 |
games | +0.000 |
with | +0.000 |
Neg logit contributions | |
iqu | -0.004 |
otion | -0.004 |
wen | -0.004 |
erk | -0.004 |
ately | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
likes | +0.008 |
They | +0.006 |
and | +0.006 |
games | +0.005 |
shapes | +0.005 |
Neg logit contributions | |
wen | -0.036 |
erk | -0.036 |
ately | -0.036 |
otion | -0.035 |
izz | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
likes | +0.006 |
They | +0.005 |
and | +0.005 |
with | +0.004 |
fun | +0.004 |
Neg logit contributions | |
iqu | -0.026 |
otion | -0.026 |
ately | -0.025 |
erk | -0.025 |
ous | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
likes | +0.009 |
and | +0.007 |
games | +0.007 |
fun | +0.006 |
They | +0.006 |
Neg logit contributions | |
otion | -0.029 |
iqu | -0.029 |
ately | -0.029 |
ous | -0.029 |
erk | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
izz | +0.003 |
wen | +0.003 |
otion | +0.003 |
iqu | +0.003 |
erk | +0.003 |
Neg logit contributions | |
likes | -0.001 |
games | -0.001 |
and | -0.001 |
shapes | -0.001 |
They | -0.001 |
Token | L |
Token ID | 43 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
izz | +0.022 |
wen | +0.021 |
iqu | +0.021 |
otion | +0.020 |
ately | +0.020 |
Neg logit contributions | |
likes | -0.013 |
and | -0.012 |
They | -0.011 |
green | -0.011 |
shapes | -0.011 |
Token | ily |
Token ID | 813 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
iqu | +0.040 |
ately | +0.039 |
otion | +0.039 |
wen | +0.038 |
erk | +0.038 |
Neg logit contributions | |
likes | -0.031 |
and | -0.030 |
They | -0.030 |
with | -0.028 |
liked | -0.026 |
Token | said |
Token ID | 531 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
They | +0.036 |
likes | +0.035 |
fun | +0.031 |
games | +0.031 |
nice | +0.030 |
Neg logit contributions | |
ately | -0.062 |
iqu | -0.062 |
erk | -0.060 |
ow | -0.060 |
wen | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
otion | +0.009 |
iqu | +0.009 |
ately | +0.009 |
ous | +0.009 |
used | +0.009 |
Neg logit contributions | |
likes | -0.003 |
They | -0.003 |
and | -0.003 |
with | -0.002 |
fun | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
likes | +0.005 |
and | +0.004 |
They | +0.004 |
with | +0.003 |
fun | +0.003 |
Neg logit contributions | |
iqu | -0.019 |
otion | -0.019 |
ately | -0.019 |
wen | -0.018 |
erk | -0.018 |
Token | Let |
Token ID | 5756 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
likes | +0.047 |
and | +0.046 |
They | +0.045 |
with | +0.041 |
nice | +0.037 |
Neg logit contributions | |
iqu | -0.100 |
ately | -0.098 |
otion | -0.098 |
wen | -0.097 |
erk | -0.096 |
Token | 's |
Token ID | 338 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
likes | +0.003 |
They | +0.003 |
liked | +0.002 |
games | +0.002 |
and | +0.002 |
Neg logit contributions | |
iqu | -0.008 |
unct | -0.008 |
ow | -0.008 |
wen | -0.008 |
otion | -0.008 |
Token | find |
Token ID | 1064 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
iqu | +0.051 |
otion | +0.051 |
ately | +0.051 |
wen | +0.050 |
ous | +0.050 |
Neg logit contributions | |
and | -0.021 |
They | -0.021 |
likes | -0.020 |
with | -0.019 |
nice | -0.017 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
and | +0.048 |
likes | +0.047 |
They | +0.046 |
with | +0.041 |
liked | +0.040 |
Neg logit contributions | |
iqu | -0.100 |
otion | -0.099 |
ately | -0.097 |
wen | -0.097 |
used | -0.096 |
Token | scared |
Token ID | 12008 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
likes | +0.044 |
They | +0.042 |
and | +0.041 |
with | +0.038 |
games | +0.036 |
Neg logit contributions | |
iqu | -0.060 |
otion | -0.059 |
ow | -0.057 |
erk | -0.057 |
hesitation | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
likes | +0.018 |
They | +0.011 |
liked | +0.007 |
games | +0.006 |
shapes | +0.006 |
Neg logit contributions | |
ately | -0.109 |
otion | -0.108 |
ous | -0.107 |
ow | -0.105 |
iqu | -0.105 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
iqu | +0.036 |
wen | +0.036 |
ately | +0.036 |
otion | +0.035 |
ous | +0.034 |
Neg logit contributions | |
likes | -0.031 |
and | -0.031 |
They | -0.031 |
with | -0.029 |
nice | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
likes | +0.029 |
They | +0.024 |
and | +0.021 |
liked | +0.019 |
with | +0.019 |
Neg logit contributions | |
ately | -0.105 |
ous | -0.104 |
otion | -0.103 |
iqu | -0.102 |
erk | -0.101 |
Token | They |
Token ID | 1119 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
likes | +0.013 |
and | +0.010 |
games | +0.007 |
with | +0.007 |
nice | +0.007 |
Neg logit contributions | |
ately | -0.080 |
iqu | -0.080 |
otion | -0.079 |
antis | -0.078 |
used | -0.077 |
Token | did |
Token ID | 750 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
and | +0.043 |
likes | +0.042 |
They | +0.042 |
with | +0.037 |
liked | +0.037 |
Neg logit contributions | |
iqu | -0.080 |
otion | -0.079 |
ately | -0.079 |
wen | -0.078 |
used | -0.078 |
Token | not |
Token ID | 407 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
iqu | +0.013 |
ately | +0.013 |
otion | +0.013 |
wen | +0.012 |
used | +0.012 |
Neg logit contributions | |
likes | -0.012 |
and | -0.012 |
They | -0.012 |
with | -0.011 |
nice | -0.010 |
Token | know |
Token ID | 760 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
iqu | +0.039 |
otion | +0.038 |
ately | +0.038 |
wen | +0.037 |
