Token | . |
Token ID | 13 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
joy | +0.015 |
time | +0.011 |
than | +0.011 |
minutes | +0.010 |
no | +0.009 |
Neg logit contributions | |
Amen | -0.023 |
glers | -0.023 |
Sorry | -0.023 |
aliens | -0.022 |
chers | -0.022 |
Token | Let |
Token ID | 3914 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
glers | +0.080 |
aliens | +0.076 |
Amen | +0.076 |
chers | +0.076 |
Sorry | +0.074 |
Neg logit contributions | |
joy | -0.051 |
time | -0.038 |
than | -0.036 |
minutes | -0.033 |
no | -0.032 |
Token | â |
Token ID | 22940 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
glers | +0.133 |
Amen | +0.129 |
aliens | +0.128 |
chers | +0.127 |
actresses | +0.122 |
Neg logit contributions | |
joy | -0.125 |
time | -0.111 |
than | -0.098 |
no | -0.096 |
to | -0.095 |
Token | € |
Token ID | 26391 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
glers | +0.151 |
Amen | +0.148 |
chers | +0.140 |
Sorry | +0.140 |
aliens | +0.138 |
Neg logit contributions | |
joy | -0.175 |
time | -0.137 |
than | -0.137 |
minutes | -0.131 |
no | -0.124 |
Token | ™ |
Token ID | 8151 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
glers | +0.093 |
Amen | +0.091 |
chers | +0.089 |
Sorry | +0.089 |
girls | +0.087 |
Neg logit contributions | |
joy | -0.072 |
time | -0.055 |
than | -0.054 |
minutes | -0.052 |
no | -0.049 |
Token | s |
Token ID | 82 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
joy | +0.009 |
time | +0.008 |
than | +0.008 |
no | +0.007 |
to | +0.007 |
Neg logit contributions | |
aliens | -0.007 |
Amen | -0.006 |
glers | -0.006 |
chers | -0.006 |
actresses | -0.006 |
Token | bake |
Token ID | 28450 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
chers | +0.263 |
aliens | +0.262 |
Amen | +0.262 |
glers | +0.260 |
actresses | +0.247 |
Neg logit contributions | |
time | -0.194 |
to | -0.179 |
joy | -0.174 |
that | -0.158 |
an | -0.156 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
glers | +0.041 |
Amen | +0.039 |
chers | +0.039 |
aliens | +0.039 |
Sorry | +0.038 |
Neg logit contributions | |
joy | -0.024 |
time | -0.016 |
than | -0.016 |
minutes | -0.015 |
no | -0.014 |
Token | cake |
Token ID | 12187 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
glers | +0.088 |
Amen | +0.084 |
aliens | +0.083 |
chers | +0.082 |
Sorry | +0.081 |
Neg logit contributions | |
joy | -0.089 |
time | -0.071 |
than | -0.069 |
minutes | -0.066 |
no | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
glers | +0.100 |
Amen | +0.099 |
aliens | +0.098 |
chers | +0.096 |
Sorry | +0.095 |
Neg logit contributions | |
joy | -0.057 |
time | -0.045 |
than | -0.044 |
minutes | -0.039 |
to | -0.039 |
Token | celebrate |
Token ID | 10648 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
glers | +0.071 |
chers | +0.069 |
aliens | +0.068 |
Amen | +0.067 |
girls | +0.066 |
Neg logit contributions | |
joy | -0.047 |
time | -0.044 |
to | -0.043 |
than | -0.040 |
that | -0.038 |
Token | ! |
Token ID | 0 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
joy | +0.014 |
time | +0.010 |
than | +0.010 |
minutes | +0.009 |
no | +0.009 |
Neg logit contributions | |
glers | -0.019 |
Amen | -0.019 |
aliens | -0.018 |
chers | -0.018 |
Sorry | -0.018 |
Token | Let |
Token ID | 3914 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
glers | +0.100 |
aliens | +0.096 |
chers | +0.095 |
Amen | +0.095 |
girls | +0.091 |
Neg logit contributions | |
joy | -0.068 |
time | -0.052 |
than | -0.049 |
minutes | -0.045 |
no | -0.045 |
Token | â |
Token ID | 22940 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
glers | +0.127 |
Amen | +0.123 |
aliens | +0.121 |
chers | +0.120 |
girls | +0.116 |
Neg logit contributions | |
joy | -0.121 |
time | -0.107 |
than | -0.095 |
no | -0.092 |
to | -0.092 |
Token | € |
Token ID | 26391 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
glers | +0.150 |
Amen | +0.145 |
chers | +0.139 |
Sorry | +0.138 |
aliens | +0.138 |
Neg logit contributions | |
joy | -0.171 |
time | -0.135 |
than | -0.134 |
minutes | -0.128 |
no | -0.122 |
Token | ™ |
Token ID | 8151 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
glers | +0.091 |
Amen | +0.088 |
chers | +0.087 |
Sorry | +0.086 |
aliens | +0.085 |
Neg logit contributions | |
joy | -0.074 |
time | -0.057 |
than | -0.056 |
minutes | -0.054 |
no | -0.051 |
Token | s |
Token ID | 82 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
joy | +0.005 |
time | +0.004 |
than | +0.004 |
no | +0.004 |
to | +0.004 |
Neg logit contributions | |
aliens | -0.004 |
Amen | -0.004 |
glers | -0.004 |
actresses | -0.003 |
chers | -0.003 |
Token | ride |
Token ID | 6594 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Amen | +0.250 |
glers | +0.249 |
chers | +0.249 |
aliens | +0.248 |
girls | +0.236 |
Neg logit contributions | |
time | -0.187 |
to | -0.176 |
joy | -0.168 |
that | -0.154 |
an | -0.153 |
Token | on |
Token ID | 319 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
glers | +0.055 |
Amen | +0.053 |
aliens | +0.053 |
chers | +0.051 |
Sorry | +0.051 |
Neg logit contributions | |
joy | -0.037 |
time | -0.028 |
than | -0.027 |
no | -0.025 |
minutes | -0.024 |
Token | ! |
Token ID | 0 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
glers | +0.105 |
Amen | +0.101 |
aliens | +0.100 |
chers | +0.099 |
Sorry | +0.098 |
Neg logit contributions | |
joy | -0.091 |
time | -0.070 |
than | -0.068 |
minutes | -0.064 |
no | -0.062 |
Token | â |
Token ID | 22940 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
glers | +0.051 |
aliens | +0.047 |
chers | +0.045 |
maid | +0.045 |
actresses | +0.045 |
Neg logit contributions | |
joy | -0.033 |
time | -0.025 |
but | -0.023 |
than | -0.023 |
to | -0.022 |
Token | € |
Token ID | 26391 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Amen | +0.072 |
glers | +0.071 |
hing | +0.070 |
ishly | +0.067 |
Sorry | +0.066 |
Neg logit contributions | |
joy | -0.090 |
minutes | -0.070 |
than | -0.069 |
time | -0.068 |
long | -0.065 |
Token | your |
Token ID | 534 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
joy | +0.010 |
than | +0.007 |
time | +0.007 |
looking | +0.006 |
minutes | +0.006 |
Neg logit contributions | |
glers | -0.015 |
Amen | -0.014 |
aliens | -0.014 |
chers | -0.014 |
Sorry | -0.014 |
Token | happy |
Token ID | 3772 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
aliens | +0.027 |
glers | +0.027 |
Amen | +0.026 |
Sorry | +0.026 |
chers | +0.025 |
Neg logit contributions | |
joy | -0.026 |
minutes | -0.019 |
than | -0.019 |
looking | -0.019 |
time | -0.019 |
Token | place |
Token ID | 1295 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
joy | +0.023 |
time | +0.015 |
minutes | +0.015 |
than | +0.015 |
looking | +0.015 |
Neg logit contributions | |
glers | -0.032 |
Amen | -0.032 |
aliens | -0.031 |
Sorry | -0.031 |
chers | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
joy | +0.001 |
time | +0.001 |
than | +0.001 |
minutes | +0.001 |
no | +0.001 |
Neg logit contributions | |
glers | -0.002 |
Amen | -0.002 |
aliens | -0.002 |
chers | -0.002 |
Sorry | -0.002 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
glers | +0.056 |
chers | +0.051 |
aliens | +0.049 |
maid | +0.049 |
girls | +0.048 |
Neg logit contributions | |
joy | -0.041 |
time | -0.032 |
than | -0.031 |
minutes | -0.028 |
-- | -0.028 |
Token | all |
Token ID | 477 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
glers | +0.080 |
Amen | +0.076 |
aliens | +0.075 |
chers | +0.074 |
girls | +0.073 |
Neg logit contributions | |
joy | -0.069 |
time | -0.064 |
than | -0.054 |
to | -0.054 |
no | -0.053 |
Token | your |
Token ID | 534 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
chers | +0.267 |
girls | +0.256 |
glers | +0.256 |
Amen | +0.253 |
aliens | +0.248 |
Neg logit contributions | |
time | -0.187 |
to | -0.152 |
joy | -0.150 |
than | -0.142 |
. | -0.142 |
Token | worries |
Token ID | 18572 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
glers | +0.030 |
Amen | +0.029 |
aliens | +0.029 |
chers | +0.028 |
Sorry | +0.028 |
Neg logit contributions | |
joy | -0.026 |
time | -0.021 |
than | -0.020 |
minutes | -0.019 |
no | -0.018 |
Token | drift |
Token ID | 24260 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
glers | +0.071 |
Amen | +0.069 |
aliens | +0.067 |
Sorry | +0.066 |
chers | +0.066 |
Neg logit contributions | |
joy | -0.038 |
time | -0.031 |
than | -0.030 |
to | -0.027 |
minutes | -0.025 |
Token | away |
Token ID | 1497 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
glers | +0.009 |
chers | +0.008 |
Sorry | +0.008 |
actresses | +0.008 |
Amen | +0.008 |
Neg logit contributions | |
joy | -0.007 |
time | -0.007 |
than | -0.006 |
to | -0.006 |
minutes | -0.005 |
Token | ." |
Token ID | 526 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
glers | +0.069 |
Amen | +0.066 |
chers | +0.064 |
Sorry | +0.064 |
aliens | +0.062 |
Neg logit contributions | |
joy | -0.051 |
than | -0.043 |
time | -0.043 |
to | -0.038 |
minutes | -0.037 |
Token | ! |
Token ID | 0 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
glers | +0.030 |
Amen | +0.029 |
chers | +0.029 |
aliens | +0.028 |
Sorry | +0.028 |
Neg logit contributions | |
joy | -0.015 |
time | -0.009 |
no | -0.009 |
minutes | -0.009 |
than | -0.008 |
Token | Now |
Token ID | 2735 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
glers | +0.019 |
aliens | +0.018 |
chers | +0.018 |
Amen | +0.017 |
Sorry | +0.017 |
Neg logit contributions | |
joy | -0.018 |
time | -0.014 |
than | -0.014 |
minutes | -0.013 |
no | -0.012 |
Token | you |
Token ID | 345 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
glers | +0.028 |
Amen | +0.026 |
aliens | +0.026 |
chers | +0.026 |
Sorry | +0.025 |
Neg logit contributions | |
joy | -0.030 |
time | -0.024 |
than | -0.023 |
minutes | -0.022 |
no | -0.021 |
Token | can |
Token ID | 460 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
time | +0.018 |
joy | +0.017 |
like | +0.015 |
to | +0.015 |
than | +0.015 |
Neg logit contributions | |
glers | -0.022 |
Amen | -0.020 |
actresses | -0.019 |
Sorry | -0.019 |
girls | -0.018 |
Token | make |
Token ID | 787 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
chers | +0.020 |
aliens | +0.020 |
glers | +0.020 |
Amen | +0.019 |
girls | +0.019 |
Neg logit contributions | |
time | -0.013 |
joy | -0.012 |
to | -0.012 |
. | -0.011 |
like | -0.011 |
Token | all |
Token ID | 477 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
glers | +0.088 |
aliens | +0.086 |
Amen | +0.084 |
chers | +0.083 |
Sorry | +0.082 |
Neg logit contributions | |
joy | -0.068 |
than | -0.050 |
time | -0.049 |
minutes | -0.046 |
looking | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
glers | +0.257 |
Amen | +0.253 |
chers | +0.252 |
aliens | +0.246 |
girls | +0.245 |
Neg logit contributions | |
joy | -0.178 |
time | -0.144 |
than | -0.137 |
no | -0.125 |
to | -0.121 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
glers | +0.057 |
aliens | +0.055 |
Amen | +0.055 |
chers | +0.054 |
Sorry | +0.053 |
Neg logit contributions | |
joy | -0.052 |
time | -0.040 |
than | -0.040 |
minutes | -0.038 |
no | -0.037 |
Token | pictures |
Token ID | 5986 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
glers | +0.021 |
Amen | +0.020 |
aliens | +0.020 |
chers | +0.019 |
Sorry | +0.019 |
Neg logit contributions | |
joy | -0.017 |
time | -0.014 |
than | -0.013 |
minutes | -0.012 |
no | -0.012 |
Token | without |
Token ID | 1231 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
glers | +0.036 |
Amen | +0.035 |
girls | +0.034 |
aliens | +0.033 |
chers | +0.033 |
Neg logit contributions | |
joy | -0.022 |
than | -0.019 |
time | -0.019 |
to | -0.017 |
minutes | -0.016 |
Token | worrying |
Token ID | 18916 |
Feature activation | +9.43e-03 |
Pos logit contributions | |
glers | +0.001 |
aliens | +0.001 |
Amen | +0.001 |
chers | +0.001 |
Sorry | +0.001 |
Neg logit contributions | |
joy | -0.001 |
time | -0.001 |
than | -0.001 |
looking | -0.000 |
minutes | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +4.58e-03 |
Pos logit contributions | |
joy | +0.031 |
than | +0.023 |
time | +0.023 |
to | +0.021 |
looking | +0.019 |
Neg logit contributions | |
glers | -0.063 |
Amen | -0.061 |
aliens | -0.061 |
chers | -0.061 |
Sorry | -0.059 |
Token | He |
Token ID | 679 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
glers | +0.000 |
Sorry | +0.000 |
aliens | +0.000 |
Amen | +0.000 |
floats | +0.000 |
Neg logit contributions | |
joy | -0.000 |
minutes | -0.000 |
time | -0.000 |
than | -0.000 |
no | -0.000 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
glers | +0.002 |
aliens | +0.002 |
Amen | +0.002 |
chers | +0.002 |
Sorry | +0.001 |
Neg logit contributions | |
joy | -0.002 |
time | -0.001 |
than | -0.001 |
minutes | -0.001 |
no | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
glers | +0.001 |
aliens | +0.001 |
floats | +0.001 |
actresses | +0.001 |
Amen | +0.001 |
Neg logit contributions | |
joy | -0.000 |
time | -0.000 |
minutes | -0.000 |
-- | -0.000 |
than | -0.000 |
Token | make |
Token ID | 787 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
glers | +0.004 |
chers | +0.004 |
Amen | +0.004 |
aliens | +0.004 |
girls | +0.004 |
Neg logit contributions | |
joy | -0.004 |
time | -0.003 |
than | -0.003 |
to | -0.003 |
no | -0.003 |
Token | all |
Token ID | 477 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
glers | +0.084 |
aliens | +0.081 |
chers | +0.079 |
Amen | +0.078 |
floats | +0.077 |
Neg logit contributions | |
joy | -0.079 |
time | -0.061 |
than | -0.060 |
minutes | -0.057 |
no | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
glers | +0.264 |
chers | +0.263 |
Amen | +0.263 |
aliens | +0.257 |
girls | +0.255 |
Neg logit contributions | |
joy | -0.164 |
time | -0.134 |
than | -0.125 |
no | -0.111 |
looking | -0.109 |
Token | kids |
Token ID | 3988 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
glers | +0.054 |
Amen | +0.054 |
chers | +0.053 |
Sorry | +0.051 |
girls | +0.051 |
Neg logit contributions | |
joy | -0.048 |
time | -0.043 |
than | -0.038 |
minutes | -0.034 |
no | -0.034 |
Token | laugh |
Token ID | 6487 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
glers | +0.116 |
Amen | +0.116 |
Sorry | +0.113 |
aliens | +0.113 |
chers | +0.111 |
Neg logit contributions | |
joy | -0.081 |
time | -0.065 |
than | -0.064 |
to | -0.056 |
because | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
glers | +0.037 |
Amen | +0.036 |
chers | +0.036 |
Sorry | +0.036 |
aliens | +0.036 |
Neg logit contributions | |
joy | -0.011 |
time | -0.007 |
than | -0.007 |
minutes | -0.005 |
no | -0.005 |
Token | One |
Token ID | 1881 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
glers | +0.001 |
Amen | +0.001 |
aliens | +0.001 |
Sorry | +0.001 |
floats | +0.001 |
Neg logit contributions | |
joy | -0.001 |
than | -0.001 |
minutes | -0.001 |
time | -0.001 |
no | -0.001 |
Token | toys |
Token ID | 14958 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
glers | +0.031 |
aliens | +0.030 |
chers | +0.029 |
Amen | +0.029 |
Sorry | +0.029 |
Neg logit contributions | |
joy | -0.033 |
time | -0.026 |
than | -0.026 |
no | -0.024 |
minutes | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
glers | +0.059 |
aliens | +0.056 |
chers | +0.056 |
Amen | +0.056 |
Sorry | +0.055 |
Neg logit contributions | |
joy | -0.026 |
time | -0.017 |
than | -0.015 |
minutes | -0.014 |
no | -0.014 |
Token | Let |
Token ID | 3914 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
glers | +0.064 |
chers | +0.061 |
aliens | +0.060 |
maid | +0.058 |
Amen | +0.058 |
Neg logit contributions | |
joy | -0.042 |
time | -0.032 |
than | -0.030 |
minutes | -0.028 |
-- | -0.027 |
Token | 's |
Token ID | 338 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
glers | +0.121 |
Amen | +0.120 |
aliens | +0.117 |
chers | +0.116 |
girls | +0.114 |
Neg logit contributions | |
time | -0.085 |
joy | -0.084 |
to | -0.069 |
no | -0.065 |
than | -0.064 |
Token | put |
Token ID | 1234 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
chers | +0.258 |
glers | +0.248 |
girls | +0.243 |
rol | +0.241 |
Amen | +0.240 |
Neg logit contributions | |
time | -0.142 |
to | -0.122 |
like | -0.111 |
. | -0.111 |
because | -0.108 |
Token | all |
Token ID | 477 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
glers | +0.048 |
Amen | +0.046 |
aliens | +0.046 |
chers | +0.045 |
Sorry | +0.044 |
Neg logit contributions | |
joy | -0.057 |
time | -0.045 |
than | -0.044 |
minutes | -0.042 |
no | -0.042 |
Token | your |
Token ID | 534 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Amen | +0.252 |
glers | +0.248 |
chers | +0.242 |
girls | +0.242 |
aliens | +0.240 |
Neg logit contributions | |
joy | -0.176 |
time | -0.151 |
than | -0.140 |
to | -0.132 |
minutes | -0.129 |
Token | cars |
Token ID | 5006 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
glers | +0.049 |
aliens | +0.047 |
Amen | +0.047 |
chers | +0.046 |
Sorry | +0.045 |
Neg logit contributions | |
joy | -0.061 |
time | -0.049 |
than | -0.048 |
minutes | -0.046 |
no | -0.045 |
Token | in |
Token ID | 287 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
glers | +0.008 |
Amen | +0.008 |
aliens | +0.008 |
Sorry | +0.008 |
chers | +0.008 |
Neg logit contributions | |
joy | -0.005 |
time | -0.004 |
than | -0.004 |
minutes | -0.004 |
no | -0.004 |
Token | one |
Token ID | 530 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
glers | +0.053 |
aliens | +0.051 |
Amen | +0.051 |
chers | +0.050 |
Sorry | +0.049 |
Neg logit contributions | |
joy | -0.032 |
time | -0.023 |
than | -0.022 |
minutes | -0.020 |
no | -0.020 |
Token | box |
Token ID | 3091 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
Amen | +0.037 |
glers | +0.037 |
chers | +0.036 |
aliens | +0.036 |
actresses | +0.035 |
Neg logit contributions | |
joy | -0.032 |
time | -0.028 |
than | -0.027 |
minutes | -0.025 |
to | -0.024 |
Token | loved |
Token ID | 6151 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
glers | +0.058 |
Amen | +0.056 |
aliens | +0.055 |
chers | +0.054 |
Sorry | +0.054 |
Neg logit contributions | |
joy | -0.031 |
time | -0.023 |
than | -0.022 |
minutes | -0.019 |
no | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
glers | +0.042 |
aliens | +0.042 |
Amen | +0.041 |
actresses | +0.040 |
floats | +0.040 |
Neg logit contributions | |
joy | -0.019 |
than | -0.011 |
time | -0.011 |
minutes | -0.011 |
looking | -0.010 |
Token | jump |
Token ID | 4391 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
glers | +0.027 |
chers | +0.027 |
aliens | +0.025 |
Amen | +0.025 |
girls | +0.025 |
Neg logit contributions | |
joy | -0.025 |
time | -0.023 |
than | -0.020 |
to | -0.019 |
minutes | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
joy | +0.005 |
time | +0.003 |
than | +0.003 |
minutes | +0.003 |
no | +0.003 |
Neg logit contributions | |
glers | -0.007 |
aliens | -0.007 |
Amen | -0.007 |
chers | -0.007 |
Sorry | -0.007 |
Token | play |
Token ID | 711 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
glers | +0.046 |
chers | +0.046 |
aliens | +0.045 |
Amen | +0.044 |
maid | +0.043 |
Neg logit contributions | |
joy | -0.040 |
time | -0.034 |
to | -0.033 |
than | -0.032 |
but | -0.031 |
Token | all |
Token ID | 477 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
glers | +0.066 |
Amen | +0.063 |
aliens | +0.063 |
chers | +0.063 |
Sorry | +0.061 |
Neg logit contributions | |
joy | -0.040 |
time | -0.029 |
than | -0.028 |
minutes | -0.026 |
no | -0.025 |
Token | day |
Token ID | 1110 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
glers | +0.309 |
Amen | +0.298 |
aliens | +0.296 |
chers | +0.293 |
Sorry | +0.290 |
Neg logit contributions | |
joy | -0.129 |
time | -0.079 |
than | -0.075 |
minutes | -0.068 |
no | -0.064 |
Token | long |
Token ID | 890 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
glers | +0.019 |
Amen | +0.018 |
aliens | +0.018 |
chers | +0.018 |
Sorry | +0.018 |
Neg logit contributions | |
joy | -0.006 |
time | -0.003 |
than | -0.003 |
minutes | -0.003 |
no | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
joy | +0.003 |
looking | +0.001 |
time | +0.001 |
deliber | +0.001 |
than | +0.001 |
Neg logit contributions | |
glers | -0.006 |
aliens | -0.006 |
girls | -0.006 |
chers | -0.006 |
Amen | -0.005 |
Token | One |
Token ID | 1881 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
glers | +0.017 |
Amen | +0.017 |
aliens | +0.016 |
chers | +0.016 |
Sorry | +0.016 |
Neg logit contributions | |
joy | -0.010 |
time | -0.007 |
than | -0.007 |
minutes | -0.006 |
no | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
joy | +0.020 |
than | +0.013 |
blond | +0.012 |
deliber | +0.012 |
drawn | +0.012 |
Neg logit contributions | |
glers | -0.018 |
igators | -0.017 |
floats | -0.017 |
Amen | -0.016 |
aliens | -0.016 |
Token | And |
Token ID | 843 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Amen | +0.000 |
glers | +0.000 |
aliens | +0.000 |
Sorry | +0.000 |
chers | +0.000 |
Neg logit contributions | |
joy | -0.000 |
than | -0.000 |
time | -0.000 |
minutes | -0.000 |
no | -0.000 |
Token | very |
Token ID | 845 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
glers | +0.112 |
chers | +0.104 |
aliens | +0.104 |
Amen | +0.102 |