erk | +0.037 |
Neg logit contributions | |
likes | -0.027 |
and | -0.027 |
They | -0.027 |
with | -0.025 |
liked | -0.023 |
Token | how |
Token ID | 703 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
and | +0.001 |
with | +0.001 |
They | +0.001 |
each | +0.001 |
fun | +0.001 |
Neg logit contributions | |
unct | -0.003 |
used | -0.003 |
wen | -0.003 |
istent | -0.003 |
iqu | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
and | +0.003 |
likes | +0.003 |
They | +0.003 |
with | +0.003 |
nice | +0.002 |
Neg logit contributions | |
iqu | -0.014 |
otion | -0.014 |
ately | -0.014 |
wen | -0.014 |
used | -0.014 |
Token | from |
Token ID | 422 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
iqu | +0.081 |
otion | +0.079 |
wen | +0.078 |
ately | +0.078 |
used | +0.077 |
Neg logit contributions | |
and | -0.049 |
They | -0.046 |
with | -0.044 |
likes | -0.041 |
nice | -0.038 |
Token | inside |
Token ID | 2641 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
iqu | +0.055 |
otion | +0.054 |
ately | +0.054 |
wen | +0.053 |
erk | +0.053 |
Neg logit contributions | |
likes | -0.021 |
They | -0.020 |
and | -0.020 |
with | -0.017 |
nice | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
iqu | +0.024 |
otion | +0.024 |
ately | +0.024 |
wen | +0.023 |
erk | +0.023 |
Neg logit contributions | |
likes | -0.005 |
and | -0.005 |
They | -0.005 |
with | -0.004 |
liked | -0.003 |
Token | It |
Token ID | 632 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
used | +0.021 |
ately | +0.021 |
otion | +0.021 |
iqu | +0.021 |
erk | +0.021 |
Neg logit contributions | |
likes | -0.009 |
and | -0.008 |
They | -0.008 |
games | -0.008 |
fun | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
iqu | +0.033 |
ately | +0.033 |
otion | +0.033 |
wen | +0.032 |
used | +0.032 |
Neg logit contributions | |
and | -0.007 |
likes | -0.007 |
They | -0.006 |
with | -0.006 |
liked | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ately | +0.109 |
unct | +0.107 |
used | +0.107 |
iqu | +0.107 |
otion | +0.107 |
Neg logit contributions | |
and | -0.024 |
with | -0.019 |
They | -0.018 |
nice | -0.015 |
green | -0.015 |
Token | loud |
Token ID | 7812 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
and | +0.020 |
likes | +0.020 |
They | +0.019 |
with | +0.018 |
nice | +0.017 |
Neg logit contributions | |
ately | -0.064 |
iqu | -0.064 |
otion | -0.064 |
wen | -0.063 |
used | -0.063 |
Token | scream |
Token ID | 8196 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
likes | +0.024 |
They | +0.023 |
and | +0.022 |
with | +0.021 |
liked | +0.020 |
Neg logit contributions | |
otion | -0.043 |
iqu | -0.042 |
ous | -0.042 |
ately | -0.042 |
erk | -0.041 |
Token | ! |
Token ID | 0 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
iqu | +0.070 |
unct | +0.068 |
wen | +0.068 |
used | +0.067 |
ately | +0.067 |
Neg logit contributions | |
and | -0.019 |
with | -0.016 |
They | -0.016 |
likes | -0.014 |
nice | -0.011 |
Token | |
Token ID | 220 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
otion | +0.005 |
used | +0.005 |
ately | +0.005 |
iqu | +0.005 |
erk | +0.005 |
Neg logit contributions | |
likes | -0.004 |
and | -0.003 |
games | -0.003 |
fun | -0.003 |
shapes | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
otion | +0.029 |
wen | +0.028 |
iqu | +0.028 |
erk | +0.028 |
ately | +0.028 |
Neg logit contributions | |
likes | -0.006 |
games | -0.004 |
and | -0.004 |
fair | -0.004 |
green | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
iqu | +0.066 |
ately | +0.064 |
wen | +0.064 |
otion | +0.064 |
erk | +0.063 |
Neg logit contributions | |
and | -0.020 |
likes | -0.019 |
They | -0.019 |
with | -0.018 |
nice | -0.015 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
iqu | +0.076 |
antis | +0.071 |
otion | +0.071 |
ately | +0.071 |
wen | +0.071 |
Neg logit contributions | |
and | -0.051 |
They | -0.049 |
likes | -0.047 |
with | -0.046 |
| -0.044 |
Token | , |
Token ID | 11 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
iqu | +0.052 |
otion | +0.051 |
ately | +0.051 |
wen | +0.051 |
erk | +0.050 |
Neg logit contributions | |
and | -0.013 |
likes | -0.013 |
They | -0.012 |
with | -0.011 |
nice | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
iqu | +0.005 |
ately | +0.005 |
otion | +0.005 |
wen | +0.005 |
erk | +0.005 |
Neg logit contributions | |
and | -0.001 |
likes | -0.001 |
They | -0.001 |
with | -0.001 |
| -0.001 |
Token | Don |
Token ID | 3987 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
likes | +0.016 |
and | +0.016 |
They | +0.015 |
with | +0.014 |
| +0.013 |
Neg logit contributions | |
iqu | -0.030 |
otion | -0.030 |
ately | -0.029 |
erk | -0.029 |
wen | -0.029 |
Token | 't |
Token ID | 470 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
iqu | +0.066 |
erk | +0.060 |
ately | +0.060 |
antis | +0.059 |
unct | +0.059 |
Neg logit contributions | |
and | -0.092 |
They | -0.088 |
with | -0.087 |
| -0.086 |
likes | -0.083 |
Token | be |
Token ID | 307 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
iqu | +0.037 |
otion | +0.037 |
wen | +0.037 |
ately | +0.037 |
erk | +0.035 |
Neg logit contributions | |
and | -0.032 |
likes | -0.031 |
They | -0.031 |
with | -0.030 |
nice | -0.028 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
iqu | +0.033 |
otion | +0.032 |
ately | +0.032 |
wen | +0.032 |
erk | +0.032 |