actresses | +0.100 |
Neg logit contributions | |
joy | -0.087 |
time | -0.072 |
than | -0.070 |
to | -0.065 |
minutes | -0.063 |
Token | wet |
Token ID | 9583 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
glers | +0.095 |
aliens | +0.091 |
Amen | +0.090 |
chers | +0.089 |
girls | +0.088 |
Neg logit contributions | |
joy | -0.055 |
time | -0.042 |
than | -0.040 |
minutes | -0.036 |
no | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
glers | +0.106 |
Amen | +0.103 |
aliens | +0.102 |
chers | +0.101 |
Sorry | +0.100 |
Neg logit contributions | |
joy | -0.047 |
time | -0.032 |
than | -0.030 |
minutes | -0.027 |
no | -0.025 |
Token | Let |
Token ID | 3914 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
glers | +0.055 |
chers | +0.052 |
aliens | +0.050 |
maid | +0.049 |
actresses | +0.048 |
Neg logit contributions | |
joy | -0.025 |
time | -0.019 |
than | -0.016 |
minutes | -0.015 |
because | -0.015 |
Token | 's |
Token ID | 338 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
glers | +0.126 |
Amen | +0.122 |
chers | +0.121 |
actresses | +0.118 |
aliens | +0.117 |
Neg logit contributions | |
time | -0.081 |
joy | -0.070 |
to | -0.065 |
no | -0.057 |
. | -0.056 |
Token | go |
Token ID | 467 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
chers | +0.271 |
glers | +0.262 |
rol | +0.250 |
aliens | +0.248 |
actresses | +0.244 |
Neg logit contributions | |
time | -0.170 |
to | -0.144 |
like | -0.133 |
a | -0.129 |
. | -0.128 |
Token | and |
Token ID | 290 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Sorry | +0.170 |
aliens | +0.169 |
glers | +0.169 |
Amen | +0.165 |
actresses | +0.162 |
Neg logit contributions | |
to | -0.052 |
joy | -0.046 |
time | -0.038 |
but | -0.034 |
and | -0.033 |
Token | have |
Token ID | 423 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
glers | +0.126 |
maid | +0.125 |
chers | +0.124 |
aliens | +0.123 |
ains | +0.121 |
Neg logit contributions | |
to | -0.065 |
joy | -0.055 |
time | -0.055 |
a | -0.053 |
an | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
glers | +0.084 |
Amen | +0.081 |
chers | +0.080 |
aliens | +0.080 |
Sorry | +0.079 |
Neg logit contributions | |
joy | -0.033 |
time | -0.022 |
than | -0.019 |
minutes | -0.018 |
no | -0.017 |
Token | snack |
Token ID | 26906 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
glers | +0.034 |
Amen | +0.033 |
aliens | +0.032 |
chers | +0.032 |
Sorry | +0.032 |
Neg logit contributions | |
joy | -0.028 |
time | -0.022 |
than | -0.021 |
minutes | -0.020 |
no | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
glers | +0.023 |
aliens | +0.022 |
chers | +0.022 |
floats | +0.022 |
Amen | +0.021 |
Neg logit contributions | |
joy | -0.015 |
no | -0.009 |
time | -0.009 |
minutes | -0.009 |
than | -0.009 |
Token | jump |
Token ID | 4391 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
joy | +0.009 |
than | +0.007 |
time | +0.007 |
minutes | +0.007 |
no | +0.006 |
Neg logit contributions | |
glers | -0.010 |
aliens | -0.009 |
Amen | -0.009 |
chers | -0.009 |
floats | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
joy | +0.005 |
time | +0.004 |
than | +0.003 |
minutes | +0.003 |
to | +0.003 |
Neg logit contributions | |
Amen | -0.012 |
glers | -0.012 |
Sorry | -0.012 |
aliens | -0.012 |
chers | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
glers | +0.002 |
aliens | +0.002 |
chers | +0.002 |
Amen | +0.002 |
floats | +0.002 |
Neg logit contributions | |
joy | -0.001 |
time | -0.001 |
than | -0.001 |
minutes | -0.001 |
no | -0.001 |
Token | play |
Token ID | 711 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
glers | +0.037 |
chers | +0.035 |
Amen | +0.035 |
aliens | +0.035 |
maid | +0.034 |
Neg logit contributions | |
joy | -0.031 |
time | -0.025 |
than | -0.024 |
to | -0.023 |
no | -0.022 |
Token | all |
Token ID | 477 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
glers | +0.078 |
aliens | +0.076 |
Amen | +0.075 |
chers | +0.075 |
Sorry | +0.073 |
Neg logit contributions | |
joy | -0.059 |
time | -0.043 |
than | -0.042 |
minutes | -0.040 |
no | -0.039 |
Token | day |
Token ID | 1110 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
glers | +0.291 |
Amen | +0.277 |
aliens | +0.275 |
floats | +0.269 |
igators | +0.267 |
Neg logit contributions | |
joy | -0.153 |
minutes | -0.087 |
time | -0.086 |
than | -0.083 |
no | -0.077 |
Token | long |
Token ID | 890 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
glers | +0.018 |
aliens | +0.017 |
Amen | +0.017 |
chers | +0.017 |
floats | +0.016 |
Neg logit contributions | |
joy | -0.008 |
than | -0.004 |
minutes | -0.004 |
time | -0.004 |
deliber | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
joy | +0.002 |
deliber | +0.001 |
looking | +0.001 |
time | +0.001 |
sight | +0.001 |
Neg logit contributions | |
aliens | -0.004 |
glers | -0.004 |
girls | -0.004 |
chers | -0.004 |
Amen | -0.004 |
Token | One |
Token ID | 1881 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
glers | +0.002 |
Amen | +0.002 |
Sorry | +0.002 |
aliens | +0.002 |
floats | +0.002 |
Neg logit contributions | |
joy | -0.002 |
than | -0.002 |
minutes | -0.002 |
no | -0.002 |
looking | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | +5.90e-03 |
Pos logit contributions | |
joy | +0.021 |
heights | +0.014 |
than | +0.014 |
inspection | +0.014 |
inc | +0.014 |
Neg logit contributions | |
glers | -0.017 |
Amen | -0.017 |
igators | -0.016 |
floats | -0.016 |
aliens | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
glers | +0.043 |
aliens | +0.042 |
chers | +0.041 |
floats | +0.040 |
girls | +0.038 |
Neg logit contributions | |
joy | -0.049 |
time | -0.037 |
no | -0.036 |
than | -0.036 |
looking | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
glers | +0.087 |
aliens | +0.085 |
floats | +0.082 |
Amen | +0.080 |
chers | +0.079 |
Neg logit contributions | |
joy | -0.058 |
than | -0.042 |
time | -0.040 |
no | -0.038 |
minutes | -0.038 |
Token | grass |
Token ID | 8701 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
glers | +0.011 |
floats | +0.011 |
aliens | +0.011 |
Sorry | +0.010 |
docks | +0.010 |
Neg logit contributions | |
joy | -0.013 |
no | -0.010 |
than | -0.010 |
deliber | -0.009 |
minutes | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
joy | +0.008 |
time | +0.006 |
than | +0.005 |
minutes | +0.005 |
no | +0.004 |
Neg logit contributions | |
glers | -0.019 |
Amen | -0.018 |
aliens | -0.018 |
chers | -0.018 |
Sorry | -0.018 |
Token | make |
Token ID | 787 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
chers | +0.043 |
Amen | +0.043 |
glers | +0.042 |
Sorry | +0.041 |
maid | +0.040 |
Neg logit contributions | |
joy | -0.033 |
to | -0.029 |
time | -0.028 |
than | -0.028 |
but | -0.026 |
Token | all |
Token ID | 477 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
glers | +0.104 |
aliens | +0.100 |
chers | +0.098 |
Amen | +0.096 |
floats | +0.096 |
Neg logit contributions | |
joy | -0.083 |
than | -0.061 |
time | -0.061 |
minutes | -0.057 |
no | -0.055 |
Token | sorts |
Token ID | 10524 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
glers | +0.254 |
Amen | +0.250 |
chers | +0.248 |
aliens | +0.245 |
Sorry | +0.241 |
Neg logit contributions | |
joy | -0.175 |
time | -0.138 |
than | -0.131 |
minutes | -0.117 |
no | -0.117 |
Token | of |
Token ID | 286 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
glers | +0.099 |
Amen | +0.097 |
aliens | +0.093 |
Sorry | +0.093 |
chers | +0.093 |
Neg logit contributions | |
joy | -0.092 |
time | -0.074 |
than | -0.073 |
minutes | -0.067 |
no | -0.065 |
Token | creative |
Token ID | 7325 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
aliens | +0.088 |
glers | +0.087 |
floats | +0.085 |
chers | +0.080 |
Amen | +0.080 |
Neg logit contributions | |
joy | -0.064 |
no | -0.042 |
than | -0.041 |
minutes | -0.040 |
time | -0.040 |
Token | things |
Token ID | 1243 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
glers | +0.010 |
aliens | +0.010 |
Amen | +0.010 |
chers | +0.010 |
floats | +0.010 |
Neg logit contributions | |
joy | -0.009 |
time | -0.007 |
than | -0.007 |
minutes | -0.006 |
no | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
glers | +0.035 |
aliens | +0.033 |
chers | +0.033 |
Amen | +0.033 |
Sorry | +0.032 |
Neg logit contributions | |
joy | -0.019 |
time | -0.013 |
than | -0.012 |
minutes | -0.011 |
no | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
glers | +0.014 |
chers | +0.014 |
Amen | +0.013 |
aliens | +0.013 |
Sorry | +0.013 |
Neg logit contributions | |
joy | -0.006 |
time | -0.004 |
than | -0.003 |
to | -0.003 |
no | -0.003 |
Token | park |
Token ID | 3952 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
chers | +0.077 |
Amen | +0.075 |
glers | +0.075 |
hing | +0.073 |
maid | +0.073 |
Neg logit contributions | |
joy | -0.037 |
time | -0.031 |
to | -0.027 |
black | -0.024 |
sight | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
glers | +0.036 |
chers | +0.034 |
Amen | +0.034 |
Sorry | +0.034 |
aliens | +0.034 |
Neg logit contributions | |
joy | -0.018 |
time | -0.012 |
minutes | -0.012 |
blond | -0.011 |
no | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
glers | +0.028 |
Amen | +0.027 |
aliens | +0.027 |
chers | +0.026 |
Sorry | +0.026 |
Neg logit contributions | |
joy | -0.023 |
time | -0.018 |
than | -0.017 |
minutes | -0.016 |
no | -0.016 |
Token | played |
Token ID | 2826 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Amen | +0.093 |
Sorry | +0.089 |
aliens | +0.088 |
glers | +0.088 |
maid | +0.086 |
Neg logit contributions | |
joy | -0.038 |
time | -0.030 |
to | -0.026 |
past | -0.023 |
black | -0.022 |
Token | all |
Token ID | 477 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
glers | +0.113 |
chers | +0.111 |
aliens | +0.110 |
Amen | +0.108 |
girls | +0.106 |
Neg logit contributions | |
joy | -0.105 |
time | -0.077 |
than | -0.076 |
minutes | -0.073 |
no | -0.072 |
Token | day |
Token ID | 1110 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
glers | +0.320 |
Amen | +0.314 |
chers | +0.312 |
aliens | +0.312 |
Sorry | +0.306 |
Neg logit contributions | |
joy | -0.106 |
time | -0.073 |
than | -0.067 |
minutes | -0.054 |
no | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
glers | +0.034 |
chers | +0.033 |
aliens | +0.033 |
Amen | +0.032 |
floats | +0.032 |
Neg logit contributions | |
joy | -0.014 |
time | -0.007 |
than | -0.007 |
minutes | -0.006 |
no | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
glers | +0.019 |
Amen | +0.019 |
aliens | +0.019 |
chers | +0.018 |
Sorry | +0.018 |
Neg logit contributions | |
joy | -0.014 |
time | -0.011 |
than | -0.010 |
minutes | -0.010 |
no | -0.009 |
Token | played |
Token ID | 2826 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Amen | +0.080 |
Sorry | +0.077 |
aliens | +0.072 |
glers | +0.072 |
maid | +0.071 |
Neg logit contributions | |
joy | -0.032 |
time | -0.028 |
to | -0.023 |
but | -0.022 |
thought | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
glers | +0.113 |
aliens | +0.109 |
chers | +0.109 |
Amen | +0.109 |
Sorry | +0.105 |
Neg logit contributions | |
joy | -0.095 |
time | -0.071 |
than | -0.069 |
minutes | -0.065 |
no | -0.064 |
Token | your |
Token ID | 534 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
glers | +0.071 |
Amen | +0.068 |
aliens | +0.068 |
chers | +0.068 |
Sorry | +0.066 |
Neg logit contributions | |
joy | -0.086 |
time | -0.062 |
than | -0.061 |
looking | -0.060 |
minutes | -0.059 |
Token | room |
Token ID | 2119 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
glers | +0.018 |
Amen | +0.017 |
aliens | +0.017 |
chers | +0.017 |
Sorry | +0.017 |
Neg logit contributions | |
joy | -0.023 |
than | -0.018 |
time | -0.018 |
no | -0.018 |
minutes | -0.017 |
Token | now |
Token ID | 783 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
joy | +0.012 |
time | +0.009 |
than | +0.009 |
no | +0.009 |
looking | +0.009 |
Neg logit contributions | |
glers | -0.011 |
Amen | -0.010 |
chers | -0.010 |
Sorry | -0.010 |
aliens | -0.010 |
Token | ? |
Token ID | 30 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
joy | +0.015 |
time | +0.012 |
than | +0.012 |
minutes | +0.011 |
no | +0.011 |
Neg logit contributions | |
glers | -0.010 |
Amen | -0.009 |
aliens | -0.009 |
chers | -0.009 |
Sorry | -0.009 |
Token | Put |
Token ID | 5930 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
joy | +0.001 |
time | +0.001 |
than | +0.001 |
minutes | +0.001 |
no | +0.001 |
Neg logit contributions | |
glers | -0.001 |
aliens | -0.001 |
chers | -0.001 |
Amen | -0.001 |
maid | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
glers | +0.046 |
Amen | +0.045 |
chers | +0.045 |
Sorry | +0.044 |
floats | +0.044 |
Neg logit contributions | |
joy | -0.049 |
than | -0.037 |
time | -0.034 |
minutes | -0.033 |
looking | -0.033 |
Token | your |
Token ID | 534 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
glers | +0.250 |
Amen | +0.243 |
aliens | +0.242 |
chers | +0.241 |
girls | +0.235 |
Neg logit contributions | |
joy | -0.175 |
time | -0.145 |
than | -0.134 |
minutes | -0.126 |
no | -0.123 |
Token | toys |
Token ID | 14958 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
glers | +0.031 |
Amen | +0.029 |
aliens | +0.029 |
chers | +0.029 |
Sorry | +0.028 |
Neg logit contributions | |
joy | -0.048 |
than | -0.039 |
time | -0.038 |
no | -0.037 |
minutes | -0.036 |
Token | away |
Token ID | 1497 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
glers | +0.086 |
Amen | +0.082 |
aliens | +0.082 |
chers | +0.081 |
Sorry | +0.080 |
Neg logit contributions | |
joy | -0.068 |
time | -0.052 |
than | -0.050 |
minutes | -0.047 |
no | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
glers | +0.119 |
Amen | +0.116 |
chers | +0.113 |
aliens | +0.113 |
Sorry | +0.112 |
Neg logit contributions | |
joy | -0.091 |
time | -0.075 |
than | -0.074 |
minutes | -0.066 |
to | -0.065 |
Token | make |
Token ID | 787 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
glers | +0.030 |
chers | +0.028 |
aliens | +0.028 |
maid | +0.027 |
Amen | +0.027 |
Neg logit contributions | |
joy | -0.021 |
time | -0.020 |
than | -0.019 |
to | -0.018 |
minutes | -0.017 |
Token | special |
Token ID | 2041 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
glers | +0.138 |
Amen | +0.134 |
chers | +0.134 |
aliens | +0.133 |
girls | +0.129 |
Neg logit contributions | |
joy | -0.076 |
time | -0.059 |
than | -0.053 |
minutes | -0.048 |
to | -0.047 |
Token | medicine |
Token ID | 9007 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
glers | +0.074 |
Amen | +0.071 |
aliens | +0.070 |
chers | +0.068 |
Sorry | +0.068 |
Neg logit contributions | |
joy | -0.069 |
time | -0.052 |
than | -0.051 |
minutes | -0.049 |
no | -0.048 |
Token | that |
Token ID | 326 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
glers | +0.127 |
aliens | +0.121 |
chers | +0.121 |
girls | +0.117 |
Amen | +0.117 |
Neg logit contributions | |
joy | -0.068 |
time | -0.040 |
minutes | -0.038 |
no | -0.035 |
than | -0.035 |
Token | would |
Token ID | 561 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
glers | +0.082 |
Sorry | +0.076 |
aliens | +0.076 |
floats | +0.073 |
chers | +0.073 |
Neg logit contributions | |
joy | -0.095 |
than | -0.068 |
minutes | -0.066 |
time | -0.066 |
no | -0.063 |
Token | help |
Token ID | 1037 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
glers | +0.065 |
chers | +0.064 |
Amen | +0.063 |
aliens | +0.063 |
girls | +0.061 |
Neg logit contributions | |
joy | -0.055 |
time | -0.050 |
than | -0.047 |
no | -0.044 |
to | -0.043 |
Token | all |
Token ID | 477 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
glers | +0.145 |
aliens | +0.138 |
Amen | +0.138 |
chers | +0.136 |
Sorry | +0.135 |
Neg logit contributions | |
joy | -0.120 |
time | -0.088 |
than | -0.086 |
minutes | -0.083 |
no | -0.078 |
Token | of |
Token ID | 286 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
glers | +0.257 |
Amen | +0.253 |
chers | +0.252 |
aliens | +0.250 |
Sorry | +0.243 |
Neg logit contributions | |
joy | -0.166 |
time | -0.134 |
than | -0.126 |
no | -0.113 |
minutes | -0.112 |
Token | the |
Token ID | 262 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
glers | +0.137 |
aliens | +0.133 |
Amen | +0.129 |
chers | +0.127 |
Sorry | +0.126 |
Neg logit contributions | |
joy | -0.098 |
than | -0.068 |
time | -0.065 |
minutes | -0.064 |
no | -0.060 |
Token | animals |
Token ID | 4695 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
joy | +0.004 |
time | +0.003 |
than | +0.003 |
minutes | +0.003 |
no | +0.003 |
Neg logit contributions | |
glers | -0.003 |
aliens | -0.003 |
Amen | -0.003 |
chers | -0.003 |
Sorry | -0.003 |
Token | feel |
Token ID | 1254 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
glers | +0.080 |
Amen | +0.078 |
aliens | +0.077 |
chers | +0.076 |
Sorry | +0.076 |
Neg logit contributions | |
joy | -0.035 |
time | -0.025 |
than | -0.024 |
minutes | -0.020 |
no | -0.019 |
Token | better |
Token ID | 1365 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
glers | +0.027 |
Amen | +0.026 |
aliens | +0.026 |
chers | +0.025 |
Sorry | +0.025 |
Neg logit contributions | |
joy | -0.029 |
time | -0.022 |
than | -0.021 |
minutes | -0.021 |
no | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
Amen | +0.024 |
glers | +0.023 |
aliens | +0.023 |
chers | +0.022 |
girls | +0.022 |
Neg logit contributions | |
joy | -0.011 |
time | -0.006 |
minutes | -0.006 |
deliber | -0.005 |
no | -0.005 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
joy | +0.003 |
than | +0.002 |
time | +0.002 |
minutes | +0.002 |
no | +0.002 |
Neg logit contributions | |
Amen | -0.002 |
glers | -0.002 |
aliens | -0.002 |
Sorry | -0.002 |
floats | -0.002 |
Token | loved |
Token ID | 6151 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
Amen | +0.023 |
glers | +0.023 |
aliens | +0.022 |
floats | +0.021 |
Sorry | +0.021 |
Neg logit contributions | |
joy | -0.033 |
minutes | -0.024 |
no | -0.024 |
time | -0.024 |
deliber | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
joy | +0.002 |
minutes | +0.001 |
than | +0.001 |
time | +0.001 |
-- | +0.001 |
Neg logit contributions | |
aliens | -0.004 |
glers | -0.004 |
girls | -0.004 |
Amen | -0.004 |
floats | -0.004 |
Token | play |
Token ID | 711 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
glers | +0.007 |
Amen | +0.006 |
aliens | +0.006 |
chers | +0.006 |
Sorry | +0.006 |
Neg logit contributions | |
joy | -0.009 |
time | -0.007 |
than | -0.007 |
minutes | -0.007 |
no | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
glers | +0.065 |
aliens | +0.064 |
Amen | +0.063 |
chers | +0.063 |
Sorry | +0.061 |
Neg logit contributions | |
joy | -0.048 |
than | -0.032 |
time | -0.032 |
minutes | -0.031 |
no | -0.029 |
Token | day |
Token ID | 1110 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
glers | +0.286 |
aliens | +0.268 |
Amen | +0.267 |
igators | +0.266 |
floats | +0.262 |
Neg logit contributions | |
joy | -0.163 |
minutes | -0.091 |
time | -0.088 |
than | -0.086 |
no | -0.081 |
Token | with |
Token ID | 351 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
glers | +0.011 |
aliens | +0.010 |
chers | +0.010 |
Amen | +0.010 |
floats | +0.010 |
Neg logit contributions | |
joy | -0.005 |
than | -0.002 |
minutes | -0.002 |
deliber | -0.002 |
time | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
glers | +0.039 |
aliens | +0.038 |
Amen | +0.038 |
Sorry | +0.037 |
chers | +0.037 |
Neg logit contributions | |
joy | -0.026 |
than | -0.018 |
time | -0.017 |
minutes | -0.016 |
looking | -0.016 |
Token | ball |
Token ID | 2613 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
joy | +0.019 |
time | +0.015 |
than | +0.015 |
minutes | +0.014 |
no | +0.014 |
Neg logit contributions | |
glers | -0.014 |
aliens | -0.014 |
Amen | -0.013 |
chers | -0.013 |
Sorry | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
glers | +0.035 |
aliens | +0.034 |
Amen | +0.033 |
chers | +0.033 |
Sorry | +0.033 |
Neg logit contributions | |
joy | -0.013 |
time | -0.007 |
than | -0.006 |
minutes | -0.006 |
no | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
glers | +0.033 |
Sorry | +0.031 |
Amen | +0.031 |
girls | +0.030 |
aliens | +0.030 |
Neg logit contributions | |
joy | -0.015 |
time | -0.013 |
to | -0.012 |
minutes | -0.011 |
than | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
glers | +0.051 |
Amen | +0.050 |
aliens | +0.050 |
chers | +0.049 |
Sorry | +0.049 |
Neg logit contributions | |
joy | -0.023 |
time | -0.015 |
than | -0.014 |
minutes | -0.013 |
no | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
joy | +0.034 |
time | +0.028 |
than | +0.027 |
seen | +0.026 |
no | +0.025 |
Neg logit contributions | |
Amen | -0.039 |
aliens | -0.037 |
chers | -0.036 |
Sorry | -0.035 |
actresses | -0.035 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
joy | +0.020 |
time | +0.016 |
than | +0.015 |
minutes | +0.015 |
yet | +0.014 |
Neg logit contributions | |
glers | -0.018 |
Amen | -0.018 |
aliens | -0.017 |
chers | -0.017 |
Sorry | -0.017 |
Token | 's |
Token ID | 338 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
glers | +0.093 |
Amen | +0.089 |
chers | +0.086 |
aliens | +0.086 |
actresses | +0.084 |
Neg logit contributions | |
joy | -0.070 |