Neg logit contributions | |
likes | -0.030 |
They | -0.029 |
and | -0.029 |
with | -0.027 |
liked | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
likes | +0.001 |
They | +0.001 |
and | +0.001 |
with | +0.001 |
liked | +0.001 |
Neg logit contributions | |
iqu | -0.004 |
otion | -0.004 |
ately | -0.004 |
ous | -0.004 |
used | -0.004 |
Token | I |
Token ID | 314 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
iqu | +0.011 |
wen | +0.011 |
ately | +0.011 |
otion | +0.011 |
erk | +0.011 |
Neg logit contributions | |
and | -0.007 |
likes | -0.007 |
They | -0.007 |
with | -0.006 |
nice | -0.006 |
Token | won |
Token ID | 1839 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
otion | +0.007 |
iqu | +0.007 |
ately | +0.007 |
wen | +0.007 |
unct | +0.007 |
Neg logit contributions | |
and | -0.004 |
likes | -0.004 |
They | -0.003 |
with | -0.003 |
| -0.003 |
Token | told |
Token ID | 1297 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
likes | +0.005 |
They | +0.005 |
and | +0.005 |
with | +0.004 |
nice | +0.004 |
Neg logit contributions | |
iqu | -0.009 |
ately | -0.009 |
otion | -0.009 |
wen | -0.009 |
erk | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
iqu | +0.021 |
ately | +0.021 |
otion | +0.021 |
wen | +0.020 |
erk | +0.020 |
Neg logit contributions | |
likes | -0.008 |
and | -0.008 |
They | -0.008 |
with | -0.007 |
liked | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
iqu | +0.027 |
wen | +0.026 |
used | +0.026 |
ately | +0.026 |
erk | +0.026 |
Neg logit contributions | |
and | -0.009 |
They | -0.009 |
likes | -0.008 |
with | -0.008 |
nice | -0.007 |
Token | could |
Token ID | 714 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
likes | +0.003 |
and | +0.003 |
They | +0.003 |
with | +0.002 |
liked | +0.002 |
Neg logit contributions | |
iqu | -0.006 |
otion | -0.006 |
ately | -0.006 |
wen | -0.006 |
used | -0.006 |
Token | use |
Token ID | 779 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
iqu | +0.066 |
otion | +0.065 |
ately | +0.065 |
wen | +0.064 |
used | +0.063 |
Neg logit contributions | |
and | -0.032 |
likes | -0.031 |
They | -0.030 |
with | -0.029 |
liked | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
likes | +0.010 |
They | +0.009 |
and | +0.009 |
with | +0.008 |
liked | +0.007 |
Neg logit contributions | |
iqu | -0.030 |
ately | -0.030 |
otion | -0.030 |
wen | -0.029 |
erk | -0.029 |
Token | for |
Token ID | 329 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
iqu | +0.018 |
ately | +0.018 |
otion | +0.018 |
wen | +0.018 |
erk | +0.018 |
Neg logit contributions | |
likes | -0.005 |
and | -0.005 |
They | -0.005 |
with | -0.004 |
liked | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
and | +0.000 |
fun | +0.000 |
with | +0.000 |
They | +0.000 |
nice | +0.000 |
Neg logit contributions | |
iqu | -0.000 |
used | -0.000 |
otion | -0.000 |
ous | -0.000 |
wen | -0.000 |
Token | pretend |
Token ID | 16614 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
iqu | +0.011 |
ately | +0.011 |
otion | +0.011 |
erk | +0.011 |
used | +0.011 |
Neg logit contributions | |
likes | -0.005 |
They | -0.005 |
and | -0.004 |
with | -0.004 |
liked | -0.004 |
Token | play |
Token ID | 711 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
iqu | +0.013 |
ately | +0.012 |
erk | +0.012 |
ous | +0.012 |
ow | +0.012 |
Neg logit contributions | |
They | -0.010 |
likes | -0.010 |
and | -0.009 |
with | -0.009 |
| -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
likes | +0.014 |
They | +0.014 |
and | +0.010 |
liked | +0.009 |
| +0.009 |
Neg logit contributions | |
otion | -0.043 |
ow | -0.042 |
erk | -0.042 |
ately | -0.041 |
aro | -0.040 |
Token | top |
Token ID | 1353 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
likes | +0.004 |
They | +0.004 |
and | +0.004 |
liked | +0.004 |
games | +0.004 |
Neg logit contributions | |
otion | -0.005 |
wen | -0.005 |
ately | -0.005 |
aro | -0.005 |
iqu | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
iqu | +0.071 |
ately | +0.071 |
otion | +0.071 |
wen | +0.070 |
erk | +0.069 |
Neg logit contributions | |
likes | -0.015 |
They | -0.014 |
and | -0.013 |
with | -0.011 |
liked | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
likes | +0.012 |
fair | +0.012 |
than | +0.011 |
games | +0.011 |
nice | +0.011 |
Neg logit contributions | |
otion | -0.027 |
abella | -0.025 |
izz | -0.025 |
ately | -0.024 |
erk | -0.024 |
Token | Let |
Token ID | 5756 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
likes | +0.025 |
and | +0.025 |
They | +0.022 |
with | +0.022 |
new | +0.021 |
Neg logit contributions | |
izz | -0.051 |
erk | -0.051 |
wen | -0.051 |
otion | -0.050 |
ately | -0.050 |
Token | 's |
Token ID | 338 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
likes | +0.001 |
They | +0.001 |
than | +0.001 |
with | +0.001 |
and | +0.001 |
Neg logit contributions | |
ow | -0.002 |
wen | -0.002 |
otion | -0.002 |
iqu | -0.002 |
used | -0.002 |
Token | go |
Token ID | 467 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
iqu | +0.049 |
otion | +0.048 |
ately | +0.047 |
wen | +0.047 |
ous | +0.046 |
Neg logit contributions | |
and | -0.021 |
likes | -0.021 |
They | -0.021 |
with | -0.019 |
nice | -0.017 |
Token | sled |
Token ID | 46822 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
iqu | +0.066 |
ately | +0.065 |
otion | +0.065 |
wen | +0.064 |
erk | +0.064 |
Neg logit contributions | |
likes | -0.020 |
They | -0.019 |
and | -0.018 |
with | -0.016 |
liked | -0.014 |
Token | ding |
Token ID | 12083 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
iqu | +0.080 |
ately | +0.080 |
otion | +0.079 |
ous | +0.078 |
wen | +0.078 |
Neg logit contributions | |
likes | -0.051 |
They | -0.048 |
and | -0.047 |
with | -0.043 |
nice | -0.042 |
Token | !" |
Token ID | 2474 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
iqu | +0.072 |
ately | +0.071 |
otion | +0.071 |
wen | +0.070 |
used | +0.070 |
Neg logit contributions | |
likes | -0.024 |
They | -0.022 |
and | -0.022 |
with | -0.019 |
liked | -0.018 |
Token | Anna |
Token ID | 11735 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
likes | +0.014 |
nice | +0.012 |
fair | +0.012 |
games | +0.012 |
liked | +0.012 |
Neg logit contributions | |
otion | -0.017 |
ately | -0.017 |
ow | -0.016 |
wen | -0.016 |
izz | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
likes | +0.031 |
They | +0.029 |
nice | +0.027 |
games | +0.026 |
fun | +0.026 |
Neg logit contributions | |
ately | -0.054 |
ow | -0.054 |
erk | -0.053 |
wen | -0.052 |
iqu | -0.052 |
Token | wise |
Token ID | 10787 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
iqu | +0.024 |
otion | +0.023 |
wen | +0.023 |
ately | +0.023 |
used | +0.023 |
Neg logit contributions | |
and | -0.010 |
likes | -0.010 |
They | -0.009 |
with | -0.009 |
nice | -0.008 |
Token | owl |
Token ID | 39610 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
iqu | +0.075 |
ately | +0.074 |
otion | +0.074 |
wen | +0.073 |
erk | +0.072 |
Neg logit contributions | |
likes | -0.032 |
and | -0.031 |
They | -0.031 |
with | -0.028 |
liked | -0.025 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
iqu | +0.031 |
ately | +0.031 |
otion | +0.031 |
ow | +0.030 |
erk | +0.030 |
Neg logit contributions | |
They | -0.016 |
likes | -0.015 |
and | -0.014 |
with | -0.013 |
games | -0.013 |
Token | at |
Token ID | 379 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
They | +0.048 |
likes | +0.044 |
games | +0.043 |
shapes | +0.042 |
Let | +0.040 |
Neg logit contributions | |
iqu | -0.074 |
icking | -0.069 |
unct | -0.068 |
hesitation | -0.067 |
used | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
iqu | +0.010 |
otion | +0.010 |
ately | +0.010 |
wen | +0.010 |
used | +0.010 |
Neg logit contributions | |
and | -0.002 |
They | -0.002 |
likes | -0.002 |
with | -0.002 |
| -0.001 |
Token | bird |
Token ID | 6512 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
iqu | +0.026 |
otion | +0.026 |
ately | +0.026 |
wen | +0.025 |
erk | +0.025 |
Neg logit contributions | |
likes | -0.013 |
and | -0.013 |
They | -0.012 |
with | -0.011 |
nice | -0.010 |
Token | 's |
Token ID | 338 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
iqu | +0.099 |
ately | +0.098 |
otion | +0.098 |
erk | +0.097 |
used | +0.096 |
Neg logit contributions | |
likes | -0.010 |
They | -0.009 |
and | -0.007 |
with | -0.004 |
liked | -0.003 |
Token | wing |
Token ID | 8539 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
iqu | +0.044 |
ately | +0.043 |
otion | +0.042 |
erk | +0.042 |
wen | +0.041 |
Neg logit contributions | |
likes | -0.047 |
They | -0.047 |
and | -0.045 |
with | -0.043 |
liked | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
ately | +0.064 |
iqu | +0.064 |
erk | +0.063 |
otion | +0.063 |
ous | +0.063 |
Neg logit contributions | |
likes | -0.009 |
They | -0.009 |
and | -0.006 |
with | -0.004 |
fun | -0.004 |
Token | sighed |
Token ID | 21893 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
iqu | +0.016 |
ately | +0.016 |
otion | +0.016 |
erk | +0.016 |
wen | +0.016 |
Neg logit contributions | |
likes | -0.009 |
They | -0.009 |
and | -0.009 |
with | -0.008 |
nice | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
likes | +0.016 |
They | +0.014 |
and | +0.012 |
games | +0.010 |
fun | +0.010 |
Neg logit contributions | |
iqu | -0.062 |
ately | -0.061 |
erk | -0.061 |
otion | -0.061 |
ous | -0.061 |
Token | there |
Token ID | 612 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
otion | +0.103 |
ately | +0.101 |
ous | +0.101 |
wen | +0.101 |
iqu | +0.099 |
Neg logit contributions | |
and | -0.027 |
with | -0.025 |
nice | -0.023 |
They | -0.021 |
fun | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
iqu | +0.010 |
otion | +0.010 |
ately | +0.010 |
wen | +0.010 |
used | +0.009 |
Neg logit contributions | |
and | -0.001 |
likes | -0.001 |
They | -0.001 |
with | -0.001 |
nice | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
likes | +0.003 |
and | +0.002 |
games | +0.002 |
nice | +0.002 |
fun | +0.002 |
Neg logit contributions | |
ately | -0.006 |
used | -0.006 |
ow | -0.006 |
iqu | -0.006 |
otion | -0.006 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
likes | +0.016 |
They | +0.016 |
and | +0.015 |
with | +0.014 |
nice | +0.013 |
Neg logit contributions | |
iqu | -0.032 |
ately | -0.032 |
wen | -0.031 |
erk | -0.031 |
otion | -0.031 |
Token | her |
Token ID | 607 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
iqu | +0.045 |
ately | +0.044 |
otion | +0.044 |
wen | +0.044 |
erk | +0.043 |
Neg logit contributions | |
likes | -0.018 |
and | -0.017 |
They | -0.017 |
with | -0.015 |
liked | -0.014 |
Token | mother |
Token ID | 2802 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