time | -0.067 |
to | -0.057 |
than | -0.054 |
no | -0.053 |
Token | all |
Token ID | 477 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
chers | +0.209 |
glers | +0.208 |
rol | +0.193 |
aliens | +0.193 |
Amen | +0.192 |
Neg logit contributions | |
time | -0.132 |
like | -0.110 |
to | -0.109 |
because | -0.106 |
joy | -0.103 |
Token | help |
Token ID | 1037 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
chers | +0.244 |
Amen | +0.242 |
glers | +0.236 |
girls | +0.232 |
aliens | +0.231 |
Neg logit contributions | |
time | -0.168 |
joy | -0.164 |
to | -0.143 |
than | -0.136 |
past | -0.131 |
Token | Max |
Token ID | 5436 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
glers | +0.165 |
Amen | +0.161 |
rol | +0.152 |
maid | +0.150 |
chers | +0.149 |
Neg logit contributions | |
to | -0.073 |
joy | -0.073 |
time | -0.070 |
than | -0.066 |
no | -0.062 |
Token | feel |
Token ID | 1254 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
glers | +0.162 |
Amen | +0.157 |
aliens | +0.156 |
Sorry | +0.153 |
chers | +0.152 |
Neg logit contributions | |
joy | -0.075 |
time | -0.056 |
than | -0.054 |
to | -0.047 |
minutes | -0.044 |
Token | better |
Token ID | 1365 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
glers | +0.059 |
Amen | +0.055 |
chers | +0.055 |
girls | +0.054 |
actresses | +0.053 |
Neg logit contributions | |
joy | -0.061 |
time | -0.055 |
than | -0.050 |
to | -0.048 |
minutes | -0.047 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
glers | +0.130 |
Amen | +0.125 |
aliens | +0.124 |
chers | +0.123 |
Sorry | +0.121 |
Neg logit contributions | |
joy | -0.107 |
time | -0.083 |
than | -0.079 |
minutes | -0.075 |
no | -0.073 |
Token | 's |
Token ID | 338 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
glers | +0.042 |
Amen | +0.040 |
Sorry | +0.040 |
aliens | +0.039 |
chers | +0.039 |
Neg logit contributions | |
joy | -0.059 |
than | -0.045 |
minutes | -0.044 |
time | -0.044 |
no | -0.043 |
Token | amazing |
Token ID | 4998 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
Sorry | +0.054 |
glers | +0.053 |
aliens | +0.052 |
Amen | +0.052 |
floats | +0.051 |
Neg logit contributions | |
joy | -0.047 |
no | -0.031 |
looking | -0.031 |
deliber | -0.030 |
minutes | -0.029 |
Token | ! |
Token ID | 0 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
joy | +0.029 |
than | +0.021 |
minutes | +0.020 |
no | +0.020 |
dream | +0.020 |
Neg logit contributions | |
glers | -0.030 |
Sorry | -0.030 |
Amen | -0.029 |
floats | -0.029 |
maid | -0.028 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
joy | +0.012 |
time | +0.009 |
than | +0.008 |
minutes | +0.007 |
-- | +0.007 |
Neg logit contributions | |
glers | -0.019 |
aliens | -0.018 |
chers | -0.018 |
Amen | -0.018 |
girls | -0.017 |
Token | 's |
Token ID | 338 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
glers | +0.064 |
Amen | +0.060 |
aliens | +0.060 |
chers | +0.059 |
Sorry | +0.058 |
Neg logit contributions | |
joy | -0.081 |
time | -0.066 |
than | -0.065 |
minutes | -0.062 |
no | -0.061 |
Token | all |
Token ID | 477 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
glers | +0.170 |
chers | +0.169 |
aliens | +0.163 |
Amen | +0.156 |
girls | +0.155 |
Neg logit contributions | |
time | -0.132 |
joy | -0.129 |
to | -0.112 |
than | -0.110 |
because | -0.106 |
Token | applaud |
Token ID | 22517 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
glers | +0.214 |
chers | +0.214 |
aliens | +0.212 |
girls | +0.207 |
Amen | +0.207 |
Neg logit contributions | |
joy | -0.198 |
time | -0.187 |
than | -0.165 |
to | -0.157 |
no | -0.155 |
Token | you |
Token ID | 345 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
glers | +0.052 |
Amen | +0.050 |
aliens | +0.050 |
chers | +0.049 |
Sorry | +0.049 |
Neg logit contributions | |
joy | -0.042 |
time | -0.032 |
than | -0.031 |
minutes | -0.029 |
no | -0.028 |
Token | for |
Token ID | 329 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
joy | +0.023 |
time | +0.018 |
than | +0.017 |
minutes | +0.016 |
no | +0.016 |
Neg logit contributions | |
glers | -0.026 |
Amen | -0.025 |
aliens | -0.025 |
chers | -0.024 |
Sorry | -0.024 |
Token | your |
Token ID | 534 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
joy | +0.013 |
than | +0.010 |
time | +0.009 |
looking | +0.009 |
minutes | +0.008 |
Neg logit contributions | |
Amen | -0.018 |
aliens | -0.018 |
glers | -0.017 |
Sorry | -0.017 |
actresses | -0.017 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
joy | +0.041 |
than | +0.031 |
looking | +0.030 |
time | +0.029 |
minutes | +0.029 |
Neg logit contributions | |
glers | -0.042 |
Sorry | -0.042 |
aliens | -0.041 |
Amen | -0.041 |
chers | -0.041 |
Token | on |
Token ID | 319 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
joy | +0.027 |
deliber | +0.021 |
time | +0.020 |
no | +0.020 |
looking | +0.020 |
Neg logit contributions | |
aliens | -0.028 |
glers | -0.027 |
maid | -0.026 |
chers | -0.025 |
Amen | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
aliens | +0.022 |
glers | +0.022 |
Amen | +0.021 |
floats | +0.021 |
Sorry | +0.021 |
Neg logit contributions | |
joy | -0.015 |
looking | -0.010 |
than | -0.009 |
time | -0.009 |
deliber | -0.009 |
Token | Jill |
Token ID | 22772 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
glers | +0.034 |
aliens | +0.033 |
Amen | +0.033 |
chers | +0.033 |
Sorry | +0.032 |
Neg logit contributions | |
joy | -0.021 |
time | -0.015 |
than | -0.014 |
minutes | -0.013 |
no | -0.013 |
Token | ! |
Token ID | 0 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
joy | +0.018 |
time | +0.013 |
than | +0.013 |
minutes | +0.012 |
no | +0.012 |
Neg logit contributions | |
glers | -0.025 |
Amen | -0.024 |
chers | -0.024 |
aliens | -0.024 |
Sorry | -0.023 |
Token | Let |
Token ID | 3914 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
glers | +0.032 |
aliens | +0.030 |
chers | +0.030 |
Amen | +0.030 |
Sorry | +0.029 |
Neg logit contributions | |
joy | -0.020 |
time | -0.015 |
than | -0.014 |
minutes | -0.013 |
no | -0.012 |
Token | 's |
Token ID | 338 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
glers | +0.102 |
Amen | +0.098 |
aliens | +0.097 |
chers | +0.096 |
Sorry | +0.093 |
Neg logit contributions | |
joy | -0.112 |
time | -0.095 |
than | -0.089 |
minutes | -0.085 |
no | -0.084 |
Token | go |
Token ID | 467 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
glers | +0.236 |
chers | +0.236 |
aliens | +0.224 |
Amen | +0.222 |
rol | +0.216 |
Neg logit contributions | |
time | -0.170 |
to | -0.153 |
joy | -0.139 |
an | -0.138 |
like | -0.136 |
Token | fly |
Token ID | 6129 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
glers | +0.134 |
aliens | +0.133 |
Sorry | +0.132 |
Amen | +0.131 |
actresses | +0.126 |
Neg logit contributions | |
joy | -0.072 |
time | -0.056 |
to | -0.055 |
than | -0.053 |
but | -0.047 |
Token | together |
Token ID | 1978 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
glers | +0.029 |
Amen | +0.028 |
aliens | +0.027 |
chers | +0.027 |
Sorry | +0.027 |
Neg logit contributions | |
joy | -0.020 |
time | -0.016 |
than | -0.015 |
minutes | -0.014 |
no | -0.014 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
glers | +0.126 |
Amen | +0.122 |
aliens | +0.120 |
chers | +0.119 |
Sorry | +0.118 |
Neg logit contributions | |
joy | -0.087 |
time | -0.067 |
than | -0.065 |
minutes | -0.059 |
no | -0.057 |
Token | She |
Token ID | 1375 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
joy | +0.016 |
time | +0.012 |
than | +0.012 |
minutes | +0.011 |
looking | +0.010 |
Neg logit contributions | |
glers | -0.026 |
Amen | -0.025 |
Sorry | -0.025 |
aliens | -0.025 |
chers | -0.024 |
Token | bird |
Token ID | 6512 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
glers | +0.003 |
girls | +0.003 |
chers | +0.003 |
ishly | +0.003 |
rol | +0.003 |
Neg logit contributions | |
joy | -0.003 |
time | -0.003 |
minutes | -0.002 |
than | -0.002 |
black | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
glers | +0.036 |
Amen | +0.035 |
aliens | +0.034 |
chers | +0.034 |
Sorry | +0.034 |
Neg logit contributions | |
joy | -0.023 |
time | -0.017 |
than | -0.016 |
minutes | -0.015 |
no | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
glers | +0.034 |
chers | +0.033 |
Amen | +0.032 |
Sorry | +0.031 |
girls | +0.031 |
Neg logit contributions | |
joy | -0.013 |
time | -0.009 |
than | -0.008 |
to | -0.007 |
minutes | -0.007 |
Token | dragon |
Token ID | 10441 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
joy | +0.007 |
time | +0.007 |
black | +0.006 |
sight | +0.006 |
long | +0.006 |
Neg logit contributions | |
glers | -0.008 |
chers | -0.007 |
girls | -0.007 |
rol | -0.007 |
ishly | -0.007 |
Token | played |
Token ID | 2826 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Amen | +0.028 |
glers | +0.028 |
Sorry | +0.027 |
chers | +0.025 |
actresses | +0.025 |
Neg logit contributions | |
joy | -0.023 |
time | -0.020 |
than | -0.019 |
to | -0.018 |
minutes | -0.017 |
Token | all |
Token ID | 477 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
glers | +0.083 |
aliens | +0.080 |
Amen | +0.079 |
chers | +0.079 |
Sorry | +0.076 |
Neg logit contributions | |
joy | -0.102 |
time | -0.081 |
than | -0.079 |
minutes | -0.076 |
no | -0.076 |
Token | day |
Token ID | 1110 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
glers | +0.325 |
chers | +0.320 |
Amen | +0.319 |
aliens | +0.314 |
Sorry | +0.312 |
Neg logit contributions | |
joy | -0.093 |
time | -0.069 |
than | -0.062 |
minutes | -0.046 |
no | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
glers | +0.023 |
aliens | +0.022 |
Amen | +0.022 |
chers | +0.022 |
girls | +0.022 |
Neg logit contributions | |
joy | -0.008 |
time | -0.004 |
than | -0.004 |
no | -0.004 |
minutes | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
glers | +0.009 |
Amen | +0.009 |
chers | +0.009 |
aliens | +0.009 |
Sorry | +0.009 |
Neg logit contributions | |
joy | -0.012 |
time | -0.010 |
than | -0.010 |
minutes | -0.009 |
no | -0.009 |
Token | made |
Token ID | 925 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Amen | +0.062 |
Sorry | +0.061 |
glers | +0.058 |
arse | +0.057 |
maid | +0.056 |
Neg logit contributions | |
joy | -0.032 |
time | -0.031 |
to | -0.027 |
than | -0.025 |
because | -0.025 |
Token | people |
Token ID | 661 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
glers | +0.091 |
Amen | +0.089 |
chers | +0.086 |
Sorry | +0.085 |
aliens | +0.085 |
Neg logit contributions | |
joy | -0.055 |
time | -0.042 |
than | -0.038 |
minutes | -0.036 |
no | -0.035 |
Token | loved |
Token ID | 6151 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
glers | +0.112 |
Amen | +0.109 |
chers | +0.108 |
girls | +0.107 |
Sorry | +0.106 |
Neg logit contributions | |
joy | -0.074 |
time | -0.063 |
than | -0.061 |
to | -0.054 |
minutes | -0.051 |
Token | to |
Token ID | 284 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
joy | +0.002 |
minutes | +0.001 |
-- | +0.001 |
time | +0.001 |
looking | +0.001 |
Neg logit contributions | |
aliens | -0.005 |
glers | -0.005 |
actresses | -0.005 |
girls | -0.005 |
floats | -0.005 |
Token | serve |
Token ID | 4691 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
glers | +0.002 |
chers | +0.002 |
Amen | +0.002 |
aliens | +0.002 |
Sorry | +0.001 |
Neg logit contributions | |
joy | -0.002 |
time | -0.002 |
than | -0.002 |
no | -0.001 |
to | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
glers | +0.070 |
Amen | +0.068 |
aliens | +0.067 |
chers | +0.066 |
Sorry | +0.065 |
Neg logit contributions | |
joy | -0.062 |
time | -0.049 |
than | -0.047 |
minutes | -0.044 |
no | -0.043 |
Token | help |
Token ID | 1037 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
chers | +0.037 |
glers | +0.037 |
maid | +0.035 |
rol | +0.035 |
arse | +0.035 |
Neg logit contributions | |
joy | -0.023 |
time | -0.022 |
to | -0.022 |
than | -0.018 |
long | -0.018 |
Token | all |
Token ID | 477 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
glers | +0.096 |
Amen | +0.095 |
chers | +0.093 |
aliens | +0.088 |
Sorry | +0.088 |
Neg logit contributions | |
joy | -0.110 |
time | -0.100 |
than | -0.095 |
to | -0.088 |
no | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
glers | +0.284 |
chers | +0.282 |
Amen | +0.280 |
aliens | +0.274 |
Sorry | +0.271 |
Neg logit contributions | |
joy | -0.133 |
time | -0.107 |
than | -0.097 |
minutes | -0.083 |
no | -0.083 |
Token | animals |
Token ID | 4695 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
glers | +0.016 |
Amen | +0.015 |
chers | +0.015 |
ishly | +0.015 |
girls | +0.015 |
Neg logit contributions | |
joy | -0.012 |
time | -0.011 |
than | -0.009 |
minutes | -0.008 |
long | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
glers | +0.091 |
Amen | +0.090 |
aliens | +0.088 |
Sorry | +0.087 |
chers | +0.086 |
Neg logit contributions | |
joy | -0.033 |
time | -0.025 |
than | -0.024 |
to | -0.020 |
minutes | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
glers | +0.040 |
aliens | +0.039 |
Amen | +0.039 |
chers | +0.037 |
Sorry | +0.037 |
Neg logit contributions | |
joy | -0.024 |
than | -0.016 |
time | -0.015 |
minutes | -0.015 |
no | -0.015 |
Token | forest |
Token ID | 8222 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
joy | +0.020 |
time | +0.016 |
than | +0.015 |
minutes | +0.014 |
no | +0.013 |
Neg logit contributions | |
glers | -0.024 |
Amen | -0.023 |
chers | -0.023 |
aliens | -0.023 |
Sorry | -0.022 |
Token | lucky |
Token ID | 9670 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
glers | +0.027 |
Amen | +0.025 |
Sorry | +0.025 |
aliens | +0.025 |
chers | +0.024 |
Neg logit contributions | |
joy | -0.021 |
than | -0.016 |
minutes | -0.015 |
time | -0.015 |
no | -0.015 |
Token | pie |
Token ID | 2508 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
glers | +0.023 |
Sorry | +0.022 |
floats | +0.022 |
Amen | +0.021 |
maid | +0.021 |
Neg logit contributions | |
joy | -0.033 |
no | -0.027 |
minutes | -0.027 |
deliber | -0.026 |
Re | -0.026 |
Token | ! |
Token ID | 0 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
joy | +0.012 |
time | +0.008 |
than | +0.008 |
minutes | +0.007 |
no | +0.007 |
Neg logit contributions | |
glers | -0.021 |
Amen | -0.020 |
aliens | -0.020 |
chers | -0.020 |
Sorry | -0.020 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
glers | +0.029 |
chers | +0.026 |
aliens | +0.026 |
ics | +0.025 |
maid | +0.025 |
Neg logit contributions | |
joy | -0.018 |
time | -0.014 |
But | -0.013 |
than | -0.013 |
to | -0.013 |
Token | 's |
Token ID | 338 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
glers | +0.088 |
Amen | +0.085 |
aliens | +0.084 |
chers | +0.082 |
actresses | +0.082 |
Neg logit contributions | |
time | -0.063 |
joy | -0.062 |
to | -0.050 |
no | -0.048 |
than | -0.048 |
Token | all |
Token ID | 477 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
chers | +0.180 |
glers | +0.173 |
aliens | +0.170 |
actresses | +0.165 |
Amen | +0.160 |
Neg logit contributions | |
time | -0.143 |
joy | -0.122 |
to | -0.121 |
like | -0.118 |
than | -0.116 |
Token | eat |
Token ID | 4483 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
chers | +0.228 |
aliens | +0.225 |
Amen | +0.221 |
girls | +0.221 |
glers | +0.220 |
Neg logit contributions | |
time | -0.179 |
joy | -0.178 |
to | -0.155 |
than | -0.152 |
past | -0.145 |
Token | it |
Token ID | 340 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
glers | +0.025 |
Amen | +0.024 |
aliens | +0.024 |
chers | +0.024 |
Sorry | +0.024 |
Neg logit contributions | |
joy | -0.019 |
time | -0.013 |
than | -0.013 |
minutes | -0.012 |
no | -0.012 |
Token | together |
Token ID | 1978 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
glers | +0.031 |
Amen | +0.031 |
aliens | +0.030 |
Sorry | +0.029 |
chers | +0.029 |
Neg logit contributions | |
joy | -0.032 |
time | -0.028 |
than | -0.027 |
minutes | -0.025 |
to | -0.025 |
Token | !" |
Token ID | 2474 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
glers | +0.049 |
Amen | +0.046 |
aliens | +0.046 |
chers | +0.046 |
Sorry | +0.044 |
Neg logit contributions | |
joy | -0.058 |
time | -0.047 |
than | -0.045 |
minutes | -0.043 |
no | -0.043 |
Token | Max |
Token ID | 5436 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
joy | +0.035 |
time | +0.026 |
than | +0.025 |
minutes | +0.025 |
no | +0.023 |
Neg logit contributions | |
glers | -0.041 |
Sorry | -0.040 |
girls | -0.039 |
floats | -0.039 |
aliens | -0.038 |
Token | my |
Token ID | 1820 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
joy | +0.033 |
than | +0.024 |
minutes | +0.024 |
no | +0.024 |
time | +0.024 |
Neg logit contributions | |
glers | -0.025 |
chers | -0.023 |
Amen | -0.022 |
girls | -0.021 |
aliens | -0.021 |
Token | had |
Token ID | 550 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
joy | +0.056 |
minutes | +0.041 |
time | +0.041 |
than | +0.040 |
no | +0.040 |
Neg logit contributions | |
glers | -0.048 |
chers | -0.046 |
girls | -0.043 |
aliens | -0.042 |
ishly | -0.041 |
Token | told |
Token ID | 1297 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
joy | +0.066 |
than | +0.050 |
minutes | +0.046 |
looking | +0.045 |
no | +0.045 |
Neg logit contributions | |
chers | -0.062 |
glers | -0.059 |
aliens | -0.057 |
ics | -0.054 |
married | -0.052 |
Token | him |
Token ID | 683 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
glers | +0.001 |
aliens | +0.001 |
hing | +0.001 |
chers | +0.001 |
ics | +0.001 |
Neg logit contributions | |
joy | -0.002 |
minutes | -0.001 |
than | -0.001 |
looking | -0.001 |
blond | -0.001 |
Token | long |
Token ID | 890 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
joy | +0.057 |
minutes | +0.033 |
time | +0.032 |
than | +0.031 |
no | +0.030 |
Neg logit contributions | |
glers | -0.119 |
aliens | -0.116 |
chers | -0.115 |
Sorry | -0.110 |
Amen | -0.110 |
Token | ago |
Token ID | 2084 |
Feature activation | -7.58e+00 |
Pos logit contributions | |
joy | +0.106 |
than | +0.075 |
no | +0.073 |
looking | +0.073 |
minutes | +0.071 |
Neg logit contributions | |
aliens | -0.120 |
glers | -0.119 |
floats | -0.111 |
girls | -0.110 |
chers | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
joy | +0.221 |
minutes | +0.128 |
deliber | +0.126 |
looking | +0.123 |
no | +0.120 |
Neg logit contributions | |
glers | -0.394 |
chers | -0.381 |
aliens | -0.372 |
ics | -0.372 |
girls | -0.365 |
Token | The |
Token ID | 383 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
joy | +0.010 |
than | +0.008 |
time | +0.008 |
minutes | +0.007 |
no | +0.007 |
Neg logit contributions | |
glers | -0.011 |
Amen | -0.011 |
Sorry | -0.011 |
aliens | -0.010 |
girls | -0.010 |
Token | bird |
Token ID | 6512 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
joy | +0.012 |
time | +0.009 |
than | +0.009 |
minutes | +0.008 |
no | +0.008 |
Neg logit contributions | |
glers | -0.013 |
aliens | -0.012 |
Amen | -0.012 |
chers | -0.012 |
Sorry | -0.012 |
Token | spread |
Token ID | 4104 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
glers | +0.026 |
Amen | +0.025 |
aliens | +0.025 |
chers | +0.025 |
Sorry | +0.025 |
Neg logit contributions | |
joy | -0.022 |
time | -0.018 |
than | -0.017 |
minutes | -0.016 |
no | -0.016 |
Token | out |
Token ID | 503 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
glers | +0.019 |
aliens | +0.019 |
chers | +0.018 |
hing | +0.018 |
Amen | +0.018 |
Neg logit contributions | |
joy | -0.018 |
than | -0.013 |
time | -0.012 |
minutes | -0.012 |
deliber | -0.012 |
Token | born |
Token ID | 4642 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
joy | +0.016 |
than | +0.012 |
looking | +0.011 |
no | +0.011 |
deliber | +0.010 |
Neg logit contributions | |
aliens | -0.019 |
Amen | -0.019 |
glers | -0.019 |
chers | -0.018 |
igators | -0.018 |
Token | only |
Token ID | 691 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
joy | +0.057 |
minutes | +0.041 |
deliber | +0.040 |
looking | +0.040 |
no | +0.039 |
Neg logit contributions | |
glers | -0.090 |
aliens | -0.089 |
chers | -0.085 |
ishly | -0.082 |
floats | -0.081 |
Token | a |
Token ID | 257 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
joy | +0.040 |
looking | +0.030 |
no | +0.029 |
deliber | +0.028 |
Tom | +0.027 |
Neg logit contributions | |
aliens | -0.061 |
glers | -0.058 |
chers | -0.056 |
igators | -0.056 |
ishly | -0.056 |
Token | few |
Token ID | 1178 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
joy | +0.025 |
than | +0.019 |
time | +0.018 |
deliber | +0.018 |
no | +0.018 |
Neg logit contributions | |
glers | -0.031 |
aliens | -0.031 |
Amen | -0.031 |
chers | -0.030 |
Sorry | -0.030 |
Token | days |
Token ID | 1528 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
joy | +0.070 |
no | +0.047 |
looking | +0.046 |
deliber | +0.045 |
than | +0.045 |
Neg logit contributions | |
aliens | -0.104 |
glers | -0.099 |
igators | -0.096 |
floats | -0.095 |
chers | -0.095 |
Token | ago |
Token ID | 2084 |
Feature activation | -7.34e+00 |
Pos logit contributions | |
joy | +0.053 |
time | +0.037 |
than | +0.035 |
minutes | +0.034 |
no | +0.034 |
Neg logit contributions | |
glers | -0.090 |
chers | -0.085 |
aliens | -0.083 |
girls | -0.080 |