iqu | +0.048 |
otion | +0.047 |
ately | +0.047 |
wen | +0.046 |
used | +0.046 |
Neg logit contributions | |
and | -0.033 |
likes | -0.033 |
They | -0.032 |
with | -0.030 |
nice | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
iqu | +0.066 |
wen | +0.065 |
ately | +0.064 |
otion | +0.063 |
used | +0.063 |
Neg logit contributions | |
and | -0.027 |
likes | -0.025 |
They | -0.024 |
with | -0.024 |
| -0.020 |
Token | go |
Token ID | 467 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
iqu | +0.093 |
otion | +0.089 |
ous | +0.089 |
ately | +0.088 |
wen | +0.088 |
Neg logit contributions | |
and | -0.050 |
with | -0.046 |
They | -0.044 |
likes | -0.043 |
nice | -0.040 |
Token | but |
Token ID | 475 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
iqu | +0.087 |
otion | +0.086 |
ately | +0.085 |
wen | +0.085 |
ous | +0.084 |
Neg logit contributions | |
and | -0.022 |
likes | -0.020 |
They | -0.019 |
with | -0.019 |
| -0.014 |
Token | her |
Token ID | 607 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
iqu | +0.103 |
antis | +0.097 |
ous | +0.097 |
ules | +0.096 |
wen | +0.096 |
Neg logit contributions | |
and | -0.038 |
with | -0.034 |
They | -0.029 |
likes | -0.028 |
liked | -0.027 |
Token | mother |
Token ID | 2802 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
otion | +0.047 |
aro | +0.045 |
iqu | +0.044 |
izz | +0.044 |
ous | +0.044 |
Neg logit contributions | |
and | -0.038 |
likes | -0.036 |
with | -0.034 |
nice | -0.033 |
They | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
iqu | +0.131 |
wen | +0.127 |
ately | +0.126 |
otion | +0.126 |
erk | +0.125 |
Neg logit contributions | |
and | -0.027 |
They | -0.026 |
likes | -0.025 |
with | -0.023 |
| -0.018 |
Token | they |
Token ID | 484 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
iqu | +0.100 |
unct | +0.097 |
otion | +0.097 |
wen | +0.097 |
erk | +0.097 |
Neg logit contributions | |
and | -0.043 |
They | -0.042 |
likes | -0.038 |
with | -0.038 |
fun | -0.034 |
Token | see |
Token ID | 766 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
likes | +0.022 |
They | +0.021 |
shapes | +0.020 |
with | +0.020 |
and | +0.020 |
Neg logit contributions | |
otion | -0.034 |
ow | -0.033 |
ately | -0.033 |
used | -0.033 |
erk | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
likes | +0.002 |
They | +0.002 |
and | +0.002 |
with | +0.002 |
liked | +0.002 |
Neg logit contributions | |
iqu | -0.007 |
otion | -0.007 |
ately | -0.007 |
wen | -0.007 |
erk | -0.007 |
Token | big |
Token ID | 1263 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ately | +0.008 |
iqu | +0.008 |
otion | +0.008 |
wen | +0.008 |
used | +0.008 |
Neg logit contributions | |
and | -0.001 |
likes | -0.001 |
They | -0.001 |
with | -0.001 |
nice | -0.001 |
Token | club |
Token ID | 3430 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
likes | +0.030 |
They | +0.030 |
and | +0.029 |
with | +0.027 |
| +0.025 |
Neg logit contributions | |
iqu | -0.061 |
otion | -0.061 |
ately | -0.060 |
erk | -0.059 |
ous | -0.059 |
Token | on |
Token ID | 319 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
otion | +0.071 |
iqu | +0.068 |
used | +0.067 |
ow | +0.067 |
ately | +0.067 |
Neg logit contributions | |
likes | -0.023 |
They | -0.022 |
and | -0.018 |
fun | -0.016 |
nice | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
iqu | +0.024 |
ately | +0.023 |
otion | +0.023 |
wen | +0.023 |
erk | +0.023 |
Neg logit contributions | |
and | -0.004 |
They | -0.004 |
likes | -0.004 |
with | -0.003 |
nice | -0.003 |
Token | grass |
Token ID | 8701 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
wen | +0.004 |
iqu | +0.004 |
ately | +0.004 |
tha | +0.004 |
unct | +0.004 |
Neg logit contributions | |
likes | -0.003 |
They | -0.003 |
and | -0.003 |
with | -0.003 |
liked | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
iqu | +0.074 |
ately | +0.072 |
wen | +0.072 |
unct | +0.072 |
otion | +0.072 |
Neg logit contributions | |
and | -0.010 |
They | -0.009 |
likes | -0.008 |
with | -0.007 |
| -0.004 |
Token | It |
Token ID | 632 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
otion | +0.010 |
ately | +0.009 |
ow | +0.009 |
used | +0.009 |
iqu | +0.009 |
Neg logit contributions | |
likes | -0.004 |
and | -0.003 |
nice | -0.003 |
with | -0.003 |
games | -0.003 |
Token | ily |
Token ID | 813 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
otion | +0.053 |
ately | +0.052 |
iqu | +0.052 |
wen | +0.051 |
erk | +0.050 |
Neg logit contributions | |
They | -0.048 |
likes | -0.048 |
and | -0.046 |
with | -0.044 |
fun | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
They | +0.026 |
likes | +0.023 |
games | +0.022 |
with | +0.021 |
nice | +0.021 |
Neg logit contributions | |
wen | -0.051 |
ately | -0.051 |
iqu | -0.050 |
ow | -0.050 |
unct | -0.050 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
iqu | +0.019 |
ately | +0.019 |
otion | +0.019 |
wen | +0.019 |
ous | +0.019 |
Neg logit contributions | |
and | -0.007 |
likes | -0.007 |
They | -0.006 |
with | -0.006 |
nice | -0.006 |
Token | because |
Token ID | 780 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
likes | +0.034 |
They | +0.031 |
games | +0.026 |
and | +0.026 |
liked | +0.025 |
Neg logit contributions | |
ately | -0.083 |
ous | -0.081 |
otion | -0.081 |
iqu | -0.081 |
erk | -0.078 |
Token | she |