floats | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
joy | +0.211 |
minutes | +0.136 |
time | +0.134 |
looking | +0.133 |
deliber | +0.129 |
Neg logit contributions | |
glers | -0.377 |
chers | -0.363 |
aliens | -0.361 |
Amen | -0.349 |
girls | -0.347 |
Token | The |
Token ID | 383 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
joy | +0.010 |
than | +0.008 |
time | +0.008 |
minutes | +0.007 |
no | +0.007 |
Neg logit contributions | |
Amen | -0.015 |
glers | -0.015 |
aliens | -0.015 |
Sorry | -0.015 |
chers | -0.015 |
Token | deer |
Token ID | 20096 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
joy | +0.012 |
than | +0.009 |
time | +0.009 |
minutes | +0.009 |
no | +0.009 |
Neg logit contributions | |
glers | -0.013 |
aliens | -0.012 |
Amen | -0.012 |
chers | -0.012 |
Sorry | -0.012 |
Token | felt |
Token ID | 2936 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
glers | +0.060 |
Amen | +0.058 |
aliens | +0.057 |
chers | +0.057 |
Sorry | +0.056 |
Neg logit contributions | |
joy | -0.049 |
time | -0.038 |
than | -0.037 |
minutes | -0.034 |
no | -0.034 |
Token | sorry |
Token ID | 7926 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
joy | +0.003 |
than | +0.002 |
minutes | +0.002 |
time | +0.002 |
no | +0.002 |
Neg logit contributions | |
Amen | -0.004 |
aliens | -0.004 |
glers | -0.004 |
chers | -0.004 |
Sorry | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
glers | +0.034 |
Amen | +0.032 |
aliens | +0.032 |
chers | +0.032 |
Sorry | +0.032 |
Neg logit contributions | |
joy | -0.019 |
time | -0.014 |
than | -0.013 |
minutes | -0.012 |
no | -0.012 |
Token | ship |
Token ID | 4074 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
glers | +0.016 |
Amen | +0.015 |
aliens | +0.015 |
chers | +0.015 |
Sorry | +0.015 |
Neg logit contributions | |
joy | -0.015 |
time | -0.012 |
than | -0.012 |
minutes | -0.011 |
no | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
glers | +0.020 |
aliens | +0.019 |
chers | +0.019 |
Amen | +0.019 |
Sorry | +0.018 |
Neg logit contributions | |
joy | -0.018 |
time | -0.014 |
than | -0.013 |
minutes | -0.013 |
no | -0.012 |
Token | wrecked |
Token ID | 44770 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
joy | +0.067 |
than | +0.045 |
time | +0.045 |
minutes | +0.043 |
no | +0.042 |
Neg logit contributions | |
aliens | -0.094 |
glers | -0.093 |
chers | -0.090 |
floats | -0.087 |
Amen | -0.087 |
Token | long |
Token ID | 890 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
joy | +0.007 |
time | +0.005 |
deliber | +0.005 |
no | +0.005 |
than | +0.005 |
Neg logit contributions | |
aliens | -0.008 |
glers | -0.008 |
chers | -0.007 |
floats | -0.007 |
Amen | -0.007 |
Token | ago |
Token ID | 2084 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
joy | +0.093 |
no | +0.067 |
deliber | +0.063 |
looking | +0.063 |
than | +0.061 |
Neg logit contributions | |
aliens | -0.116 |
glers | -0.111 |
floats | -0.109 |
Amen | -0.106 |
chers | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
joy | +0.212 |
deliber | +0.129 |
minutes | +0.125 |
no | +0.123 |
looking | +0.122 |
Neg logit contributions | |
glers | -0.374 |
chers | -0.360 |
aliens | -0.357 |
ics | -0.354 |
girls | -0.345 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
joy | +0.018 |
time | +0.011 |
no | +0.010 |
minutes | +0.010 |
looking | +0.009 |
Neg logit contributions | |
glers | -0.038 |
aliens | -0.038 |
Amen | -0.036 |
floats | -0.036 |
chers | -0.036 |
Token | now |
Token ID | 783 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
joy | +0.026 |
time | +0.020 |
than | +0.019 |
to | +0.018 |
minutes | +0.017 |
Neg logit contributions | |
glers | -0.057 |
chers | -0.054 |
Amen | -0.053 |
maid | -0.053 |
girls | -0.053 |
Token | it |
Token ID | 340 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
joy | +0.046 |
time | +0.034 |
than | +0.032 |
minutes | +0.029 |
no | +0.027 |
Neg logit contributions | |
glers | -0.092 |
Amen | -0.088 |
chers | -0.087 |
aliens | -0.086 |
girls | -0.085 |
Token | was |
Token ID | 373 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
joy | +0.010 |
time | +0.009 |
than | +0.008 |
to | +0.008 |
minutes | +0.008 |
Neg logit contributions | |
Amen | -0.017 |
glers | -0.017 |
Sorry | -0.016 |
actresses | -0.016 |
aliens | -0.016 |
Token | filled |
Token ID | 5901 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
joy | +0.024 |
time | +0.017 |
no | +0.016 |
deliber | +0.016 |
orm | +0.016 |
Neg logit contributions | |
glers | -0.028 |
floats | -0.025 |
aliens | -0.024 |
chers | -0.024 |
Amen | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
glers | +0.068 |
Amen | +0.064 |
aliens | +0.064 |
chers | +0.062 |
Sorry | +0.062 |
Neg logit contributions | |
joy | -0.046 |
time | -0.031 |
minutes | -0.030 |
than | -0.029 |
deliber | -0.027 |
Token | treasures |
Token ID | 29561 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
glers | +0.022 |
Amen | +0.021 |
chers | +0.021 |
Sorry | +0.021 |
girls | +0.020 |
Neg logit contributions | |
joy | -0.015 |
time | -0.012 |
than | -0.011 |
minutes | -0.010 |
no | -0.010 |
Token | from |
Token ID | 422 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
glers | +0.001 |
aliens | +0.001 |
chers | +0.001 |
Amen | +0.001 |
girls | +0.001 |
Neg logit contributions | |
joy | -0.000 |
time | -0.000 |
than | -0.000 |
minutes | -0.000 |
no | -0.000 |
Token | long |
Token ID | 890 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
glers | +0.110 |
aliens | +0.108 |
Amen | +0.107 |
chers | +0.104 |
Sorry | +0.102 |
Neg logit contributions | |
joy | -0.065 |
time | -0.046 |
than | -0.043 |
minutes | -0.041 |
no | -0.039 |
Token | ago |
Token ID | 2084 |
Feature activation | -7.02e+00 |
Pos logit contributions | |
joy | +0.079 |
no | +0.057 |
time | +0.055 |
than | +0.054 |
looking | +0.054 |
Neg logit contributions | |
aliens | -0.102 |
glers | -0.099 |
floats | -0.095 |
chers | -0.094 |
girls | -0.093 |
Token | ! |
Token ID | 0 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
joy | +0.202 |
deliber | +0.134 |
no | +0.131 |
looking | +0.129 |
minutes | +0.120 |
Neg logit contributions | |
glers | -0.350 |
chers | -0.341 |
aliens | -0.339 |
ics | -0.338 |
girls | -0.333 |
Token |
|
Token ID | 198 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
joy | +0.021 |
time | +0.015 |
than | +0.014 |
minutes | +0.014 |
no | +0.013 |
Neg logit contributions | |
glers | -0.032 |
Amen | -0.031 |
chers | -0.030 |
aliens | -0.030 |
Sorry | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
joy | +0.007 |
time | +0.005 |
than | +0.004 |
minutes | +0.004 |
no | +0.004 |
Neg logit contributions | |
glers | -0.016 |
Amen | -0.016 |
aliens | -0.016 |
chers | -0.016 |
Sorry | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
joy | +0.006 |
time | +0.005 |
than | +0.004 |
minutes | +0.004 |
no | +0.004 |
Neg logit contributions | |
glers | -0.009 |
Amen | -0.009 |
aliens | -0.009 |
chers | -0.009 |
Sorry | -0.009 |
Token | adventurers |
Token ID | 36843 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
joy | +0.010 |
time | +0.009 |
minutes | +0.007 |
adventurous | +0.007 |
long | +0.006 |
Neg logit contributions | |
glers | -0.021 |
Sorry | -0.021 |
rol | -0.021 |
maid | -0.020 |
girls | -0.020 |
Token | coins |
Token ID | 10796 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
glers | +0.046 |
aliens | +0.044 |
Amen | +0.044 |
chers | +0.043 |
Sorry | +0.042 |
Neg logit contributions | |
joy | -0.034 |
time | -0.026 |
than | -0.025 |
minutes | -0.023 |
no | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
joy | +0.013 |
time | +0.008 |
minutes | +0.008 |
no | +0.008 |
deliber | +0.007 |
Neg logit contributions | |
glers | -0.026 |
chers | -0.025 |
aliens | -0.024 |
girls | -0.023 |
maid | -0.023 |
Token | people |
Token ID | 661 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
Amen | +0.050 |
glers | +0.048 |
chers | +0.047 |
aliens | +0.046 |
Sorry | +0.046 |
Neg logit contributions | |
joy | -0.043 |
time | -0.036 |
than | -0.035 |
minutes | -0.032 |
to | -0.031 |
Token | used |
Token ID | 973 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
glers | +0.033 |
Amen | +0.032 |
aliens | +0.032 |
chers | +0.031 |
Sorry | +0.031 |
Neg logit contributions | |
joy | -0.030 |
time | -0.024 |
than | -0.024 |
minutes | -0.022 |
no | -0.021 |
Token | long |
Token ID | 890 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
joy | +0.006 |
deliber | +0.004 |
minutes | +0.004 |
no | +0.004 |
looking | +0.004 |
Neg logit contributions | |
aliens | -0.006 |
glers | -0.006 |
chers | -0.005 |
girls | -0.005 |
floats | -0.005 |
Token | ago |
Token ID | 2084 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
joy | +0.122 |
no | +0.091 |
deliber | +0.086 |
looking | +0.085 |
Re | +0.078 |
Neg logit contributions | |
aliens | -0.122 |
glers | -0.115 |
floats | -0.114 |
girls | -0.111 |
chers | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
joy | +0.205 |
deliber | +0.125 |
no | +0.117 |
looking | +0.114 |
minutes | +0.112 |
Neg logit contributions | |
glers | -0.370 |
chers | -0.358 |
aliens | -0.357 |
girls | -0.350 |
ics | -0.343 |
Token | They |
Token ID | 1119 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
joy | +0.005 |
than | +0.004 |
time | +0.004 |
minutes | +0.004 |
no | +0.004 |
Neg logit contributions | |
glers | -0.006 |
Sorry | -0.006 |
Amen | -0.006 |
floats | -0.006 |
aliens | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Amen | +0.035 |
chers | +0.034 |
glers | +0.034 |
Sorry | +0.034 |
aliens | +0.033 |
Neg logit contributions | |
joy | -0.030 |
time | -0.024 |
than | -0.024 |
to | -0.022 |
but | -0.022 |
Token | paintings |
Token ID | 21641 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
joy | +0.048 |
time | +0.037 |
than | +0.036 |
minutes | +0.034 |
no | +0.033 |
Neg logit contributions | |
glers | -0.057 |
aliens | -0.055 |
chers | -0.053 |
Amen | -0.053 |
floats | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
joy | +0.032 |
time | +0.020 |
minutes | +0.019 |
no | +0.019 |
than | +0.018 |
Neg logit contributions | |
glers | -0.057 |
aliens | -0.053 |
chers | -0.052 |
floats | -0.051 |
girls | -0.050 |
Token | how |
Token ID | 703 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
joy | +0.009 |
time | +0.007 |
than | +0.006 |
minutes | +0.006 |
to | +0.006 |
Neg logit contributions | |
glers | -0.013 |
Amen | -0.012 |
chers | -0.012 |
aliens | -0.012 |
Sorry | -0.012 |
Token | they |
Token ID | 484 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
glers | +0.033 |
aliens | +0.032 |
chers | +0.031 |
Amen | +0.031 |
Sorry | +0.031 |
Neg logit contributions | |
joy | -0.022 |
time | -0.016 |
than | -0.015 |
minutes | -0.015 |
no | -0.014 |
Token | were |
Token ID | 547 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Amen | +0.082 |
glers | +0.081 |
Sorry | +0.079 |
chers | +0.077 |
aliens | +0.077 |
Neg logit contributions | |
joy | -0.060 |
time | -0.050 |
than | -0.049 |
minutes | -0.044 |
to | -0.043 |
Token | used |
Token ID | 973 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
glers | +0.071 |
chers | +0.068 |
aliens | +0.067 |
girls | +0.065 |
actresses | +0.064 |
Neg logit contributions | |
joy | -0.058 |
time | -0.043 |
no | -0.040 |
minutes | -0.040 |
than | -0.039 |
Token | long |
Token ID | 890 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
glers | +0.008 |
aliens | +0.008 |
chers | +0.008 |
girls | +0.007 |
igators | +0.007 |
Neg logit contributions | |
joy | -0.004 |
looking | -0.002 |
deliber | -0.002 |
no | -0.002 |
minutes | -0.002 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
joy | +0.109 |
no | +0.092 |
looking | +0.089 |
deliber | +0.084 |
Re | +0.083 |
Neg logit contributions | |
aliens | -0.088 |
floats | -0.084 |
glers | -0.079 |
ports | -0.073 |
girls | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
joy | +0.182 |
deliber | +0.103 |
time | +0.102 |
no | +0.101 |
looking | +0.101 |
Neg logit contributions | |
glers | -0.378 |
chers | -0.369 |
aliens | -0.367 |
girls | -0.355 |
Amen | -0.354 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
joy | +0.012 |
than | +0.010 |
time | +0.009 |
no | +0.009 |
minutes | +0.009 |
Neg logit contributions | |
glers | -0.015 |
Amen | -0.014 |
Sorry | -0.014 |
aliens | -0.014 |
chers | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
joy | +0.012 |
time | +0.010 |
than | +0.009 |
minutes | +0.009 |
no | +0.008 |
Neg logit contributions | |
glers | -0.015 |
Amen | -0.015 |
aliens | -0.015 |
chers | -0.015 |
Sorry | -0.014 |
Token | fascinated |
Token ID | 30103 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
joy | +0.008 |
time | +0.006 |
than | +0.006 |
looking | +0.006 |
no | +0.006 |
Neg logit contributions | |
glers | -0.009 |
Amen | -0.009 |
chers | -0.009 |
aliens | -0.009 |
actresses | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
aster | +0.050 |
joy | +0.049 |
taco | +0.043 |
cavity | +0.043 |
Ble | +0.043 |
Neg logit contributions | |
glers | -0.043 |
aliens | -0.040 |
maid | -0.036 |
floats | -0.034 |
ie | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
aliens | +0.034 |
glers | +0.031 |
floats | +0.031 |
maid | +0.030 |
remote | +0.030 |
Neg logit contributions | |
joy | -0.027 |
deliber | -0.021 |
looking | -0.020 |
no | -0.019 |
time | -0.019 |
Token | scale |
Token ID | 5046 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
joy | +0.051 |
than | +0.040 |
no | +0.039 |
deliber | +0.039 |
-- | +0.039 |
Neg logit contributions | |
aliens | -0.039 |
remote | -0.039 |
glers | -0.038 |
Amen | -0.037 |
chers | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
joy | +0.059 |
time | +0.036 |
deliber | +0.035 |
minutes | +0.034 |
no | +0.034 |
Neg logit contributions | |
glers | -0.105 |
chers | -0.100 |
aliens | -0.099 |
girls | -0.096 |
Amen | -0.094 |
Token | long |
Token ID | 890 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
joy | +0.011 |
than | +0.008 |
time | +0.008 |
no | +0.008 |
minutes | +0.008 |
Neg logit contributions | |
Amen | -0.014 |
glers | -0.014 |
aliens | -0.014 |
Sorry | -0.013 |
chers | -0.013 |
Token | time |
Token ID | 640 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
joy | +0.061 |
looking | +0.044 |
no | +0.043 |
Re | +0.039 |
deliber | +0.036 |
Neg logit contributions | |
Amen | -0.135 |
aliens | -0.131 |
remote | -0.128 |
spaceship | -0.127 |
maid | -0.123 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
joy | +0.087 |
looking | +0.066 |
no | +0.064 |
Re | +0.062 |
S | +0.062 |
Neg logit contributions | |
glers | -0.139 |
aliens | -0.137 |
chers | -0.135 |
girls | -0.133 |
docks | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
joy | +0.198 |
deliber | +0.126 |
looking | +0.124 |
no | +0.119 |
minutes | +0.119 |
Neg logit contributions | |
glers | -0.345 |
chers | -0.330 |
aliens | -0.327 |
ics | -0.324 |
girls | -0.319 |
Token |
|
Token ID | 198 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
joy | +0.027 |
than | +0.021 |
minutes | +0.021 |
time | +0.020 |
no | +0.019 |
Neg logit contributions | |
Sorry | -0.030 |
Amen | -0.030 |
glers | -0.029 |
girls | -0.028 |
aliens | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
joy | +0.017 |
than | +0.013 |
minutes | +0.012 |
time | +0.011 |
blond | +0.011 |
Neg logit contributions | |
Amen | -0.020 |
glers | -0.020 |
chers | -0.019 |
aliens | -0.019 |
girls | -0.018 |
Token | As |
Token ID | 1722 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
joy | +0.017 |
than | +0.012 |
time | +0.012 |
minutes | +0.012 |
sight | +0.011 |
Neg logit contributions | |
glers | -0.018 |
Amen | -0.017 |
chers | -0.016 |
Sorry | -0.016 |
aliens | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
joy | +0.005 |
than | +0.004 |
looking | +0.003 |
minutes | +0.003 |
blond | +0.003 |
Neg logit contributions | |
glers | -0.005 |
aliens | -0.004 |
Sorry | -0.004 |
floats | -0.004 |
Amen | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
glers | +0.016 |
aliens | +0.015 |
igators | +0.015 |
chers | +0.015 |
floats | +0.015 |
Neg logit contributions | |
joy | -0.015 |
no | -0.009 |
deliber | -0.009 |
blond | -0.009 |
minutes | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
joy | +0.025 |
time | +0.018 |
minutes | +0.018 |
no | +0.018 |
sight | +0.018 |
Neg logit contributions | |
chers | -0.019 |
glers | -0.019 |
aliens | -0.017 |
Amen | -0.017 |
girls | -0.016 |
Token | seen |
Token ID | 1775 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
joy | +0.059 |
deliber | +0.039 |
minutes | +0.037 |
sight | +0.036 |
looking | +0.036 |
Neg logit contributions | |
chers | -0.068 |
glers | -0.064 |
aliens | -0.063 |
married | -0.061 |
actresses | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
joy | +0.084 |
deliber | +0.057 |
minutes | +0.055 |
looking | +0.051 |
no | +0.050 |
Neg logit contributions | |
glers | -0.137 |
aliens | -0.134 |
chers | -0.130 |
girls | -0.124 |
Amen | -0.124 |
Token | year |
Token ID | 614 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
glers | +0.023 |
Amen | +0.021 |
chers | +0.021 |
aliens | +0.021 |
girls | +0.021 |
Neg logit contributions | |
joy | -0.023 |
time | -0.019 |
than | -0.018 |
minutes | -0.017 |
no | -0.017 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
joy | +0.047 |
no | +0.028 |
time | +0.028 |
deliber | +0.027 |
minutes | +0.027 |
Neg logit contributions | |
glers | -0.078 |
aliens | -0.074 |
chers | -0.073 |
docks | -0.072 |
Amen | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
joy | +0.192 |
deliber | +0.117 |
looking | +0.114 |
minutes | +0.114 |
time | +0.110 |
Neg logit contributions | |
glers | -0.353 |
chers | -0.340 |
aliens | -0.334 |
ics | -0.333 |
Amen | -0.330 |
Token | He |
Token ID | 679 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
joy | +0.020 |
than | +0.017 |
time | +0.016 |
minutes | +0.015 |
no | +0.015 |
Neg logit contributions | |
Amen | -0.026 |
Sorry | -0.025 |
glers | -0.025 |
aliens | -0.024 |
girls | -0.024 |
Token | went |
Token ID | 1816 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
joy | +0.018 |
time | +0.014 |
than | +0.014 |
no | +0.013 |
minutes | +0.013 |
Neg logit contributions | |
glers | -0.019 |
aliens | -0.018 |
Amen | -0.018 |
chers | -0.018 |
Sorry | -0.017 |
Token | home |
Token ID | 1363 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
glers | +0.023 |
chers | +0.022 |
Amen | +0.022 |
aliens | +0.022 |
actresses | +0.021 |
Neg logit contributions | |
joy | -0.013 |
time | -0.010 |
than | -0.010 |
minutes | -0.009 |
no | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
glers | +0.039 |
chers | +0.039 |
Amen | +0.038 |
actresses | +0.038 |
aliens | +0.037 |
Neg logit contributions | |
joy | -0.021 |
time | -0.016 |
orm | -0.014 |
minutes | -0.014 |
looking | -0.014 |
Token | our |
Token ID | 674 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
aliens | +0.090 |
glers | +0.088 |
Amen | +0.085 |
girls | +0.083 |
chers | +0.083 |
Neg logit contributions | |
joy | -0.063 |
than | -0.048 |
minutes | -0.045 |
looking | -0.045 |
-- | -0.045 |
Token | country |
Token ID | 1499 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
aliens | +0.021 |
glers | +0.021 |
chers | +0.020 |
Sorry | +0.020 |
floats | +0.020 |
Neg logit contributions | |
joy | -0.023 |
than | -0.019 |
looking | -0.019 |
time | -0.018 |
no | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
joy | +0.019 |
time | +0.012 |
than | +0.011 |
minutes | +0.011 |
no | +0.010 |
Neg logit contributions | |
glers | -0.045 |
aliens | -0.043 |
chers | -0.043 |
Amen | -0.043 |
Sorry | -0.042 |
Token | long |
Token ID | 890 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
glers | +0.016 |
Amen | +0.015 |
aliens | +0.015 |
chers | +0.015 |
Sorry | +0.015 |
Neg logit contributions | |
joy | -0.011 |
time | -0.008 |
than | -0.008 |
minutes | -0.007 |
no | -0.007 |
Token | time |
Token ID | 640 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
joy | +0.060 |
no | +0.038 |
looking | +0.036 |
than | +0.035 |
deliber | +0.035 |
Neg logit contributions | |
aliens | -0.106 |
Amen | -0.106 |
glers | -0.106 |
floats | -0.101 |
chers | -0.100 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
joy | +0.072 |
looking | +0.046 |
no | +0.046 |
time | +0.045 |
deliber | +0.043 |
Neg logit contributions | |
glers | -0.145 |
aliens | -0.143 |
chers | -0.142 |
Amen | -0.137 |
girls | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
joy | +0.183 |
time | +0.109 |
minutes | +0.108 |
looking | +0.105 |
no | +0.104 |
Neg logit contributions | |
glers | -0.371 |
chers | -0.357 |
aliens | -0.355 |
Amen | -0.350 |
girls | -0.345 |
Token | He |
Token ID | 679 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
joy | +0.008 |
time | +0.006 |
than | +0.005 |
minutes | +0.005 |
no | +0.005 |
Neg logit contributions | |
glers | -0.014 |
Amen | -0.013 |
aliens | -0.013 |
chers | -0.013 |
Sorry | -0.013 |
Token | helped |
Token ID | 4193 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
joy | +0.015 |
time | +0.011 |
than | +0.011 |
minutes | +0.010 |
no | +0.010 |
Neg logit contributions | |
glers | -0.018 |
Amen | -0.018 |
aliens | -0.018 |
chers | -0.017 |
Sorry | -0.017 |
Token | many |