Token ID | 673 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
iqu | +0.063 |
erk | +0.059 |
ately | +0.059 |
wen | +0.058 |
owing | +0.058 |
Neg logit contributions | |
and | -0.023 |
with | -0.021 |
They | -0.017 |
| -0.016 |
green | -0.016 |
Token | couldn |
Token ID | 3521 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
iqu | +0.012 |
ately | +0.012 |
otion | +0.012 |
wen | +0.012 |
erk | +0.012 |
Neg logit contributions | |
likes | -0.007 |
and | -0.007 |
They | -0.007 |
with | -0.006 |
liked | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
iqu | +0.102 |
hesitation | +0.100 |
ately | +0.100 |
erk | +0.092 |
ules | +0.091 |
Neg logit contributions | |
and | -0.133 |
They | -0.131 |
with | -0.128 |
| -0.127 |
likes | -0.122 |
Token | stand |
Token ID | 1302 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
iqu | +0.110 |
wen | +0.105 |
otion | +0.103 |
ately | +0.102 |
used | +0.102 |
Neg logit contributions | |
and | -0.048 |
with | -0.043 |
likes | -0.041 |
They | -0.040 |
liked | -0.037 |
Token | up |
Token ID | 510 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ately | +0.051 |
otion | +0.050 |
wen | +0.050 |
ous | +0.049 |
iqu | +0.049 |
Neg logit contributions | |
and | -0.020 |
with | -0.019 |
nice | -0.015 |
likes | -0.015 |
pretty | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
and | +0.012 |
likes | +0.011 |
They | +0.011 |
with | +0.010 |
nice | +0.007 |
Neg logit contributions | |
iqu | -0.062 |
otion | -0.061 |
ately | -0.061 |
wen | -0.061 |
used | -0.060 |
Token | play |
Token ID | 711 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
iqu | +0.074 |
wen | +0.071 |
otion | +0.070 |
ately | +0.069 |
ules | +0.069 |
Neg logit contributions | |
and | -0.023 |
with | -0.020 |
likes | -0.019 |
They | -0.018 |
| -0.017 |
Token | in |
Token ID | 287 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
likes | +0.029 |
They | +0.024 |
piles | +0.022 |
shapes | +0.022 |
fun | +0.022 |
Neg logit contributions | |
ow | -0.053 |
aro | -0.052 |
used | -0.051 |
ately | -0.051 |
ous | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
likes | +0.020 |
They | +0.016 |
and | +0.015 |
liked | +0.014 |
with | +0.013 |
Neg logit contributions | |
otion | -0.054 |
erk | -0.053 |
ow | -0.053 |
wen | -0.053 |
iqu | -0.053 |
Token | rain |
Token ID | 6290 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
likes | +0.014 |
They | +0.013 |
and | +0.013 |
with | +0.012 |
liked | +0.011 |
Neg logit contributions | |
iqu | -0.026 |
wen | -0.026 |
ow | -0.026 |
unct | -0.026 |
antis | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ow | +0.061 |
iqu | +0.060 |
ous | +0.060 |
erk | +0.060 |
otion | +0.059 |
Neg logit contributions | |
likes | -0.017 |
They | -0.015 |
and | -0.013 |
nice | -0.011 |
fun | -0.010 |
Token | The |
Token ID | 383 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
otion | +0.004 |
ow | +0.004 |
ately | +0.004 |
ous | +0.004 |
antis | +0.004 |
Neg logit contributions | |
likes | -0.001 |
and | -0.001 |
games | -0.001 |
fun | -0.001 |
with | -0.001 |
Token | ostr |
Token ID | 42387 |
Feature activation | -9.60e+00 |
Pos logit contributions | |
iqu | +0.026 |
otion | +0.025 |
ately | +0.025 |
used | +0.024 |
wen | +0.024 |
Neg logit contributions | |
and | -0.022 |
likes | -0.021 |
They | -0.020 |
nice | -0.019 |
green | -0.019 |
Token | ich |
Token ID | 488 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
hesitation | +0.206 |
otion | +0.192 |
erk | +0.187 |
iqu | +0.184 |
ately | +0.176 |
Neg logit contributions | |
and | -0.270 |
likes | -0.263 |
with | -0.255 |
They | -0.244 |
| -0.241 |
Token | was |
Token ID | 373 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
ately | +0.051 |
iqu | +0.051 |
erk | +0.050 |
wen | +0.050 |
otion | +0.050 |
Neg logit contributions | |
They | -0.018 |
likes | -0.017 |
and | -0.015 |
with | -0.014 |
nice | -0.014 |
Token | wet |
Token ID | 9583 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ately | +0.096 |
iqu | +0.095 |
wen | +0.094 |
otion | +0.094 |
ous | +0.092 |
Neg logit contributions | |
and | -0.040 |
with | -0.037 |
likes | -0.037 |
They | -0.036 |
nice | -0.034 |
Token | from |
Token ID | 422 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
likes | +0.012 |
They | +0.010 |
and | +0.006 |
with | +0.004 |
fun | +0.004 |
Neg logit contributions | |
ately | -0.101 |
iqu | -0.101 |
otion | -0.101 |
ous | -0.100 |
erk | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
iqu | +0.108 |
ately | +0.106 |
wen | +0.105 |
otion | +0.103 |
used | +0.103 |
Neg logit contributions | |
and | -0.026 |
likes | -0.021 |
with | -0.021 |
They | -0.020 |
green | -0.019 |
Token | owers |
Token ID | 3618 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
iqu | +0.061 |
otion | +0.059 |
ately | +0.059 |
wen | +0.058 |
erk | +0.057 |
Neg logit contributions | |
likes | -0.087 |
and | -0.086 |
They | -0.086 |
with | -0.082 |
| -0.077 |
Token | in |
Token ID | 287 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
iqu | +0.018 |
ately | +0.018 |
otion | +0.018 |
wen | +0.017 |
erk | +0.017 |
Neg logit contributions | |
likes | -0.003 |
and | -0.003 |
They | -0.003 |
with | -0.002 |
liked | -0.002 |
Token | his |
Token ID | 465 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
likes | +0.009 |
They | +0.008 |
and | +0.008 |
with | +0.007 |
liked | +0.006 |