Token ID | 867 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
glers | +0.093 |
aliens | +0.090 |
chers | +0.087 |
Amen | +0.087 |
actresses | +0.085 |
Neg logit contributions | |
joy | -0.080 |
than | -0.058 |
time | -0.058 |
minutes | -0.057 |
no | -0.052 |
Token | people |
Token ID | 661 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
glers | +0.051 |
aliens | +0.050 |
chers | +0.048 |
Amen | +0.047 |
floats | +0.046 |
Neg logit contributions | |
joy | -0.053 |
time | -0.040 |
than | -0.040 |
no | -0.038 |
looking | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
joy | +0.048 |
time | +0.033 |
looking | +0.032 |
no | +0.031 |
than | +0.031 |
Neg logit contributions | |
glers | -0.084 |
aliens | -0.082 |
Sorry | -0.080 |
chers | -0.080 |
floats | -0.080 |
Token | twenty |
Token ID | 8208 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
joy | +0.038 |
time | +0.030 |
than | +0.029 |
minutes | +0.027 |
no | +0.026 |
Neg logit contributions | |
glers | -0.044 |
Amen | -0.042 |
aliens | -0.042 |
chers | -0.041 |
Sorry | -0.041 |
Token | - |
Token ID | 12 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
joy | +0.193 |
nowhere | +0.128 |
dream | +0.127 |
looking | +0.125 |
seen | +0.119 |
Neg logit contributions | |
glers | -0.225 |
maid | -0.217 |
floats | -0.213 |
chers | -0.211 |
aliens | -0.207 |
Token | seven |
Token ID | 26548 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
joy | +0.173 |
time | +0.147 |
than | +0.131 |
but | +0.129 |
sight | +0.129 |
Neg logit contributions | |
glers | -0.107 |
chers | -0.106 |
Amen | -0.099 |
Sorry | -0.096 |
floats | -0.096 |
Token | , |
Token ID | 11 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
joy | +0.142 |
looking | +0.109 |
no | +0.107 |
deliber | +0.099 |
dream | +0.093 |
Neg logit contributions | |
glers | -0.152 |
aliens | -0.148 |
floats | -0.146 |
maid | -0.140 |
sisters | -0.137 |
Token | twenty |
Token ID | 8208 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
joy | +0.135 |
looking | +0.114 |
time | +0.110 |
than | +0.110 |
seen | +0.109 |
Neg logit contributions | |
Amen | -0.107 |
aliens | -0.107 |
Sorry | -0.104 |
glers | -0.103 |
floats | -0.101 |
Token | - |
Token ID | 12 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
joy | +0.271 |
dream | +0.176 |
nowhere | +0.175 |
sight | +0.166 |
seen | +0.165 |
Neg logit contributions | |
glers | -0.286 |
maid | -0.276 |
chers | -0.275 |
floats | -0.271 |
aliens | -0.262 |
Token | eight |
Token ID | 26022 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
joy | +0.238 |
time | +0.189 |
sight | +0.176 |
thinking | +0.170 |
but | +0.168 |
Neg logit contributions | |
glers | -0.133 |
Amen | -0.131 |
chers | -0.129 |
igators | -0.125 |
floats | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
joy | +0.193 |
looking | +0.144 |
time | +0.133 |
dream | +0.132 |
no | +0.130 |
Neg logit contributions | |
glers | -0.228 |
aliens | -0.217 |
girls | -0.213 |
chers | -0.212 |
maid | -0.209 |
Token | twenty |
Token ID | 8208 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
joy | +0.118 |
looking | +0.096 |
time | +0.096 |
than | +0.092 |
seen | +0.092 |
Neg logit contributions | |
Amen | -0.091 |
aliens | -0.090 |
glers | -0.087 |
Sorry | -0.087 |
floats | -0.085 |
Token | - |
Token ID | 12 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
joy | +0.256 |
nowhere | +0.178 |
dream | +0.171 |
looking | +0.166 |
seen | +0.164 |
Neg logit contributions | |
glers | -0.268 |
maid | -0.260 |
chers | -0.254 |
floats | -0.252 |
aliens | -0.245 |
Token | by |
Token ID | 416 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
glers | +0.049 |
Amen | +0.048 |
aliens | +0.047 |
chers | +0.046 |
Sorry | +0.046 |
Neg logit contributions | |
joy | -0.037 |
time | -0.028 |
than | -0.027 |
minutes | -0.025 |
no | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
aliens | +0.006 |
glers | +0.005 |
actresses | +0.005 |
floats | +0.005 |
Amen | +0.005 |
Neg logit contributions | |
joy | -0.005 |
deliber | -0.004 |
minutes | -0.004 |
looking | -0.004 |
time | -0.004 |
Token | famous |
Token ID | 5863 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
glers | +0.049 |
chers | +0.047 |
Amen | +0.047 |
aliens | +0.046 |
girls | +0.045 |
Neg logit contributions | |
joy | -0.032 |
time | -0.025 |
than | -0.023 |
minutes | -0.021 |
no | -0.020 |
Token | artist |
Token ID | 6802 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
aliens | +0.014 |
Sorry | +0.013 |
glers | +0.013 |
Amen | +0.013 |
floats | +0.013 |
Neg logit contributions | |
joy | -0.017 |
minutes | -0.013 |
no | -0.013 |
time | -0.013 |
deliber | -0.013 |
Token | long |
Token ID | 890 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
joy | +0.003 |
time | +0.002 |
than | +0.001 |
minutes | +0.001 |
no | +0.001 |
Neg logit contributions | |
glers | -0.007 |
aliens | -0.007 |
Amen | -0.007 |
chers | -0.007 |
Sorry | -0.007 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
joy | +0.059 |
looking | +0.037 |
deliber | +0.037 |
no | +0.036 |
minutes | +0.036 |
Neg logit contributions | |
aliens | -0.083 |
glers | -0.080 |
Amen | -0.079 |
floats | -0.078 |
Sorry | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
joy | +0.202 |
deliber | +0.128 |
looking | +0.125 |
no | +0.123 |
minutes | +0.116 |
Neg logit contributions | |
glers | -0.335 |
aliens | -0.327 |
chers | -0.326 |
ics | -0.326 |
girls | -0.319 |
Token | |
Token ID | 220 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
joy | +0.005 |
time | +0.003 |
than | +0.003 |
minutes | +0.003 |
no | +0.003 |
Neg logit contributions | |
glers | -0.010 |
Amen | -0.010 |
aliens | -0.010 |
Sorry | -0.010 |
chers | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
glers | +0.073 |
Amen | +0.071 |
aliens | +0.071 |
chers | +0.070 |
Sorry | +0.069 |
Neg logit contributions | |
joy | -0.035 |
time | -0.022 |
than | -0.022 |
minutes | -0.020 |
no | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e-03 |
Pos logit contributions | |
joy | +0.002 |
than | +0.001 |
minutes | +0.001 |
time | +0.001 |
no | +0.001 |
Neg logit contributions | |
Amen | -0.003 |
glers | -0.003 |
aliens | -0.003 |
chers | -0.003 |
Sorry | -0.003 |
Token | One |
Token ID | 3198 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
joy | +0.000 |
than | +0.000 |
minutes | +0.000 |
time | +0.000 |
yet | +0.000 |
Neg logit contributions | |
glers | -0.000 |
Amen | -0.000 |
aliens | -0.000 |
igators | -0.000 |
floats | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
joy | +0.003 |
time | +0.002 |
than | +0.002 |
minutes | +0.002 |
no | +0.001 |
Neg logit contributions | |
glers | -0.006 |
Amen | -0.006 |
aliens | -0.006 |
chers | -0.006 |
Sorry | -0.006 |
Token | died |
Token ID | 3724 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
glers | +0.029 |
aliens | +0.028 |
Amen | +0.028 |
chers | +0.027 |
Sorry | +0.027 |
Neg logit contributions | |
joy | -0.030 |
time | -0.023 |
than | -0.022 |
minutes | -0.021 |
no | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
glers | +0.062 |
aliens | +0.061 |
Amen | +0.060 |
chers | +0.060 |
Sorry | +0.059 |
Neg logit contributions | |
joy | -0.029 |
time | -0.019 |
minutes | -0.017 |
than | -0.017 |
no | -0.016 |
Token | long |
Token ID | 890 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
glers | +0.007 |
Amen | +0.007 |
aliens | +0.007 |
chers | +0.006 |
Sorry | +0.006 |
Neg logit contributions | |
joy | -0.005 |
than | -0.004 |
time | -0.004 |
no | -0.004 |
minutes | -0.003 |
Token | time |
Token ID | 640 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
joy | +0.067 |
no | +0.045 |
deliber | +0.043 |
looking | +0.041 |
than | +0.040 |
Neg logit contributions | |
Amen | -0.113 |
aliens | -0.112 |
glers | -0.107 |
remote | -0.104 |
maid | -0.103 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.77e+00 |
Pos logit contributions | |
joy | +0.074 |
no | +0.047 |
time | +0.045 |
looking | +0.045 |
deliber | +0.043 |
Neg logit contributions | |
aliens | -0.145 |
glers | -0.144 |
chers | -0.143 |
Amen | -0.143 |
girls | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
joy | +0.185 |
time | +0.106 |
looking | +0.105 |
minutes | +0.104 |
deliber | +0.104 |
Neg logit contributions | |
glers | -0.360 |
chers | -0.350 |
Amen | -0.347 |
aliens | -0.347 |
girls | -0.338 |
Token | It |
Token ID | 632 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
glers | +0.002 |
Amen | +0.002 |
aliens | +0.002 |
Sorry | +0.002 |
chers | +0.002 |
Neg logit contributions | |
joy | -0.001 |
time | -0.001 |
than | -0.001 |
minutes | -0.001 |
no | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
joy | +0.007 |
time | +0.006 |
than | +0.006 |
minutes | +0.005 |
to | +0.005 |
Neg logit contributions | |
glers | -0.012 |
Amen | -0.011 |
Sorry | -0.011 |
aliens | -0.011 |
chers | -0.011 |
Token | not |
Token ID | 407 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
joy | +0.006 |
than | +0.004 |
time | +0.004 |
looking | +0.004 |
minutes | +0.004 |
Neg logit contributions | |
Amen | -0.009 |
glers | -0.009 |
aliens | -0.009 |
chers | -0.009 |
Sorry | -0.009 |
Token | alive |
Token ID | 6776 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
joy | +0.045 |
time | +0.029 |
no | +0.028 |
than | +0.028 |
minutes | +0.027 |
Neg logit contributions | |
aliens | -0.071 |
glers | -0.070 |
Amen | -0.069 |
chers | -0.068 |
Sorry | -0.066 |
Token | found |
Token ID | 1043 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
joy | +0.039 |
than | +0.027 |
minutes | +0.025 |
time | +0.025 |
looking | +0.025 |
Neg logit contributions | |
aliens | -0.060 |
glers | -0.059 |
chers | -0.058 |
actresses | -0.056 |
floats | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
joy | +0.046 |
deliber | +0.030 |
minutes | +0.030 |
time | +0.030 |
than | +0.030 |
Neg logit contributions | |
aliens | -0.078 |
glers | -0.076 |
chers | -0.074 |
Amen | -0.070 |
girls | -0.070 |
Token | truck |
Token ID | 7779 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
joy | +0.018 |
minutes | +0.013 |
than | +0.013 |
deliber | +0.012 |
no | +0.012 |
Neg logit contributions | |
aliens | -0.022 |
glers | -0.022 |
Amen | -0.021 |
remote | -0.020 |
floats | -0.020 |
Token | many |
Token ID | 867 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
glers | +0.007 |
chers | +0.006 |
aliens | +0.006 |
Amen | +0.006 |
Sorry | +0.006 |
Neg logit contributions | |
joy | -0.004 |
time | -0.003 |
minutes | -0.003 |
than | -0.002 |
no | -0.002 |
Token | years |
Token ID | 812 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
joy | +0.009 |
no | +0.006 |
deliber | +0.006 |
time | +0.006 |
than | +0.006 |
Neg logit contributions | |
glers | -0.012 |
aliens | -0.012 |
floats | -0.011 |
igators | -0.011 |
chers | -0.011 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
joy | +0.072 |
no | +0.050 |
deliber | +0.042 |
time | +0.042 |
Re | +0.038 |
Neg logit contributions | |
glers | -0.136 |
aliens | -0.133 |
floats | -0.126 |
docks | -0.125 |
chers | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
joy | +0.189 |
minutes | +0.115 |
deliber | +0.113 |
no | +0.111 |
looking | +0.110 |
Neg logit contributions | |
glers | -0.349 |
chers | -0.336 |
aliens | -0.330 |
ics | -0.327 |
Amen | -0.325 |
Token | worked |
Token ID | 3111 |
Feature activation | +5.27e-03 |
Pos logit contributions | |
joy | +0.024 |
time | +0.017 |
than | +0.017 |
minutes | +0.016 |
no | +0.015 |
Neg logit contributions | |
glers | -0.036 |
aliens | -0.035 |
Amen | -0.034 |
chers | -0.034 |
Sorry | -0.034 |
Token | hard |
Token ID | 1327 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
glers | +0.000 |
chers | +0.000 |
aliens | +0.000 |
off | +0.000 |
hips | +0.000 |
Neg logit contributions | |
joy | -0.000 |
looking | -0.000 |
deliber | -0.000 |
blond | -0.000 |
minutes | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
joy | +0.020 |
S | +0.016 |
Re | +0.015 |
Tom | +0.015 |
orm | +0.014 |
Neg logit contributions | |
glers | -0.031 |
aliens | -0.030 |
chers | -0.029 |
off | -0.029 |
ports | -0.028 |
Token | fix |
Token ID | 4259 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
joy | +0.026 |
time | +0.022 |
than | +0.021 |
minutes | +0.020 |
no | +0.019 |
Neg logit contributions | |
glers | -0.025 |
Amen | -0.024 |
aliens | -0.024 |
chers | -0.024 |
Sorry | -0.023 |
Token | queen |
Token ID | 16599 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
joy | +0.037 |
no | +0.036 |
looking | +0.032 |
deliber | +0.032 |
Re | +0.032 |
Neg logit contributions | |
aliens | -0.023 |
Amen | -0.021 |
maid | -0.020 |
actresses | -0.019 |
glers | -0.018 |
Token | from |
Token ID | 422 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
joy | +0.020 |
time | +0.013 |
no | +0.011 |
minutes | +0.011 |
than | +0.010 |
Neg logit contributions | |
glers | -0.046 |
aliens | -0.046 |
Amen | -0.046 |
chers | -0.045 |
girls | -0.044 |
Token | long |
Token ID | 890 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
aliens | +0.043 |
Amen | +0.042 |
glers | +0.042 |
actresses | +0.039 |
chers | +0.039 |
Neg logit contributions | |
joy | -0.031 |
than | -0.022 |
time | -0.022 |
-- | -0.021 |
looking | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
joy | +0.086 |
looking | +0.073 |
no | +0.070 |
than | +0.065 |
-- | +0.065 |
Neg logit contributions | |
aliens | -0.118 |
Amen | -0.110 |
glers | -0.105 |
remote | -0.103 |
actresses | -0.103 |
Token | long |
Token ID | 890 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
joy | +0.033 |
no | +0.029 |
looking | +0.027 |
time | +0.027 |
-- | +0.025 |
Neg logit contributions | |
aliens | -0.047 |
Amen | -0.046 |
astronauts | -0.044 |
floats | -0.043 |
actresses | -0.043 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
joy | +0.080 |
no | +0.069 |
looking | +0.068 |
Re | +0.063 |
deliber | +0.062 |
Neg logit contributions | |
aliens | -0.095 |
Amen | -0.086 |
actresses | -0.083 |
remote | -0.083 |
glers | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
joy | +0.198 |
looking | +0.139 |
deliber | +0.135 |
no | +0.132 |
peculiar | +0.126 |
Neg logit contributions | |
glers | -0.314 |
chers | -0.312 |
ics | -0.311 |
aliens | -0.308 |
Amen | -0.304 |
Token | Mia |
Token ID | 32189 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
joy | +0.008 |
than | +0.006 |
time | +0.006 |
no | +0.006 |
looking | +0.006 |
Neg logit contributions | |
glers | -0.010 |
aliens | -0.010 |
Amen | -0.010 |
Sorry | -0.009 |
girls | -0.009 |
Token | listened |
Token ID | 16399 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
joy | +0.043 |
time | +0.033 |
than | +0.032 |
minutes | +0.030 |
no | +0.029 |
Neg logit contributions | |
glers | -0.055 |
Amen | -0.052 |
aliens | -0.052 |
chers | -0.051 |
Sorry | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
Amen | +0.011 |
aliens | +0.011 |
chers | +0.011 |
glers | +0.011 |
actresses | +0.011 |
Neg logit contributions | |
joy | -0.007 |
time | -0.005 |
mel | -0.005 |
seen | -0.005 |
no | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
joy | +0.021 |
time | +0.016 |
than | +0.016 |
minutes | +0.015 |
no | +0.014 |
Neg logit contributions | |
glers | -0.024 |
Amen | -0.023 |
aliens | -0.022 |
chers | -0.022 |
Sorry | -0.022 |
Token | were |
Token ID | 547 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
joy | +0.003 |
time | +0.003 |
than | +0.003 |
to | +0.003 |
because | +0.003 |
Neg logit contributions | |
Amen | -0.003 |
glers | -0.003 |
aliens | -0.003 |
Sorry | -0.003 |
chers | -0.003 |
Token | from |
Token ID | 422 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
glers | +0.026 |
aliens | +0.025 |
Amen | +0.025 |
chers | +0.025 |
Sorry | +0.024 |
Neg logit contributions | |
joy | -0.019 |
time | -0.014 |
than | -0.013 |
minutes | -0.013 |
no | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
glers | +0.052 |
aliens | +0.052 |
Amen | +0.050 |
Sorry | +0.049 |
chers | +0.049 |
Neg logit contributions | |
joy | -0.036 |
than | -0.025 |
time | -0.025 |
looking | -0.024 |
minutes | -0.024 |
Token | long |
Token ID | 890 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
joy | +0.007 |
than | +0.006 |
time | +0.005 |
no | +0.005 |
minutes | +0.005 |
Neg logit contributions | |
glers | -0.009 |
Amen | -0.009 |
aliens | -0.009 |
Sorry | -0.009 |
chers | -0.009 |
Token | time |
Token ID | 640 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
joy | +0.072 |
no | +0.054 |
than | +0.048 |
looking | +0.047 |
-- | +0.047 |
Neg logit contributions | |
glers | -0.112 |
floats | -0.108 |
aliens | -0.106 |
Amen | -0.104 |
igators | -0.101 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
joy | +0.088 |
time | +0.060 |
no | +0.057 |
looking | +0.056 |
than | +0.054 |
Neg logit contributions | |
glers | -0.143 |
chers | -0.141 |
aliens | -0.140 |
Amen | -0.135 |
Sorry | -0.135 |
Token | and |
Token ID | 290 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
joy | +0.180 |
time | +0.105 |
looking | +0.100 |
minutes | +0.100 |
no | +0.100 |
Neg logit contributions | |
glers | -0.363 |
chers | -0.350 |
aliens | -0.347 |
Amen | -0.347 |
Sorry | -0.340 |
Token | they |
Token ID | 484 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
joy | +0.025 |
time | +0.020 |
than | +0.019 |
minutes | +0.018 |
to | +0.017 |
Neg logit contributions | |
glers | -0.036 |
Amen | -0.035 |
aliens | -0.034 |
chers | -0.034 |
girls | -0.033 |
Token | help |
Token ID | 1037 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
time | +0.002 |
joy | +0.002 |
to | +0.002 |
than | +0.002 |
because | +0.002 |
Neg logit contributions | |
glers | -0.003 |
Amen | -0.003 |
girls | -0.003 |
aliens | -0.003 |
chers | -0.003 |
Token | us |
Token ID | 514 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
glers | +0.079 |
aliens | +0.075 |
Amen | +0.075 |
chers | +0.074 |
Sorry | +0.073 |
Neg logit contributions | |
joy | -0.070 |
time | -0.053 |
than | -0.052 |
minutes | -0.049 |
no | -0.047 |
Token | remember |
Token ID | 3505 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
glers | +0.001 |
Amen | +0.001 |
aliens | +0.001 |
chers | +0.001 |
Sorry | +0.001 |
Neg logit contributions | |
joy | -0.001 |
time | -0.000 |
than | -0.000 |
to | -0.000 |
minutes | -0.000 |
Token | had |
Token ID | 550 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
joy | +0.039 |
time | +0.030 |
than | +0.029 |
minutes | +0.028 |
no | +0.027 |
Neg logit contributions | |
glers | -0.044 |
aliens | -0.042 |
chers | -0.042 |
Amen | -0.042 |
Sorry | -0.040 |
Token | bought |
Token ID | 5839 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
joy | +0.084 |
than | +0.054 |
deliber | +0.054 |
no | +0.054 |
looking | +0.053 |
Neg logit contributions | |
aliens | -0.091 |
glers | -0.091 |
chers | -0.090 |
floats | -0.085 |
actresses | -0.082 |
Token | a |
Token ID | 257 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
joy | +0.030 |
deliber | +0.020 |
minutes | +0.019 |
no | +0.019 |
than | +0.018 |
Neg logit contributions | |
glers | -0.038 |
aliens | -0.038 |
chers | -0.036 |
floats | -0.035 |
maid | -0.034 |
Token | long |
Token ID | 890 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
glers | +0.006 |
chers | +0.006 |
Amen | +0.006 |
aliens | +0.006 |
girls | +0.006 |
Neg logit contributions | |
joy | -0.005 |
time | -0.004 |
than | -0.003 |
minutes | -0.003 |
to | -0.003 |
Token | time |
Token ID | 640 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
joy | +0.095 |
no | +0.069 |
than | +0.068 |
looking | +0.065 |
minutes | +0.063 |
Neg logit contributions | |
Amen | -0.103 |
glers | -0.100 |
aliens | -0.099 |
floats | -0.095 |
Sorry | -0.095 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
joy | +0.083 |
no | +0.049 |
time | +0.049 |
deliber | +0.046 |
looking | +0.046 |
Neg logit contributions | |
glers | -0.160 |
aliens | -0.156 |
chers | -0.154 |
floats | -0.149 |
girls | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
joy | +0.188 |
deliber | +0.109 |
no | +0.109 |
looking | +0.108 |
time | +0.104 |
Neg logit contributions | |
glers | -0.351 |
chers | -0.338 |
aliens | -0.336 |
Amen | -0.329 |
ics | -0.328 |
Token | They |
Token ID | 1119 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
joy | +0.006 |
than | +0.004 |
time | +0.004 |
no | +0.004 |
minutes | +0.004 |
Neg logit contributions | |
glers | -0.009 |
Amen | -0.009 |
Sorry | -0.008 |
aliens | -0.008 |
chers | -0.008 |
Token | did |
Token ID | 750 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
Amen | +0.031 |
glers | +0.031 |
Sorry | +0.030 |
aliens | +0.030 |
chers | +0.030 |
Neg logit contributions | |
joy | -0.021 |
time | -0.017 |
than | -0.015 |
minutes | -0.015 |
to | -0.015 |
Token | not |
Token ID | 407 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
joy | +0.009 |
looking | +0.006 |
no | +0.006 |
time | +0.006 |
minutes | +0.006 |
Neg logit contributions | |
glers | -0.010 |
aliens | -0.009 |
chers | -0.009 |
Amen | -0.009 |
floats | -0.009 |
Token | know |
Token ID | 760 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
joy | +0.058 |
no | +0.042 |
minutes | +0.041 |
time | +0.040 |
than | +0.040 |
Neg logit contributions | |
aliens | -0.037 |
glers | -0.036 |
Amen | -0.036 |
actresses | -0.035 |
Sorry | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
joy | +0.010 |
time | +0.008 |
than | +0.008 |
minutes | +0.007 |
no | +0.007 |
Neg logit contributions | |
glers | -0.013 |
Amen | -0.012 |
chers | -0.012 |
aliens | -0.012 |
Sorry | -0.012 |
Token | brave |
Token ID | 14802 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
joy | +0.003 |
time | +0.002 |
than | +0.002 |
to | +0.002 |
minutes | +0.002 |
Neg logit contributions | |
glers | -0.003 |
Amen | -0.003 |
chers | -0.003 |
maid | -0.002 |
ishly | -0.002 |
Token | people |
Token ID | 661 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
joy | +0.002 |
time | +0.001 |
than | +0.001 |
no | +0.001 |
minutes | +0.001 |
Neg logit contributions | |
glers | -0.001 |
aliens | -0.001 |
Amen | -0.001 |
chers | -0.001 |
girls | -0.001 |
Token | from |
Token ID | 422 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
joy | +0.002 |
time | +0.001 |
than | +0.001 |
minutes | +0.001 |
no | +0.001 |
Neg logit contributions | |
glers | -0.007 |
Amen | -0.006 |
aliens | -0.006 |
Sorry | -0.006 |
chers | -0.006 |
Token | long |
Token ID | 890 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
glers | +0.055 |
aliens | +0.055 |
Amen | +0.053 |
chers | +0.051 |
Sorry | +0.051 |
Neg logit contributions | |
joy | -0.041 |
time | -0.030 |
than | -0.028 |
looking | -0.027 |
minutes | -0.027 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
joy | +0.072 |
looking | +0.051 |
no | +0.049 |
than | +0.046 |
deliber | +0.045 |
Neg logit contributions | |
aliens | -0.127 |
glers | -0.124 |
girls | -0.120 |
chers | -0.118 |
Amen | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | +9.99e-03 |
Pos logit contributions | |
joy | +0.169 |
time | +0.096 |
looking | +0.096 |
minutes | +0.092 |
no | +0.092 |
Neg logit contributions | |
glers | -0.367 |
aliens | -0.356 |
chers | -0.355 |
Amen | -0.353 |
girls | -0.349 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
glers | +0.001 |
Amen | +0.000 |
chers | +0.000 |
aliens | +0.000 |
Sorry | +0.000 |
Neg logit contributions | |
joy | -0.000 |
time | -0.000 |
than | -0.000 |
minutes | -0.000 |
no | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
joy | +0.001 |
than | +0.000 |
minutes | +0.000 |
time | +0.000 |
yet | +0.000 |
Neg logit contributions | |
glers | -0.001 |
Amen | -0.001 |
aliens | -0.001 |
chers | -0.001 |
girls | -0.001 |
Token | One |
Token ID | 3198 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
glers | +0.001 |
Amen | +0.001 |
aliens | +0.001 |
chers | +0.001 |
Sorry | +0.001 |
Neg logit contributions | |
joy | -0.000 |
time | -0.000 |
than | -0.000 |
minutes | -0.000 |
yet | -0.000 |
Token | day |
Token ID | 1110 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
joy | +0.074 |
no | +0.045 |
than | +0.045 |
blond | +0.044 |
-- | +0.042 |
Neg logit contributions | |
Amen | -0.087 |
glers | -0.087 |
aliens | -0.085 |
igators | -0.083 |
actresses | -0.081 |
Token | in |
Token ID | 287 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
joy | +0.037 |
minutes | +0.025 |
looking | +0.025 |
time | +0.024 |
deliber | +0.024 |
Neg logit contributions | |
glers | -0.064 |
aliens | -0.063 |
chers | -0.063 |
Amen | -0.062 |
girls | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
aliens | +0.015 |
glers | +0.015 |
Amen | +0.015 |
Sorry | +0.014 |
chers | +0.014 |
Neg logit contributions | |
joy | -0.011 |
minutes | -0.008 |
than | -0.008 |
looking | -0.008 |
time | -0.007 |
Token | park |
Token ID | 3952 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
joy | +0.032 |
than | +0.029 |
no | +0.027 |
inspection | +0.027 |
deliber | +0.027 |
Neg logit contributions | |
aliens | -0.024 |
Sorry | -0.024 |
spaceship | -0.023 |
Amen | -0.023 |
terminal | -0.022 |
Token | many |
Token ID | 867 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
joy | +0.028 |
time | +0.018 |
minutes | +0.017 |
no | +0.016 |
looking | +0.016 |
Neg logit contributions | |
glers | -0.062 |
aliens | -0.059 |
chers | -0.058 |
Amen | -0.057 |
girls | -0.057 |
Token | years |
Token ID | 812 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
glers | +0.008 |
aliens | +0.008 |
chers | +0.007 |
floats | +0.007 |
Amen | +0.007 |
Neg logit contributions | |
joy | -0.007 |
than | -0.005 |
time | -0.005 |
no | -0.005 |
looking | -0.005 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
joy | +0.073 |
no | +0.051 |
time | +0.047 |
deliber | +0.045 |
Re | +0.042 |
Neg logit contributions | |
aliens | -0.137 |
glers | -0.135 |
floats | -0.126 |
chers | -0.126 |
maid | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
joy | +0.187 |
deliber | +0.118 |
looking | +0.115 |
minutes | +0.115 |
no | +0.113 |
Neg logit contributions | |
glers | -0.333 |
chers | -0.324 |
ics | -0.319 |
aliens | -0.318 |
girls | -0.313 |
Token | Toby |
Token ID | 37578 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
joy | +0.013 |
time | +0.010 |
than | +0.009 |
to | +0.009 |
minutes | +0.009 |
Neg logit contributions | |
glers | -0.014 |
Amen | -0.013 |
chers | -0.013 |
aliens | -0.013 |
Sorry | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
glers | +0.017 |
Amen | +0.017 |
aliens | +0.016 |
Sorry | +0.016 |
chers | +0.016 |
Neg logit contributions | |
joy | -0.011 |
time | -0.009 |
than | -0.008 |
to | -0.007 |
-- | -0.007 |
Token | amazed |
Token ID | 24562 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
joy | +0.006 |
time | +0.005 |
than | +0.005 |
minutes | +0.004 |
no | +0.004 |
Neg logit contributions | |
glers | -0.010 |
Amen | -0.010 |
aliens | -0.010 |
chers | -0.010 |
Sorry | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
aster | +0.025 |
joy | +0.023 |
blond | +0.022 |
minutes | +0.022 |
Ble | +0.021 |
Neg logit contributions | |
glers | -0.027 |
maid | -0.025 |
aliens | -0.025 |
ishly | -0.022 |
amer | -0.021 |
Token | big |
Token ID | 1263 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
glers | +0.004 |
Amen | +0.003 |
aliens | +0.003 |
chers | +0.003 |
Sorry | +0.003 |
Neg logit contributions | |
joy | -0.003 |
time | -0.002 |
than | -0.002 |
minutes | -0.002 |
no | -0.002 |
Token | farm |
Token ID | 5318 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
joy | +0.011 |
no | +0.009 |
looking | +0.008 |
than | +0.008 |
time | +0.008 |
Neg logit contributions | |
aliens | -0.011 |
Amen | -0.011 |
glers | -0.011 |
Sorry | -0.011 |
floats | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
joy | +0.047 |
time | +0.029 |
no | +0.028 |
minutes | +0.028 |
deliber | +0.027 |
Neg logit contributions | |
glers | -0.084 |
chers | -0.080 |
aliens | -0.080 |
girls | -0.079 |
Amen | -0.078 |
Token | long |
Token ID | 890 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
glers | +0.004 |
Amen | +0.004 |
aliens | +0.004 |
chers | +0.004 |
Sorry | +0.004 |
Neg logit contributions | |
joy | -0.003 |
time | -0.002 |
than | -0.002 |
minutes | -0.002 |
no | -0.002 |
Token | time |
Token ID | 640 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
joy | +0.058 |
no | +0.033 |
looking | +0.031 |
than | +0.029 |
deliber | +0.028 |
Neg logit contributions | |
Amen | -0.122 |
glers | -0.120 |
aliens | -0.120 |
floats | -0.115 |
Sorry | -0.113 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.55e+00 |
Pos logit contributions | |
joy | +0.083 |
looking | +0.060 |
no | +0.059 |
deliber | +0.054 |
time | +0.054 |
Neg logit contributions | |
aliens | -0.133 |
glers | -0.132 |
chers | -0.131 |
girls | -0.127 |
Amen | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
joy | +0.187 |
looking | +0.119 |
deliber | +0.116 |
no | +0.115 |
minutes | +0.110 |
Neg logit contributions | |
glers | -0.331 |
chers | -0.321 |
aliens | -0.317 |
Amen | -0.313 |
girls | -0.311 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
joy | +0.018 |
than | +0.014 |
time | +0.014 |
no | +0.013 |
minutes | +0.013 |
Neg logit contributions | |
glers | -0.020 |
Amen | -0.020 |
Sorry | -0.019 |
aliens | -0.019 |
chers | -0.019 |
Token | listened |
Token ID | 16399 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
joy | +0.007 |
time | +0.005 |
than | +0.005 |
to | +0.004 |
minutes | +0.004 |
Neg logit contributions | |
glers | -0.011 |
Amen | -0.011 |
aliens | -0.011 |
Sorry | -0.011 |
chers | -0.011 |
Token | as |
Token ID | 355 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
chers | +0.007 |
glers | +0.007 |
Amen | +0.007 |
ishly | +0.007 |
aliens | +0.007 |
Neg logit contributions | |
joy | -0.006 |
time | -0.004 |
seen | -0.004 |
blond | -0.004 |
mel | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
joy | +0.024 |
time | +0.017 |
than | +0.017 |
minutes | +0.016 |
no | +0.015 |
Neg logit contributions | |
glers | -0.041 |
aliens | -0.040 |
Amen | -0.040 |
chers | -0.039 |
Sorry | -0.038 |
Token | had |
Token ID | 550 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
glers | +0.007 |
Amen | +0.007 |
aliens | +0.007 |
chers | +0.007 |
Sorry | +0.007 |
Neg logit contributions | |
joy | -0.007 |
time | -0.005 |
than | -0.005 |
minutes | -0.005 |
no | -0.005 |
Token | been |
Token ID | 587 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
joy | +0.021 |
time | +0.014 |
than | +0.014 |
minutes | +0.013 |
no | +0.012 |
Neg logit contributions | |
glers | -0.035 |
aliens | -0.034 |
Amen | -0.034 |
chers | -0.034 |
Sorry | -0.033 |
Token | made |
Token ID | 925 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
joy | +0.054 |
than | +0.037 |
no | +0.037 |
time | +0.037 |
deliber | +0.035 |
Neg logit contributions | |
glers | -0.054 |
chers | -0.054 |
aliens | -0.053 |
Amen | -0.049 |
floats | -0.048 |
Token | many |
Token ID | 867 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
glers | +0.014 |
aliens | +0.014 |
chers | +0.014 |
hing | +0.013 |
Amen | +0.013 |
Neg logit contributions | |
joy | -0.018 |
minutes | -0.013 |
time | -0.013 |
than | -0.013 |
no | -0.012 |
Token | years |
Token ID | 812 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
glers | +0.044 |
aliens | +0.043 |
Amen | +0.043 |
chers | +0.042 |
Sorry | +0.041 |
Neg logit contributions | |
joy | -0.028 |
time | -0.020 |
than | -0.019 |
minutes | -0.018 |
no | -0.018 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
joy | +0.082 |
no | +0.052 |
deliber | +0.047 |
time | +0.042 |
than | +0.041 |
Neg logit contributions | |
glers | -0.147 |
aliens | -0.146 |
floats | -0.140 |
docks | -0.139 |
chers | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
joy | +0.207 |
deliber | +0.132 |
no | +0.124 |
minutes | +0.120 |
looking | +0.119 |
Neg logit contributions | |
glers | -0.310 |
ics | -0.308 |
chers | -0.303 |
aliens | -0.302 |
Amen | -0.292 |
Token | but |
Token ID | 475 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
joy | +0.029 |
deliber | +0.019 |
no | +0.019 |
minutes | +0.019 |
looking | +0.018 |
Neg logit contributions | |
aliens | -0.037 |
glers | -0.036 |
floats | -0.036 |
actresses | -0.034 |
chers | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
joy | +0.065 |
time | +0.046 |
than | +0.044 |
minutes | +0.041 |
no | +0.040 |
Neg logit contributions | |
glers | -0.100 |
Amen | -0.097 |
aliens | -0.097 |
chers | -0.095 |
Sorry | -0.095 |
Token | still |
Token ID | 991 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
joy | +0.027 |
than | +0.019 |
minutes | +0.019 |
time | +0.019 |
no | +0.019 |
Neg logit contributions | |
glers | -0.021 |
chers | -0.020 |
aliens | -0.020 |
Amen | -0.019 |
floats | -0.019 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
joy | +0.043 |
no | +0.031 |
time | +0.031 |
minutes | +0.031 |
deliber | +0.030 |
Neg logit contributions | |
glers | -0.033 |
aliens | -0.032 |
chers | -0.032 |
floats | -0.031 |
actresses | -0.030 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
joy | +0.001 |
time | +0.001 |
than | +0.001 |
minutes | +0.001 |
sight | +0.001 |
Neg logit contributions | |
Amen | -0.002 |
glers | -0.002 |
chers | -0.002 |
Sorry | -0.002 |
girls | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
glers | +0.078 |
aliens | +0.075 |
chers | +0.074 |
floats | +0.074 |
Amen | +0.072 |
Neg logit contributions | |
joy | -0.069 |
time | -0.050 |
no | -0.048 |
than | -0.048 |
minutes | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
glers | +0.051 |
Amen | +0.050 |
aliens | +0.050 |
chers | +0.049 |
Sorry | +0.049 |
Neg logit contributions | |
joy | -0.023 |
time | -0.016 |
than | -0.015 |
minutes | -0.014 |
no | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
joy | +0.031 |
than | +0.027 |
time | +0.026 |
minutes | +0.026 |
seen | +0.025 |
Neg logit contributions | |
Amen | -0.031 |
Sorry | -0.030 |
aliens | -0.029 |
chers | -0.029 |
ishly | -0.028 |
Token | Let |
Token ID | 5756 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
joy | +0.013 |
time | +0.010 |
minutes | +0.010 |
than | +0.010 |
yet | +0.009 |
Neg logit contributions | |
glers | -0.011 |
Amen | -0.011 |
Sorry | -0.010 |
aliens | -0.010 |
floats | -0.010 |
Token | 's |
Token ID | 338 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
glers | +0.092 |
Amen | +0.089 |
chers | +0.087 |
aliens | +0.087 |
girls | +0.084 |
Neg logit contributions | |
joy | -0.081 |
time | -0.074 |
than | -0.063 |
to | -0.062 |
no | -0.061 |
Token | make |
Token ID | 787 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
chers | +0.235 |
glers | +0.228 |
Amen | +0.224 |
aliens | +0.213 |
actresses | +0.212 |
Neg logit contributions | |
time | -0.140 |
like | -0.114 |
to | -0.114 |
because | -0.110 |
an | -0.109 |
Token | a |
Token ID | 257 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
glers | +0.157 |
Amen | +0.153 |
chers | +0.149 |
Sorry | +0.147 |
aliens | +0.147 |
Neg logit contributions | |
joy | -0.051 |
time | -0.033 |
than | -0.027 |
minutes | -0.025 |
no | -0.023 |
Token | tent |
Token ID | 11105 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
glers | +0.164 |
hing | +0.158 |
chers | +0.157 |
Amen | +0.155 |
ishly | +0.155 |
Neg logit contributions | |
joy | -0.083 |
time | -0.080 |
long | -0.070 |
fun | -0.065 |
sight | -0.064 |
Token | here |
Token ID | 994 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
glers | +0.103 |
Amen | +0.102 |
aliens | +0.099 |
actresses | +0.098 |
chers | +0.098 |
Neg logit contributions | |
joy | -0.067 |
than | -0.058 |
time | -0.056 |
to | -0.054 |
yet | -0.049 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
glers | +0.017 |
Amen | +0.016 |
aliens | +0.016 |
chers | +0.015 |
Sorry | +0.015 |
Neg logit contributions | |
joy | -0.017 |
time | -0.015 |
than | -0.015 |
to | -0.013 |
minutes | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
joy | +0.036 |
than | +0.026 |
time | +0.026 |
no | +0.025 |
minutes | +0.025 |
Neg logit contributions | |
glers | -0.047 |
aliens | -0.046 |
chers | -0.045 |
floats | -0.043 |
actresses | -0.042 |
Token | she |
Token ID | 673 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
glers | +0.040 |
aliens | +0.039 |
Amen | +0.038 |
chers | +0.038 |
Sorry | +0.038 |
Neg logit contributions | |
joy | -0.028 |
time | -0.021 |
than | -0.020 |
minutes | -0.019 |
no | -0.018 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Amen | +0.022 |
glers | +0.021 |
aliens | +0.021 |
Sorry | +0.020 |
arse | +0.020 |
Neg logit contributions | |
joy | -0.011 |
time | -0.010 |
than | -0.009 |
to | -0.009 |
thought | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
glers | +0.008 |
Sorry | +0.008 |
chers | +0.008 |
actresses | +0.007 |
off | +0.007 |
Neg logit contributions | |
joy | -0.005 |
minutes | -0.003 |
time | -0.003 |
than | -0.003 |
blond | -0.003 |
Token | collect |
Token ID | 2824 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
time | +0.014 |
joy | +0.012 |
to | +0.011 |
than | +0.011 |
like | +0.011 |
Neg logit contributions | |
chers | -0.019 |
glers | -0.018 |
Amen | -0.018 |
aliens | -0.018 |
girls | -0.018 |
Token | all |
Token ID | 477 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
joy | +0.007 |
deliber | +0.005 |
no | +0.005 |
time | +0.004 |
than | +0.004 |
Neg logit contributions | |
aliens | -0.008 |
glers | -0.008 |
floats | -0.008 |
chers | -0.008 |
igators | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
glers | +0.188 |
aliens | +0.174 |
igators | +0.171 |
floats | +0.169 |
chers | +0.167 |
Neg logit contributions | |
joy | -0.157 |
time | -0.109 |
minutes | -0.109 |
than | -0.108 |
no | -0.102 |
Token | match |
Token ID | 2872 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
joy | +0.012 |
no | +0.009 |
than | +0.008 |
looking | +0.008 |
deliber | +0.008 |
Neg logit contributions | |
aliens | -0.012 |
glers | -0.012 |
chers | -0.012 |
floats | -0.011 |
igators | -0.011 |
Token | sticks |
Token ID | 34810 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
glers | +0.012 |
aliens | +0.011 |
chers | +0.011 |
floats | +0.010 |
girls | +0.010 |
Neg logit contributions | |
joy | -0.006 |
time | -0.004 |
minutes | -0.003 |
no | -0.003 |
deliber | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
joy | +0.010 |
time | +0.006 |
minutes | +0.005 |
blond | +0.005 |
no | +0.005 |
Neg logit contributions | |
glers | -0.018 |
chers | -0.017 |
aliens | -0.017 |
girls | -0.016 |
floats | -0.016 |
Token | could |
Token ID | 714 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
glers | +0.005 |
chers | +0.005 |
aliens | +0.005 |
Amen | +0.005 |
Sorry | +0.004 |
Neg logit contributions | |
joy | -0.005 |
time | -0.004 |
than | -0.004 |
no | -0.004 |
minutes | -0.004 |
Token | It |
Token ID | 1026 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
joy | +0.021 |
time | +0.017 |
than | +0.016 |
minutes | +0.016 |
yet | +0.016 |
Neg logit contributions | |
Amen | -0.020 |
glers | -0.020 |
chers | -0.019 |
Sorry | -0.019 |
aliens | -0.018 |
Token | 's |
Token ID | 338 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
glers | +0.023 |
Amen | +0.021 |
aliens | +0.021 |
actresses | +0.021 |
girls | +0.021 |
Neg logit contributions | |
joy | -0.017 |
time | -0.015 |
to | -0.014 |
than | -0.014 |
-- | -0.013 |
Token | ok |
Token ID | 12876 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Amen | +0.077 |
aliens | +0.074 |
glers | +0.074 |
Sorry | +0.072 |
chers | +0.070 |
Neg logit contributions | |
joy | -0.073 |
than | -0.051 |
looking | -0.051 |
no | -0.049 |
minutes | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
Amen | +0.005 |
aliens | +0.005 |
maid | +0.005 |
glers | +0.005 |
Sorry | +0.005 |
Neg logit contributions | |
joy | -0.003 |
looking | -0.002 |
deliber | -0.002 |
no | -0.002 |
than | -0.002 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
glers | +0.024 |
aliens | +0.022 |
chers | +0.022 |
Amen | +0.022 |
Sorry | +0.021 |
Neg logit contributions | |
joy | -0.023 |
time | -0.018 |
than | -0.018 |
minutes | -0.017 |
no | -0.016 |
Token | 's |
Token ID | 338 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
glers | +0.066 |
Amen | +0.063 |
aliens | +0.062 |
chers | +0.061 |
Sorry | +0.060 |
Neg logit contributions | |
joy | -0.073 |
time | -0.062 |
than | -0.058 |
minutes | -0.056 |
no | -0.055 |
Token | mix |
Token ID | 5022 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
glers | +0.187 |
chers | +0.184 |
aliens | +0.177 |
actresses | +0.170 |
girls | +0.169 |
Neg logit contributions | |
time | -0.144 |
joy | -0.138 |
to | -0.122 |
than | -0.118 |
because | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
glers | +0.027 |
aliens | +0.026 |
chers | +0.025 |
floats | +0.025 |
Sorry | +0.025 |
Neg logit contributions | |
joy | -0.023 |
time | -0.016 |
than | -0.016 |
looking | -0.016 |
deliber | -0.015 |
Token | red |
Token ID | 2266 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
glers | +0.031 |
aliens | +0.030 |
Amen | +0.029 |
chers | +0.029 |
floats | +0.029 |
Neg logit contributions | |
joy | -0.030 |
than | -0.023 |
time | -0.022 |
minutes | -0.021 |
no | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
joy | +0.021 |
time | +0.016 |
than | +0.016 |
minutes | +0.014 |
no | +0.014 |
Neg logit contributions | |
glers | -0.026 |
Amen | -0.026 |
chers | -0.025 |
aliens | -0.025 |
Sorry | -0.024 |
Token | blue |
Token ID | 4171 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
glers | +0.060 |
Amen | +0.059 |
aliens | +0.058 |
chers | +0.058 |
girls | +0.056 |
Neg logit contributions | |
joy | -0.051 |
time | -0.043 |
than | -0.041 |
minutes | -0.039 |
to | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
joy | +0.006 |
time | +0.003 |
than | +0.003 |
to | +0.002 |
no | +0.001 |
Neg logit contributions | |
glers | -0.025 |
Amen | -0.025 |
Sorry | -0.025 |
aliens | -0.024 |
chers | -0.024 |
Token | see |
Token ID | 766 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Amen | +0.012 |
glers | +0.011 |
aliens | +0.011 |
girls | +0.011 |
Sorry | +0.011 |
Neg logit contributions | |
joy | -0.012 |
than | -0.010 |
minutes | -0.009 |
time | -0.009 |
looking | -0.009 |
Token | him |
Token ID | 683 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
joy | +0.064 |
time | +0.047 |
than | +0.044 |
minutes | +0.044 |
no | +0.041 |
Neg logit contributions | |
glers | -0.091 |
aliens | -0.089 |
Amen | -0.089 |
chers | -0.087 |
girls | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
glers | +0.010 |