Neg logit contributions | |
iqu | -0.029 |
ately | -0.029 |
otion | -0.029 |
erk | -0.028 |
wen | -0.028 |
Token | hands |
Token ID | 2832 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
ow | +0.022 |
iqu | +0.021 |
ately | +0.021 |
erk | +0.021 |
used | +0.020 |
Neg logit contributions | |
They | -0.016 |
likes | -0.016 |
and | -0.015 |
with | -0.014 |
They | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
and | +0.002 |
likes | +0.001 |
They | +0.001 |
with | +0.001 |
| +0.001 |
Neg logit contributions | |
iqu | -0.012 |
otion | -0.012 |
wen | -0.012 |
ately | -0.012 |
erk | -0.012 |
Token | G |
Token ID | 402 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
iqu | +0.024 |
ately | +0.023 |
used | +0.023 |
erk | +0.023 |
ow | +0.023 |
Neg logit contributions | |
likes | -0.008 |
and | -0.007 |
nice | -0.006 |
with | -0.006 |
They | -0.006 |
Token | ently |
Token ID | 1473 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
hesitation | +0.097 |
otion | +0.087 |
unct | +0.087 |
used | +0.085 |
iqu | +0.085 |
Neg logit contributions | |
and | -0.222 |
likes | -0.215 |
They | -0.203 |
| -0.198 |
with | -0.196 |
Token | , |
Token ID | 11 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
used | +0.003 |
ately | +0.003 |
iqu | +0.003 |
ous | +0.003 |
hesitation | +0.003 |
Neg logit contributions | |
likes | -0.001 |
They | -0.001 |
and | -0.001 |
fun | -0.001 |
games | -0.001 |
Token | Sam |
Token ID | 3409 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
iqu | +0.095 |
otion | +0.095 |
wen | +0.094 |
ous | +0.091 |
unct | +0.091 |
Neg logit contributions | |
and | -0.030 |
with | -0.026 |
They | -0.023 |
likes | -0.021 |
| -0.020 |
Token | reached |
Token ID | 4251 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
They | +0.005 |
likes | +0.005 |
and | +0.004 |
with | +0.004 |
fun | +0.004 |
Neg logit contributions | |
iqu | -0.009 |
ately | -0.008 |
erk | -0.008 |
used | -0.008 |
wen | -0.008 |
Token | out |
Token ID | 503 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
iqu | +0.104 |
ately | +0.102 |
otion | +0.102 |
erk | +0.101 |
used | +0.101 |
Neg logit contributions | |
likes | -0.049 |
They | -0.046 |
and | -0.045 |
with | -0.040 |
liked | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
likes | +0.011 |
They | +0.011 |
and | +0.010 |
with | +0.009 |
liked | +0.008 |
Neg logit contributions | |
iqu | -0.041 |
ately | -0.041 |
otion | -0.040 |
wen | -0.040 |
erk | -0.040 |
Token | get |
Token ID | 651 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
iqu | +0.091 |
ately | +0.089 |
otion | +0.089 |
wen | +0.088 |
erk | +0.088 |
Neg logit contributions | |
likes | -0.057 |
They | -0.055 |
and | -0.055 |
with | -0.050 |
liked | -0.047 |
Token | rid |
Token ID | 5755 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
iqu | +0.058 |
ately | +0.057 |
otion | +0.057 |
wen | +0.056 |
erk | +0.056 |
Neg logit contributions | |
likes | -0.020 |
and | -0.020 |
They | -0.020 |
with | -0.018 |
nice | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
likes | +0.015 |
They | +0.014 |
and | +0.014 |
fun | +0.013 |
liked | +0.013 |
Neg logit contributions | |
otion | -0.022 |
ately | -0.022 |
iqu | -0.021 |
ous | -0.021 |
ow | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
and | +0.001 |
They | +0.001 |
likes | +0.001 |
with | +0.001 |
| +0.001 |
Neg logit contributions | |
iqu | -0.006 |
wen | -0.006 |
ous | -0.006 |
otion | -0.006 |
used | -0.006 |
Token | fle |
Token ID | 5104 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
iqu | +0.027 |
ately | +0.027 |
otion | +0.026 |
used | +0.026 |
wen | +0.026 |
Neg logit contributions | |
likes | -0.020 |
They | -0.020 |
and | -0.020 |
with | -0.018 |
liked | -0.017 |
Token | a |
Token ID | 64 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
iqu | +0.138 |
ately | +0.135 |
otion | +0.134 |
wen | +0.131 |
erk | +0.130 |
Neg logit contributions | |
likes | -0.162 |
They | -0.160 |
and | -0.160 |
with | -0.150 |
nice | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ately | +0.088 |
iqu | +0.088 |
otion | +0.088 |
erk | +0.087 |
ow | +0.087 |
Neg logit contributions | |
likes | -0.019 |
They | -0.018 |
and | -0.016 |
with | -0.013 |
liked | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
likes | +0.015 |
games | +0.014 |
and | +0.013 |
nice | +0.012 |
fun | +0.012 |
Neg logit contributions | |
otion | -0.048 |
ately | -0.048 |
antis | -0.047 |
iqu | -0.047 |
ow | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
iqu | +0.008 |
otion | +0.008 |
wen | +0.008 |
ately | +0.008 |
erk | +0.008 |
Neg logit contributions | |
likes | -0.001 |
and | -0.001 |
They | -0.001 |
games | -0.001 |
with | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
wen | +0.042 |
otion | +0.042 |
iqu | +0.042 |
antis | +0.041 |
izz | +0.041 |
Neg logit contributions | |
likes | -0.022 |
They | -0.021 |
and | -0.021 |
games | -0.020 |
fun | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
iqu | +0.052 |
otion | +0.051 |
ately | +0.051 |
wen | +0.051 |
erk | +0.050 |
Neg logit contributions | |
likes | -0.014 |
and | -0.014 |
They | -0.013 |
with | -0.012 |
nice | -0.010 |
Token | duck |
Token ID | 22045 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
iqu | +0.046 |
ately | +0.046 |
wen | +0.046 |
used | +0.045 |
otion | +0.045 |
Neg logit contributions | |