aliens | +0.009 |
chers | +0.009 |
Amen | +0.009 |
girls | +0.009 |
Neg logit contributions | |
joy | -0.006 |
minutes | -0.004 |
than | -0.004 |
time | -0.004 |
no | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
glers | +0.025 |
Amen | +0.024 |
chers | +0.024 |
aliens | +0.024 |
maid | +0.023 |
Neg logit contributions | |
joy | -0.027 |
time | -0.023 |
than | -0.022 |
minutes | -0.020 |
to | -0.020 |
Token | all |
Token ID | 477 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
Amen | +0.063 |
Sorry | +0.061 |
glers | +0.061 |
aliens | +0.060 |
chers | +0.059 |
Neg logit contributions | |
joy | -0.040 |
time | -0.033 |
to | -0.029 |
because | -0.028 |
but | -0.027 |
Token | sat |
Token ID | 3332 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Amen | +0.188 |
glers | +0.188 |
aliens | +0.185 |
chers | +0.184 |
Sorry | +0.182 |
Neg logit contributions | |
joy | -0.117 |
time | -0.097 |
than | -0.086 |
minutes | -0.081 |
to | -0.077 |
Token | together |
Token ID | 1978 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
joy | +0.013 |
time | +0.010 |
than | +0.009 |
minutes | +0.009 |
no | +0.009 |
Neg logit contributions | |
glers | -0.016 |
Amen | -0.015 |
aliens | -0.015 |
chers | -0.015 |
Sorry | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
glers | +0.078 |
aliens | +0.075 |
chers | +0.075 |
remote | +0.072 |
floats | +0.072 |
Neg logit contributions | |
joy | -0.052 |
looking | -0.036 |
deliber | -0.033 |
no | -0.033 |
minutes | -0.032 |
Token | waiting |
Token ID | 4953 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
joy | +0.009 |
time | +0.007 |
no | +0.007 |
looking | +0.007 |
-- | +0.007 |
Neg logit contributions | |
glers | -0.014 |
floats | -0.013 |
chers | -0.013 |
actresses | -0.013 |
aliens | -0.013 |
Token | for |
Token ID | 329 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
joy | +0.010 |
looking | +0.008 |
time | +0.007 |
no | +0.007 |
deliber | +0.007 |
Neg logit contributions | |
glers | -0.015 |
aliens | -0.015 |
chers | -0.014 |
floats | -0.014 |
Sorry | -0.014 |
Token | your |
Token ID | 534 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
joy | +0.005 |
time | +0.004 |
than | +0.004 |
minutes | +0.003 |
no | +0.003 |
Neg logit contributions | |
aliens | -0.005 |
glers | -0.005 |
Amen | -0.005 |
chers | -0.005 |
Sorry | -0.004 |
Token | er |
Token ID | 1931 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
aliens | +0.009 |
glers | +0.009 |
maid | +0.008 |
Sorry | +0.008 |
chers | +0.008 |
Neg logit contributions | |
joy | -0.010 |
looking | -0.008 |
than | -0.008 |
minutes | -0.008 |
no | -0.008 |
Token | aser |
Token ID | 6005 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
glers | +0.033 |
Amen | +0.033 |
aliens | +0.031 |
Sorry | +0.031 |
chers | +0.030 |
Neg logit contributions | |
joy | -0.041 |
time | -0.033 |
than | -0.033 |
no | -0.031 |
minutes | -0.031 |
Token | ! |
Token ID | 0 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
glers | +0.038 |
Amen | +0.037 |
aliens | +0.036 |
chers | +0.035 |
Sorry | +0.035 |
Neg logit contributions | |
joy | -0.026 |
time | -0.020 |
than | -0.020 |
minutes | -0.018 |
no | -0.017 |
Token | Let |
Token ID | 3914 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
glers | +0.036 |
chers | +0.033 |
aliens | +0.032 |
floats | +0.032 |
maid | +0.032 |
Neg logit contributions | |
joy | -0.022 |
than | -0.016 |
time | -0.016 |
to | -0.015 |
But | -0.015 |
Token | 's |
Token ID | 338 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
glers | +0.103 |
Amen | +0.100 |
actresses | +0.097 |
aliens | +0.097 |
girls | +0.096 |
Neg logit contributions | |
time | -0.062 |
joy | -0.059 |
to | -0.048 |
no | -0.044 |
than | -0.043 |
Token | swim |
Token ID | 9422 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
glers | +0.247 |
chers | +0.246 |
rol | +0.237 |
actresses | +0.234 |
lights | +0.233 |
Neg logit contributions | |
time | -0.107 |
like | -0.088 |
to | -0.086 |
. | -0.082 |
because | -0.082 |
Token | together |
Token ID | 1978 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
glers | +0.084 |
Amen | +0.082 |
Sorry | +0.079 |
aliens | +0.078 |
actresses | +0.078 |
Neg logit contributions | |
joy | -0.045 |
time | -0.035 |
than | -0.035 |
to | -0.033 |
minutes | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
glers | +0.157 |
Amen | +0.151 |
Sorry | +0.147 |
aliens | +0.145 |
chers | +0.143 |
Neg logit contributions | |
joy | -0.088 |
time | -0.072 |
than | -0.069 |
to | -0.064 |
minutes | -0.059 |
Token | look |
Token ID | 804 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
glers | +0.044 |
chers | +0.041 |
ains | +0.041 |
rol | +0.041 |
hing | +0.040 |
Neg logit contributions | |
to | -0.024 |
that | -0.021 |
but | -0.021 |
joy | -0.021 |
like | -0.020 |
Token | for |
Token ID | 329 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
glers | +0.000 |
Amen | +0.000 |
chers | +0.000 |
aliens | +0.000 |
Sorry | +0.000 |
Neg logit contributions | |
joy | -0.000 |
time | -0.000 |
than | -0.000 |
minutes | -0.000 |
to | -0.000 |
Token | with |
Token ID | 351 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
joy | +0.031 |
minutes | +0.022 |
deliber | +0.022 |
time | +0.022 |
ureen | +0.020 |
Neg logit contributions | |
glers | -0.028 |
Amen | -0.026 |
ics | -0.025 |
aliens | -0.025 |
igators | -0.024 |
Token | his |
Token ID | 465 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
joy | +0.030 |
time | +0.021 |
than | +0.020 |
minutes | +0.018 |
no | +0.017 |
Neg logit contributions | |
glers | -0.062 |
Amen | -0.060 |
chers | -0.060 |
aliens | -0.059 |
Sorry | -0.058 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
joy | +0.061 |
time | +0.050 |
than | +0.048 |
no | +0.044 |
minutes | +0.044 |
Neg logit contributions | |
glers | -0.057 |
Amen | -0.055 |
chers | -0.054 |
aliens | -0.054 |
Sorry | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
joy | +0.008 |
minutes | +0.005 |
time | +0.005 |
than | +0.005 |
looking | +0.005 |
Neg logit contributions | |
glers | -0.016 |
aliens | -0.016 |
Amen | -0.016 |
chers | -0.015 |
girls | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
joy | +0.022 |
time | +0.016 |
than | +0.015 |
minutes | +0.014 |
no | +0.014 |
Neg logit contributions | |
glers | -0.039 |
aliens | -0.038 |
Amen | -0.037 |
chers | -0.037 |
Sorry | -0.036 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
joy | +0.015 |
time | +0.012 |
than | +0.011 |
minutes | +0.011 |
no | +0.011 |
Neg logit contributions | |
glers | -0.015 |
Amen | -0.014 |
aliens | -0.014 |
chers | -0.014 |
Sorry | -0.014 |
Token | s |
Token ID | 82 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Amen | +0.011 |
glers | +0.011 |
Sorry | +0.011 |
aliens | +0.010 |
chers | +0.010 |
Neg logit contributions | |
joy | -0.011 |
than | -0.009 |
time | -0.009 |
to | -0.009 |
because | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
glers | +0.078 |
aliens | +0.076 |
chers | +0.073 |
Amen | +0.073 |
girls | +0.073 |
Neg logit contributions | |
joy | -0.044 |
minutes | -0.031 |
time | -0.029 |
deliber | -0.029 |
no | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
joy | +0.015 |
to | +0.012 |
than | +0.011 |
time | +0.011 |
an | +0.010 |
Neg logit contributions | |
glers | -0.033 |
chers | -0.032 |
arse | -0.031 |
Amen | -0.031 |
hing | -0.031 |
Token | birds |
Token ID | 10087 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
joy | +0.007 |
time | +0.006 |
than | +0.006 |
minutes | +0.005 |
no | +0.005 |
Neg logit contributions | |
glers | -0.009 |
Amen | -0.009 |
chers | -0.009 |
aliens | -0.008 |
Sorry | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
Amen | +0.009 |
Sorry | +0.009 |
glers | +0.009 |
chers | +0.008 |
aliens | +0.008 |
Neg logit contributions | |
joy | -0.001 |
time | -0.001 |
than | -0.001 |
to | -0.000 |
because | -0.000 |
Token | he |
Token ID | 339 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
glers | +0.008 |
aliens | +0.008 |
Sorry | +0.008 |
chers | +0.008 |
floats | +0.008 |
Neg logit contributions | |
joy | -0.006 |
looking | -0.004 |
time | -0.004 |
blond | -0.004 |
than | -0.004 |
Token | started |
Token ID | 2067 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
glers | +0.001 |
Amen | +0.001 |
Sorry | +0.001 |
aliens | +0.001 |
chers | +0.001 |
Neg logit contributions | |
joy | -0.000 |
time | -0.000 |
minutes | -0.000 |
than | -0.000 |
to | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
joy | +0.001 |
looking | +0.001 |
time | +0.001 |
than | +0.001 |
minutes | +0.001 |
Neg logit contributions | |
glers | -0.001 |
floats | -0.001 |
chers | -0.001 |
aliens | -0.001 |
actresses | -0.001 |
Token | dive |
Token ID | 15647 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
joy | +0.047 |
time | +0.040 |
than | +0.037 |
to | +0.035 |
no | +0.035 |
Neg logit contributions | |
glers | -0.038 |
Amen | -0.036 |
chers | -0.036 |
aliens | -0.036 |
Sorry | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
joy | +0.016 |
time | +0.012 |
no | +0.012 |
looking | +0.011 |
deliber | +0.011 |
Neg logit contributions | |
glers | -0.016 |
aliens | -0.015 |
chers | -0.015 |
maid | -0.015 |
floats | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
joy | +0.010 |
than | +0.008 |
minutes | +0.007 |
time | +0.007 |
orm | +0.007 |
Neg logit contributions | |
Sorry | -0.009 |
Amen | -0.009 |
girls | -0.009 |
glers | -0.009 |
aliens | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
joy | +0.004 |
than | +0.003 |
minutes | +0.003 |
time | +0.002 |
blond | +0.002 |
Neg logit contributions | |
glers | -0.005 |
Amen | -0.005 |
chers | -0.005 |
aliens | -0.005 |
girls | -0.005 |
Token | He |
Token ID | 1544 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
joy | +0.003 |
time | +0.002 |
than | +0.002 |
minutes | +0.002 |
yet | +0.002 |
Neg logit contributions | |
glers | -0.003 |
Amen | -0.003 |
chers | -0.003 |
aliens | -0.003 |
Sorry | -0.003 |
Token | went |
Token ID | 1816 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
glers | +0.007 |
Amen | +0.006 |
Sorry | +0.006 |
aliens | +0.006 |
chers | +0.006 |
Neg logit contributions | |
joy | -0.006 |
time | -0.005 |
than | -0.005 |
minutes | -0.005 |
no | -0.004 |
Token | deeper |
Token ID | 9211 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
glers | +0.045 |
Amen | +0.044 |
aliens | +0.043 |
chers | +0.043 |
Sorry | +0.042 |
Neg logit contributions | |
joy | -0.045 |
time | -0.036 |
than | -0.034 |
minutes | -0.033 |
no | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
glers | +0.001 |
aliens | +0.001 |
floats | +0.001 |
maid | +0.001 |
chers | +0.001 |
Neg logit contributions | |
joy | -0.002 |
time | -0.001 |
looking | -0.001 |
no | -0.001 |
deliber | -0.001 |
Token | ." |
Token ID | 526 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
glers | +0.011 |
Amen | +0.011 |
aliens | +0.011 |
Sorry | +0.011 |
chers | +0.010 |
Neg logit contributions | |
joy | -0.006 |
time | -0.005 |
than | -0.005 |
to | -0.004 |
yet | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
Amen | +0.011 |
Sorry | +0.011 |
glers | +0.011 |
aliens | +0.011 |
actresses | +0.011 |
Neg logit contributions | |
joy | -0.008 |
time | -0.006 |
than | -0.006 |
minutes | -0.006 |
no | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
glers | +0.038 |
Amen | +0.038 |
aliens | +0.037 |
chers | +0.036 |
Sorry | +0.036 |
Neg logit contributions | |
joy | -0.020 |
than | -0.013 |
time | -0.013 |
minutes | -0.012 |
no | -0.011 |
Token | Mom |
Token ID | 29252 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
glers | +0.026 |
Amen | +0.025 |
aliens | +0.025 |
chers | +0.024 |
Sorry | +0.024 |
Neg logit contributions | |
joy | -0.021 |
time | -0.016 |
than | -0.016 |
minutes | -0.015 |
no | -0.014 |
Token | : |
Token ID | 25 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
joy | +0.015 |
time | +0.012 |
than | +0.012 |
minutes | +0.011 |
no | +0.011 |
Neg logit contributions | |
glers | -0.014 |
Amen | -0.013 |
aliens | -0.013 |
chers | -0.013 |
Sorry | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
joy | +0.047 |
than | +0.038 |
time | +0.036 |
minutes | +0.036 |
seen | +0.033 |
Neg logit contributions | |
Amen | -0.081 |
Sorry | -0.080 |
glers | -0.078 |
chers | -0.074 |
aliens | -0.074 |
Token | Okay |
Token ID | 16454 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Amen | +0.004 |
glers | +0.004 |
Sorry | +0.004 |
chers | +0.004 |
aliens | +0.004 |
Neg logit contributions | |
joy | -0.004 |
time | -0.003 |
than | -0.003 |
yet | -0.003 |
minutes | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
Sorry | +0.018 |
glers | +0.018 |
aliens | +0.018 |
Amen | +0.017 |
chers | +0.017 |
Neg logit contributions | |
joy | -0.013 |
looking | -0.009 |
no | -0.009 |
than | -0.009 |
deliber | -0.009 |
Token | but |
Token ID | 475 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
aliens | +0.027 |
glers | +0.027 |
Sorry | +0.026 |
chers | +0.026 |
Amen | +0.026 |
Neg logit contributions | |
joy | -0.029 |
looking | -0.020 |
no | -0.020 |
than | -0.020 |
time | -0.020 |
Token | don |
Token ID | 836 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
joy | +0.018 |
time | +0.013 |
than | +0.013 |
looking | +0.013 |
minutes | +0.013 |
Neg logit contributions | |
glers | -0.013 |
aliens | -0.013 |
Sorry | -0.013 |
Amen | -0.013 |
chers | -0.012 |
Token | 't |
Token ID | 470 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
joy | +0.009 |
time | +0.009 |
no | +0.008 |
to | +0.007 |
because | +0.007 |
Neg logit contributions | |
maid | -0.010 |
glers | -0.010 |
aliens | -0.010 |
actresses | -0.009 |
chers | -0.009 |
Token | jungle |
Token ID | 20712 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Amen | +0.018 |
chers | +0.018 |
glers | +0.018 |
maid | +0.017 |
Sorry | +0.017 |
Neg logit contributions | |
joy | -0.009 |
time | -0.008 |
black | -0.006 |
to | -0.006 |
sight | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
joy | +0.032 |
time | +0.018 |
deliber | +0.017 |
minutes | +0.016 |
no | +0.016 |
Neg logit contributions | |
glers | -0.062 |
aliens | -0.058 |
chers | -0.057 |
girls | -0.057 |
igators | -0.056 |
Token | They |
Token ID | 1119 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
glers | +0.003 |
floats | +0.003 |
Amen | +0.003 |
aliens | +0.003 |
Sorry | +0.003 |
Neg logit contributions | |
joy | -0.004 |
than | -0.003 |
no | -0.003 |
minutes | -0.003 |
time | -0.002 |
Token | would |
Token ID | 561 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Amen | +0.049 |
Sorry | +0.049 |
glers | +0.047 |
chers | +0.047 |
aliens | +0.047 |
Neg logit contributions | |
joy | -0.034 |
time | -0.030 |
than | -0.027 |
to | -0.026 |
minutes | -0.025 |
Token | plan |
Token ID | 1410 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
glers | +0.046 |
chers | +0.045 |
aliens | +0.044 |
Amen | +0.044 |
Sorry | +0.044 |
Neg logit contributions | |
joy | -0.047 |
time | -0.040 |
than | -0.037 |
minutes | -0.035 |
to | -0.034 |
Token | adventures |
Token ID | 17545 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
glers | +0.120 |
aliens | +0.116 |
chers | +0.114 |
floats | +0.111 |
girls | +0.110 |
Neg logit contributions | |
joy | -0.076 |
minutes | -0.044 |
than | -0.043 |
deliber | -0.042 |
time | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
glers | +0.013 |
aliens | +0.012 |
chers | +0.012 |
girls | +0.012 |
floats | +0.012 |
Neg logit contributions | |
joy | -0.014 |
time | -0.010 |
minutes | -0.010 |
no | -0.010 |
blond | -0.010 |
Token | explore |
Token ID | 7301 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
chers | +0.028 |
glers | +0.027 |
Amen | +0.027 |
maid | +0.026 |
aliens | +0.026 |
Neg logit contributions | |
joy | -0.025 |
time | -0.022 |
than | -0.021 |
to | -0.020 |
but | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
joy | +0.008 |
time | +0.006 |
than | +0.005 |
no | +0.005 |
minutes | +0.005 |
Neg logit contributions | |
glers | -0.012 |
aliens | -0.012 |
chers | -0.012 |
floats | -0.012 |
Amen | -0.011 |
Token | different |
Token ID | 1180 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
glers | +0.026 |
aliens | +0.025 |
chers | +0.024 |
girls | +0.023 |
floats | +0.023 |
Neg logit contributions | |
joy | -0.027 |
minutes | -0.020 |
time | -0.020 |
no | -0.020 |
than | -0.019 |
Token | animals |
Token ID | 4695 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
glers | +0.025 |
aliens | +0.024 |
floats | +0.022 |
chers | +0.022 |
girls | +0.022 |
Neg logit contributions | |
joy | -0.029 |
time | -0.023 |
minutes | -0.022 |
no | -0.022 |
than | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
aliens | +0.026 |
chers | +0.026 |
glers | +0.025 |
Amen | +0.025 |
ishly | +0.025 |
Neg logit contributions | |
joy | -0.014 |
time | -0.011 |
than | -0.010 |
no | -0.010 |
minutes | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
aliens | +0.001 |
Amen | +0.001 |
remote | +0.001 |
Sorry | +0.001 |
glers | +0.001 |
Neg logit contributions | |
joy | -0.001 |
than | -0.001 |
seen | -0.001 |
no | -0.001 |
minutes | -0.001 |
Token | Get |
Token ID | 3855 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
joy | +0.008 |
time | +0.006 |
than | +0.006 |
minutes | +0.006 |
no | +0.006 |
Neg logit contributions | |
glers | -0.012 |
Amen | -0.011 |
aliens | -0.011 |
chers | -0.011 |
Sorry | -0.011 |
Token | away |
Token ID | 1497 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
glers | +0.012 |
Amen | +0.012 |
aliens | +0.011 |
chers | +0.011 |
Sorry | +0.011 |
Neg logit contributions | |
joy | -0.017 |
time | -0.014 |
than | -0.014 |
minutes | -0.013 |
no | -0.013 |
Token | from |
Token ID | 422 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
glers | +0.067 |
Amen | +0.066 |
chers | +0.064 |
aliens | +0.064 |
Sorry | +0.062 |
Neg logit contributions | |
joy | -0.071 |
than | -0.059 |
time | -0.059 |
minutes | -0.053 |
to | -0.053 |
Token | our |
Token ID | 674 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
glers | +0.080 |
aliens | +0.077 |
Amen | +0.076 |
chers | +0.075 |
Sorry | +0.074 |
Neg logit contributions | |
joy | -0.073 |
time | -0.055 |
than | -0.054 |
minutes | -0.051 |
no | -0.051 |
Token | boat |
Token ID | 8848 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
joy | +0.005 |
time | +0.005 |
than | +0.005 |
minutes | +0.004 |
no | +0.004 |
Neg logit contributions | |
glers | -0.003 |
Amen | -0.002 |
aliens | -0.002 |
chers | -0.002 |
Sorry | -0.002 |
Token | ! |
Token ID | 0 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
joy | +0.014 |
time | +0.011 |
than | +0.010 |
minutes | +0.009 |
no | +0.009 |
Neg logit contributions | |
glers | -0.021 |
Amen | -0.021 |
aliens | -0.021 |
chers | -0.020 |
Sorry | -0.020 |
Token | This |
Token ID | 770 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
glers | +0.030 |
Amen | +0.028 |
aliens | +0.028 |
chers | +0.028 |
Sorry | +0.027 |
Neg logit contributions | |
joy | -0.031 |
time | -0.025 |
than | -0.024 |
minutes | -0.023 |
no | -0.022 |
Token | is |
Token ID | 318 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
joy | +0.061 |
time | +0.054 |
than | +0.051 |
minutes | +0.049 |
no | +0.047 |
Neg logit contributions | |
glers | -0.034 |
Amen | -0.032 |
aliens | -0.031 |
Sorry | -0.031 |
chers | -0.031 |
Token | private |
Token ID | 2839 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
joy | +0.010 |
time | +0.008 |
than | +0.008 |
minutes | +0.008 |
no | +0.008 |
Neg logit contributions | |
glers | -0.008 |
Amen | -0.007 |
aliens | -0.007 |
chers | -0.007 |
Sorry | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
joy | +0.008 |
than | +0.006 |
time | +0.006 |
no | +0.005 |
looking | +0.005 |
Neg logit contributions | |
glers | -0.010 |
Amen | -0.009 |
aliens | -0.009 |
chers | -0.009 |
Sorry | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
glers | +0.009 |
Amen | +0.009 |
Sorry | +0.009 |
chers | +0.009 |
aliens | +0.009 |
Neg logit contributions | |
joy | -0.008 |
than | -0.006 |
time | -0.005 |
no | -0.005 |
minutes | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
joy | +0.012 |
blond | +0.010 |
orm | +0.010 |
minutes | +0.009 |
time | +0.009 |
Neg logit contributions | |
glers | -0.013 |
ishly | -0.013 |
Sorry | -0.013 |
maid | -0.012 |
actresses | -0.012 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
joy | +0.057 |
time | +0.045 |
than | +0.044 |
minutes | +0.041 |
no | +0.040 |
Neg logit contributions | |
glers | -0.069 |
Amen | -0.067 |
aliens | -0.067 |
chers | -0.065 |
girls | -0.063 |
Token | her |
Token ID | 607 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
glers | +0.054 |
Amen | +0.053 |
aliens | +0.052 |
actresses | +0.051 |
maid | +0.051 |
Neg logit contributions | |
joy | -0.045 |
than | -0.034 |
looking | -0.033 |
minutes | -0.032 |
time | -0.032 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
joy | +0.023 |
looking | +0.019 |
no | +0.018 |
than | +0.018 |
time | +0.018 |
Neg logit contributions | |
glers | -0.016 |
aliens | -0.016 |
Amen | -0.015 |
chers | -0.015 |
maid | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
joy | +0.036 |
time | +0.024 |
minutes | +0.023 |
looking | +0.022 |
no | +0.022 |
Neg logit contributions | |