likes | -0.025 |
and | -0.024 |
They | -0.024 |
with | -0.022 |
nice | -0.021 |
Token | ," |
Token ID | 553 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
iqu | +0.041 |
ow | +0.041 |
erk | +0.041 |
ous | +0.041 |
otion | +0.041 |
Neg logit contributions | |
They | -0.023 |
likes | -0.023 |
and | -0.020 |
games | -0.020 |
fun | -0.020 |
Token | said |
Token ID | 531 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
otion | +0.018 |
iqu | +0.018 |
ately | +0.018 |
used | +0.018 |
erk | +0.018 |
Neg logit contributions | |
likes | -0.010 |
and | -0.010 |
They | -0.009 |
with | -0.009 |
fun | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
iqu | +0.104 |
ately | +0.101 |
otion | +0.101 |
wen | +0.100 |
erk | +0.099 |
Neg logit contributions | |
likes | -0.039 |
and | -0.039 |
They | -0.039 |
with | -0.035 |
nice | -0.031 |
Token | oct |
Token ID | 19318 |
Feature activation | -7.78e+00 |
Pos logit contributions | |
iqu | +0.082 |
otion | +0.080 |
ately | +0.080 |
erk | +0.079 |
used | +0.078 |
Neg logit contributions | |
likes | -0.039 |
They | -0.038 |
and | -0.038 |
with | -0.034 |
liked | -0.031 |
Token | opus |
Token ID | 25790 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
iqu | +0.138 |
ately | +0.135 |
otion | +0.132 |
wen | +0.131 |
hesitation | +0.129 |
Neg logit contributions | |
likes | -0.238 |
and | -0.236 |
They | -0.229 |
with | -0.228 |
| -0.215 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
iqu | +0.060 |
ately | +0.059 |
otion | +0.059 |
erk | +0.059 |
used | +0.058 |
Neg logit contributions | |
likes | -0.011 |
They | -0.010 |
and | -0.010 |
with | -0.008 |
fun | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
otion | +0.032 |
erk | +0.031 |
ow | +0.031 |
used | +0.030 |
ous | +0.030 |
Neg logit contributions | |
likes | -0.014 |
games | -0.013 |
fun | -0.012 |
and | -0.012 |
shapes | -0.011 |
Token | Do |
Token ID | 5211 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
likes | +0.036 |
and | +0.035 |
They | +0.035 |
fun | +0.034 |
nice | +0.032 |
Neg logit contributions | |
otion | -0.056 |
used | -0.054 |
ately | -0.053 |
erk | -0.053 |
antis | -0.052 |
Token | you |
Token ID | 345 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
iqu | +0.022 |
otion | +0.022 |
ately | +0.022 |
wen | +0.021 |
erk | +0.021 |
Neg logit contributions | |
likes | -0.011 |
and | -0.010 |
They | -0.010 |
with | -0.009 |
liked | -0.009 |
Token | joy |
Token ID | 8716 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
likes | +0.025 |
They | +0.024 |
and | +0.023 |
with | +0.022 |
liked | +0.021 |
Neg logit contributions | |
hesitation | -0.032 |
iqu | -0.031 |
otion | -0.031 |
ow | -0.031 |
used | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
likes | +0.015 |
and | +0.015 |
They | +0.014 |
with | +0.012 |
liked | +0.009 |
Neg logit contributions | |
iqu | -0.080 |
otion | -0.078 |
ately | -0.078 |
wen | -0.077 |
erk | -0.077 |
Token | knowing |
Token ID | 6970 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
likes | +0.015 |
They | +0.014 |
and | +0.012 |
games | +0.011 |
with | +0.011 |
Neg logit contributions | |
ately | -0.040 |
used | -0.040 |
iqu | -0.040 |
ous | -0.039 |
erk | -0.039 |
Token | now |
Token ID | 783 |
Feature activation | +9.81e-03 |
Pos logit contributions | |
and | +0.006 |
likes | +0.006 |
They | +0.006 |
with | +0.006 |
nice | +0.005 |
Neg logit contributions | |
iqu | -0.014 |
otion | -0.014 |
ately | -0.013 |
wen | -0.013 |
used | -0.013 |
Token | why |
Token ID | 1521 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
and | +0.000 |
likes | +0.000 |
They | +0.000 |
with | +0.000 |
nice | +0.000 |
Neg logit contributions | |
iqu | -0.000 |
otion | -0.000 |
ately | -0.000 |
wen | -0.000 |
erk | -0.000 |
Token | m |
Token ID | 285 |
Feature activation | -7.64e+00 |
Pos logit contributions | |
iqu | +0.039 |
otion | +0.037 |
wen | +0.037 |
ately | +0.037 |
unct | +0.037 |
Neg logit contributions | |
and | -0.017 |
They | -0.016 |
likes | -0.016 |
with | -0.015 |
nice | -0.013 |
Token | ama |
Token ID | 1689 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
hesitation | +0.124 |
otion | +0.112 |
iqu | +0.105 |
comb | +0.103 |
idget | +0.102 |
Neg logit contributions | |
and | -0.241 |
with | -0.216 |
| -0.215 |
" | -0.205 |
likes | -0.205 |
Token | had |
Token ID | 550 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
iqu | +0.069 |
otion | +0.069 |
ately | +0.068 |
wen | +0.067 |
unct | +0.067 |
Neg logit contributions | |
and | -0.026 |
likes | -0.025 |
They | -0.023 |
with | -0.022 |
liked | -0.020 |
Token | been |
Token ID | 587 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
likes | +0.003 |
They | +0.003 |
and | +0.003 |
with | +0.003 |
liked | +0.003 |
Neg logit contributions | |
iqu | -0.004 |
ately | -0.004 |
otion | -0.004 |
wen | -0.004 |
erk | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
iqu | +0.028 |
ately | +0.027 |
otion | +0.027 |
wen | +0.027 |
erk | +0.027 |
Neg logit contributions | |
likes | -0.019 |
and | -0.018 |
They | -0.018 |
with | -0.017 |
liked | -0.016 |
Token | secretive |
Token ID | 32654 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
otion | +0.034 |
ately | +0.033 |
wen | +0.033 |
iqu | +0.032 |
ous | +0.032 |
Neg logit contributions | |
and | -0.013 |
likes | -0.013 |
with | -0.013 |
nice | -0.012 |
They | -0.012 |