glers | -0.063 |
Amen | -0.062 |
ishly | -0.060 |
chers | -0.060 |
aliens | -0.059 |
Token | She |
Token ID | 1375 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
joy | +0.020 |
time | +0.016 |
than | +0.015 |
minutes | +0.014 |
no | +0.014 |
Neg logit contributions | |
glers | -0.024 |
Amen | -0.024 |
aliens | -0.023 |
chers | -0.023 |
Sorry | -0.023 |
Token | said |
Token ID | 531 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
glers | +0.001 |
Amen | +0.001 |
aliens | +0.001 |
chers | +0.001 |
Sorry | +0.001 |
Neg logit contributions | |
joy | -0.000 |
time | -0.000 |
than | -0.000 |
minutes | -0.000 |
no | -0.000 |
Token | goodbye |
Token ID | 24829 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
glers | +0.026 |
Amen | +0.025 |
aliens | +0.025 |
chers | +0.024 |
Sorry | +0.024 |
Neg logit contributions | |
joy | -0.014 |
time | -0.010 |
than | -0.009 |
minutes | -0.008 |
no | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ishly | +0.033 |
Amen | +0.030 |
maid | +0.029 |
Claus | +0.029 |
chers | +0.029 |
Neg logit contributions | |
joy | -0.023 |
time | -0.019 |
looking | -0.017 |
deliber | -0.017 |
no | -0.016 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
glers | +0.032 |
chers | +0.031 |
Amen | +0.031 |
girls | +0.031 |
aliens | +0.030 |
Neg logit contributions | |
joy | -0.025 |
time | -0.020 |
than | -0.019 |
minutes | -0.018 |
black | -0.017 |
Token | named |
Token ID | 3706 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
Amen | +0.011 |
glers | +0.011 |
aliens | +0.010 |
Sorry | +0.010 |
chers | +0.009 |
Neg logit contributions | |
joy | -0.020 |
time | -0.016 |
than | -0.015 |
no | -0.015 |
deliber | -0.015 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
joy | +0.029 |
time | +0.022 |
than | +0.021 |
minutes | +0.020 |
no | +0.019 |
Neg logit contributions | |
glers | -0.040 |
Amen | -0.039 |
aliens | -0.039 |
chers | -0.038 |
Sorry | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
joy | +0.006 |
deliber | +0.004 |
minutes | +0.004 |
time | +0.003 |
no | +0.003 |
Neg logit contributions | |
Amen | -0.010 |
aliens | -0.010 |
glers | -0.009 |
hing | -0.009 |
girls | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
joy | +0.013 |
than | +0.010 |
time | +0.009 |
no | +0.009 |
minutes | +0.009 |
Neg logit contributions | |
glers | -0.014 |
Amen | -0.013 |
aliens | -0.013 |
Sorry | -0.013 |
actresses | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
Amen | +0.017 |
glers | +0.017 |
aliens | +0.016 |
chers | +0.016 |
Sorry | +0.016 |
Neg logit contributions | |
joy | -0.018 |
than | -0.013 |
time | -0.013 |
minutes | -0.012 |
no | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
joy | +0.017 |
than | +0.012 |
-- | +0.011 |
deliber | +0.010 |
minutes | +0.010 |
Neg logit contributions | |
aliens | -0.029 |
Amen | -0.029 |
glers | -0.028 |
actresses | -0.028 |
floats | -0.028 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
joy | +0.016 |
than | +0.012 |
time | +0.011 |
minutes | +0.011 |
no | +0.011 |
Neg logit contributions | |
glers | -0.023 |
Amen | -0.023 |
aliens | -0.022 |
Sorry | -0.022 |
chers | -0.022 |
Token | named |
Token ID | 3706 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
joy | +0.055 |
time | +0.043 |
minutes | +0.042 |
no | +0.041 |
than | +0.041 |
Neg logit contributions | |
glers | -0.030 |
Amen | -0.029 |
aliens | -0.028 |
chers | -0.026 |
Sorry | -0.026 |
Token | Fl |
Token ID | 1610 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
joy | +0.038 |
than | +0.030 |
time | +0.030 |
minutes | +0.029 |
no | +0.027 |
Neg logit contributions | |
glers | -0.030 |
aliens | -0.029 |
Amen | -0.028 |
girls | -0.028 |
Sorry | -0.028 |
Token | uffy |
Token ID | 15352 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
glers | +0.010 |
Amen | +0.009 |
aliens | +0.009 |
chers | +0.009 |
Sorry | +0.009 |
Neg logit contributions | |
joy | -0.015 |
time | -0.012 |
than | -0.012 |
minutes | -0.011 |
no | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
glers | +0.032 |
aliens | +0.031 |
chers | +0.031 |
Amen | +0.030 |
Sorry | +0.030 |
Neg logit contributions | |
joy | -0.016 |
time | -0.010 |
minutes | -0.009 |
than | -0.009 |
no | -0.009 |
Token | even |
Token ID | 772 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
aliens | +0.010 |
glers | +0.010 |
Amen | +0.010 |
Sorry | +0.009 |
chers | +0.009 |
Neg logit contributions | |
joy | -0.007 |
time | -0.005 |
minutes | -0.005 |
looking | -0.005 |
no | -0.005 |
Token | if |
Token ID | 611 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
glers | +0.046 |
aliens | +0.045 |
Amen | +0.044 |
Sorry | +0.043 |
chers | +0.043 |
Neg logit contributions | |
joy | -0.042 |
time | -0.031 |
minutes | -0.029 |
than | -0.028 |
looking | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
joy | +0.001 |
time | +0.001 |
than | +0.001 |
minutes | +0.000 |
no | +0.000 |
Neg logit contributions | |
glers | -0.001 |
aliens | -0.001 |
Amen | -0.001 |
chers | -0.001 |
Sorry | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
glers | +0.008 |
Amen | +0.008 |
aliens | +0.008 |
chers | +0.007 |
Sorry | +0.007 |
Neg logit contributions | |
joy | -0.009 |
time | -0.007 |
than | -0.007 |
minutes | -0.006 |
no | -0.006 |
Token | difficult |
Token ID | 2408 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Amen | +0.036 |
glers | +0.036 |
aliens | +0.036 |
chers | +0.035 |
Sorry | +0.034 |
Neg logit contributions | |
joy | -0.030 |
looking | -0.020 |
minutes | -0.020 |
no | -0.020 |
than | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
joy | +0.015 |
looking | +0.008 |
no | +0.008 |
minutes | +0.007 |
deliber | +0.007 |
Neg logit contributions | |
aliens | -0.033 |
glers | -0.032 |
chers | -0.031 |
Sorry | -0.030 |
Amen | -0.030 |
Token | And |
Token ID | 843 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
joy | +0.007 |
time | +0.005 |
than | +0.005 |
minutes | +0.005 |
no | +0.004 |
Neg logit contributions | |
glers | -0.014 |
Amen | -0.013 |
aliens | -0.013 |
Sorry | -0.013 |
chers | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
glers | +0.048 |
aliens | +0.046 |
Amen | +0.046 |
chers | +0.046 |
Sorry | +0.046 |
Neg logit contributions | |
joy | -0.035 |
time | -0.026 |
than | -0.025 |
minutes | -0.024 |
no | -0.023 |
Token | also |
Token ID | 635 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
joy | +0.024 |
time | +0.019 |
than | +0.018 |
to | +0.016 |
-- | +0.016 |
Neg logit contributions | |
glers | -0.039 |
Amen | -0.037 |
aliens | -0.036 |
Sorry | -0.036 |
chers | -0.036 |
Token | learned |
Token ID | 4499 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
glers | +0.033 |
aliens | +0.031 |
Amen | +0.031 |
chers | +0.031 |
Sorry | +0.030 |
Neg logit contributions | |
joy | -0.025 |
time | -0.020 |
than | -0.019 |
minutes | -0.017 |
no | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
joy | +0.017 |
than | +0.012 |
time | +0.012 |
minutes | +0.012 |
no | +0.011 |
Neg logit contributions | |
glers | -0.015 |
chers | -0.014 |
Amen | -0.014 |
aliens | -0.013 |
girls | -0.013 |
Token | no |
Token ID | 645 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
aliens | +0.004 |
glers | +0.004 |
Amen | +0.004 |
Sorry | +0.004 |
floats | +0.004 |
Neg logit contributions | |
joy | -0.004 |
than | -0.003 |
minutes | -0.003 |
time | -0.003 |
looking | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
glers | +0.004 |
aliens | +0.004 |
actresses | +0.004 |
floats | +0.004 |
inas | +0.004 |
Neg logit contributions | |
joy | -0.003 |
minutes | -0.001 |
blond | -0.001 |
deliber | -0.001 |
time | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
joy | +0.022 |
than | +0.018 |
time | +0.018 |
minutes | +0.017 |
looking | +0.017 |
Neg logit contributions | |
glers | -0.024 |
Sorry | -0.023 |
aliens | -0.023 |
actresses | -0.022 |
girls | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
joy | +0.008 |
than | +0.006 |
minutes | +0.005 |
yet | +0.005 |
blond | +0.005 |
Neg logit contributions | |
glers | -0.011 |
aliens | -0.010 |
Amen | -0.010 |
chers | -0.010 |
actresses | -0.010 |
Token | Tony |
Token ID | 29387 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
joy | +0.004 |
than | +0.003 |
time | +0.003 |
minutes | +0.003 |
yet | +0.003 |
Neg logit contributions | |
glers | -0.004 |
aliens | -0.004 |
chers | -0.004 |
actresses | -0.004 |
Sorry | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
joy | +0.024 |
than | +0.018 |
time | +0.017 |
no | +0.017 |
minutes | +0.016 |
Neg logit contributions | |
glers | -0.020 |
chers | -0.019 |
aliens | -0.019 |
Amen | -0.019 |
floats | -0.018 |
Token | angry |
Token ID | 7954 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Amen | +0.003 |
glers | +0.002 |
aliens | +0.002 |
chers | +0.002 |
actresses | +0.002 |
Neg logit contributions | |
joy | -0.003 |
than | -0.002 |
looking | -0.002 |
orm | -0.002 |
no | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
joy | +0.009 |
blond | +0.007 |
deliber | +0.007 |
eating | +0.007 |
orm | +0.007 |
Neg logit contributions | |
aliens | -0.008 |
sisters | -0.007 |
glers | -0.007 |
ishly | -0.007 |
off | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
joy | +0.035 |
looking | +0.023 |
time | +0.023 |
orm | +0.022 |
minutes | +0.022 |
Neg logit contributions | |
glers | -0.042 |
ishly | -0.041 |
aliens | -0.040 |
floats | -0.040 |
actresses | -0.039 |
Token | he |
Token ID | 339 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
glers | +0.035 |
Sorry | +0.034 |
actresses | +0.034 |
aliens | +0.033 |
Amen | +0.031 |
Neg logit contributions | |
joy | -0.029 |
than | -0.023 |
looking | -0.022 |
time | -0.021 |
minutes | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
joy | +0.018 |
time | +0.011 |
than | +0.010 |
minutes | +0.009 |
no | +0.009 |
Neg logit contributions | |
glers | -0.044 |
aliens | -0.043 |
Amen | -0.042 |
chers | -0.042 |
Sorry | -0.041 |
Token | When |
Token ID | 1649 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
glers | +0.012 |
Amen | +0.012 |
aliens | +0.011 |
chers | +0.011 |
Sorry | +0.011 |
Neg logit contributions | |
joy | -0.008 |
time | -0.006 |
than | -0.006 |
minutes | -0.005 |
no | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
glers | +0.035 |
chers | +0.034 |
Amen | +0.034 |
aliens | +0.034 |
girls | +0.033 |
Neg logit contributions | |
joy | -0.020 |
time | -0.015 |
than | -0.013 |
minutes | -0.013 |
no | -0.012 |
Token | finally |
Token ID | 3443 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
glers | +0.021 |
Amen | +0.020 |
aliens | +0.020 |
chers | +0.020 |
girls | +0.020 |
Neg logit contributions | |
joy | -0.014 |
time | -0.012 |
than | -0.011 |
minutes | -0.010 |
to | -0.010 |
Token | finished |
Token ID | 5201 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
joy | +0.019 |
than | +0.015 |
time | +0.014 |
minutes | +0.014 |
no | +0.014 |
Neg logit contributions | |
glers | -0.019 |
aliens | -0.017 |
Amen | -0.017 |
chers | -0.017 |
Sorry | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
joy | +0.045 |
than | +0.034 |
minutes | +0.033 |
looking | +0.032 |
time | +0.032 |
Neg logit contributions | |
glers | -0.062 |
Sorry | -0.058 |
actresses | -0.058 |
aliens | -0.058 |
Amen | -0.058 |
Token | journal |
Token ID | 3989 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
joy | +0.025 |
than | +0.020 |
no | +0.018 |
looking | +0.018 |
minutes | +0.018 |
Neg logit contributions | |
aliens | -0.023 |
Sorry | -0.023 |
glers | -0.022 |
Amen | -0.022 |
floats | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
joy | +0.017 |
time | +0.011 |
than | +0.011 |
minutes | +0.010 |
no | +0.010 |
Neg logit contributions | |
glers | -0.031 |
aliens | -0.030 |
chers | -0.030 |
Sorry | -0.029 |
Amen | -0.029 |
Token | she |
Token ID | 673 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
glers | +0.009 |
aliens | +0.008 |
Amen | +0.008 |
chers | +0.008 |
Sorry | +0.008 |
Neg logit contributions | |
joy | -0.005 |
time | -0.003 |
than | -0.003 |
minutes | -0.003 |
no | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
joy | +0.001 |
time | +0.001 |
to | +0.001 |
than | +0.000 |
minutes | +0.000 |
Neg logit contributions | |
glers | -0.001 |
girls | -0.001 |
Amen | -0.001 |
chers | -0.001 |
igators | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
joy | +0.007 |
time | +0.005 |
than | +0.005 |
minutes | +0.005 |
no | +0.005 |
Neg logit contributions | |
glers | -0.010 |
Amen | -0.010 |
aliens | -0.010 |
chers | -0.010 |
Sorry | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
joy | +0.019 |
time | +0.013 |
than | +0.012 |
minutes | +0.011 |
no | +0.010 |
Neg logit contributions | |
glers | -0.041 |
Amen | -0.040 |
aliens | -0.039 |
chers | -0.039 |
Sorry | -0.039 |
Token | But |
Token ID | 887 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
joy | +0.002 |
than | +0.001 |
time | +0.001 |
no | +0.001 |
minutes | +0.001 |
Neg logit contributions | |
Sorry | -0.002 |
glers | -0.002 |
aliens | -0.002 |
Amen | -0.002 |
actresses | -0.002 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
joy | +0.013 |
than | +0.009 |
time | +0.009 |
looking | +0.009 |
no | +0.008 |
Neg logit contributions | |
glers | -0.014 |
Sorry | -0.014 |
aliens | -0.014 |
Amen | -0.013 |
chers | -0.013 |
Token | didn |
Token ID | 1422 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
joy | +0.023 |
than | +0.018 |
looking | +0.017 |
sight | +0.017 |
minutes | +0.017 |
Neg logit contributions | |
glers | -0.017 |
chers | -0.016 |
ishly | -0.016 |
girls | -0.015 |
maid | -0.015 |
Token | 't |
Token ID | 470 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
joy | +0.023 |
time | +0.021 |
no | +0.019 |
than | +0.019 |
to | +0.019 |
Neg logit contributions | |
glers | -0.019 |
aliens | -0.019 |
chers | -0.018 |
maid | -0.018 |
Amen | -0.018 |
Token | like |
Token ID | 588 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
joy | +0.002 |
time | +0.001 |
minutes | +0.001 |
than | +0.001 |
no | +0.001 |
Neg logit contributions | |
glers | -0.002 |
Amen | -0.002 |
aliens | -0.002 |
chers | -0.002 |
Sorry | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
joy | +0.140 |
than | +0.098 |
looking | +0.089 |
minutes | +0.088 |
time | +0.087 |
Neg logit contributions | |
aliens | -0.179 |
glers | -0.173 |
floats | -0.172 |
actresses | -0.168 |
igators | -0.161 |
Token | idea |
Token ID | 2126 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
glers | +0.023 |
aliens | +0.023 |
Amen | +0.022 |
Sorry | +0.022 |
floats | +0.022 |
Neg logit contributions | |
joy | -0.015 |
looking | -0.009 |
deliber | -0.009 |
seen | -0.008 |
blond | -0.008 |
Token | either |
Token ID | 2035 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
aliens | +0.027 |
glers | +0.026 |
chers | +0.026 |
floats | +0.025 |
Sorry | +0.024 |
Neg logit contributions | |
joy | -0.023 |
deliber | -0.015 |
no | -0.015 |
looking | -0.014 |
orm | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
joy | +0.005 |
minutes | +0.003 |
than | +0.003 |
deliber | +0.003 |
time | +0.003 |
Neg logit contributions | |
glers | -0.008 |
aliens | -0.008 |
Amen | -0.007 |
ishly | -0.007 |
Sorry | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
joy | +0.017 |
than | +0.015 |
time | +0.014 |
minutes | +0.014 |
no | +0.013 |
Neg logit contributions | |
Sorry | -0.015 |
glers | -0.014 |
Amen | -0.013 |
aliens | -0.013 |
actresses | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
joy | +0.033 |
than | +0.025 |
time | +0.025 |
minutes | +0.024 |
looking | +0.021 |
Neg logit contributions | |
Sorry | -0.049 |
glers | -0.049 |
Amen | -0.048 |
aliens | -0.047 |
actresses | -0.046 |
Token | little |
Token ID | 1310 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
joy | +0.020 |
than | +0.015 |
no | +0.014 |
time | +0.013 |
-- | +0.013 |
Neg logit contributions | |
glers | -0.030 |
aliens | -0.029 |
Amen | -0.029 |
chers | -0.028 |
floats | -0.028 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
glers | +0.046 |
aliens | +0.045 |
Amen | +0.043 |
floats | +0.042 |
Sorry | +0.042 |
Neg logit contributions | |
joy | -0.069 |
than | -0.057 |
no | -0.056 |
time | -0.056 |
looking | -0.053 |
Token | happily |
Token ID | 18177 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
glers | +0.056 |
Amen | +0.054 |
chers | +0.053 |
aliens | +0.053 |
Sorry | +0.052 |
Neg logit contributions | |
joy | -0.058 |
time | -0.045 |
than | -0.044 |
minutes | -0.042 |
no | -0.041 |
Token | began |
Token ID | 2540 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
glers | +0.046 |
Amen | +0.044 |
aliens | +0.044 |
chers | +0.044 |
Sorry | +0.043 |
Neg logit contributions | |
joy | -0.045 |
time | -0.036 |
than | -0.035 |
minutes | -0.033 |
no | -0.032 |
Token | counting |
Token ID | 14143 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
joy | +0.029 |
looking | +0.024 |
minutes | +0.021 |
orm | +0.021 |
than | +0.021 |
Neg logit contributions | |
glers | -0.058 |
actresses | -0.055 |
aliens | -0.054 |
sisters | -0.053 |
remote | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
joy | +0.144 |
looking | +0.107 |
deliber | +0.104 |
minutes | +0.099 |
time | +0.098 |
Neg logit contributions | |
glers | -0.191 |
aliens | -0.186 |
floats | -0.166 |
girls | -0.164 |
chers | -0.163 |
Token | colorful |
Token ID | 20239 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
joy | +0.063 |
no | +0.047 |
than | +0.047 |
time | +0.045 |
-- | +0.044 |
Neg logit contributions | |
glers | -0.072 |
aliens | -0.070 |
floats | -0.068 |
chers | -0.066 |
Amen | -0.065 |
Token | pet |
Token ID | 4273 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
joy | +0.089 |
time | +0.071 |
than | +0.069 |
minutes | +0.065 |
no | +0.063 |
Neg logit contributions | |
glers | -0.090 |
Amen | -0.087 |
aliens | -0.086 |
chers | -0.085 |
Sorry | -0.083 |
Token | als |
Token ID | 874 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
joy | +0.109 |
time | +0.093 |
than | +0.091 |
minutes | +0.087 |
no | +0.086 |
Neg logit contributions | |
glers | -0.052 |
Amen | -0.050 |
aliens | -0.048 |
chers | -0.048 |
Sorry | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
joy | +0.043 |
time | +0.029 |
than | +0.027 |
minutes | +0.027 |
no | +0.026 |
Neg logit contributions | |
glers | -0.074 |
aliens | -0.070 |
chers | -0.069 |
Amen | -0.067 |
floats | -0.066 |
Token | not |
Token ID | 407 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
joy | +0.025 |
time | +0.018 |
than | +0.017 |
minutes | +0.016 |
no | +0.016 |
Neg logit contributions | |
glers | -0.041 |
aliens | -0.039 |
Amen | -0.039 |
Sorry | -0.039 |
chers | -0.038 |
Token | sand |
Token ID | 6450 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
joy | +0.027 |
time | +0.019 |
minutes | +0.018 |
no | +0.018 |
than | +0.018 |
Neg logit contributions | |
glers | -0.037 |
aliens | -0.037 |
Amen | -0.035 |
Sorry | -0.035 |
chers | -0.035 |
Token | like |
Token ID | 588 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
joy | +0.028 |
time | +0.018 |
minutes | +0.017 |
deliber | +0.017 |
no | +0.017 |
Neg logit contributions | |
glers | -0.055 |
aliens | -0.051 |
chers | -0.050 |
maid | -0.050 |
floats | -0.049 |
Token | he |
Token ID | 339 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
joy | +0.114 |
than | +0.083 |
looking | +0.077 |
minutes | +0.076 |
deliber | +0.074 |
Neg logit contributions | |
glers | -0.150 |
aliens | -0.150 |
floats | -0.142 |
Sorry | -0.140 |
igators | -0.137 |
Token | had |
Token ID | 550 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
joy | +0.047 |
minutes | +0.033 |
than | +0.032 |
time | +0.032 |
deliber | +0.032 |
Neg logit contributions | |
glers | -0.039 |
chers | -0.037 |
aliens | -0.036 |
floats | -0.035 |
Sorry | -0.035 |
Token | imagined |
Token ID | 15758 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
joy | +0.075 |
deliber | +0.052 |
no | +0.049 |
looking | +0.049 |
minutes | +0.048 |
Neg logit contributions | |
glers | -0.074 |
aliens | -0.073 |
floats | -0.070 |
chers | -0.070 |
maid | -0.066 |
Token | ! |
Token ID | 0 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
joy | +0.119 |
deliber | +0.075 |
minutes | +0.075 |
time | +0.074 |
looking | +0.069 |
Neg logit contributions | |
glers | -0.209 |
aliens | -0.198 |
chers | -0.196 |
ics | -0.192 |
floats | -0.190 |
Token | He |
Token ID | 679 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
joy | +0.015 |
than | +0.012 |
time | +0.011 |
minutes | +0.011 |
no | +0.010 |
Neg logit contributions | |
Amen | -0.021 |
glers | -0.021 |
Sorry | -0.021 |
aliens | -0.020 |
chers | -0.020 |
Token | laughed |
Token ID | 13818 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
joy | +0.012 |
time | +0.010 |
than | +0.009 |
minutes | +0.009 |
no | +0.009 |
Neg logit contributions | |
glers | -0.015 |
Amen | -0.014 |
aliens | -0.014 |
chers | -0.014 |
Sorry | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
aliens | +0.002 |
glers | +0.002 |
Amen | +0.001 |
chers | +0.001 |
maid | +0.001 |
Neg logit contributions | |
joy | -0.001 |
time | -0.001 |
minutes | -0.001 |
no | -0.001 |
looking | -0.001 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
joy | +0.040 |
time | +0.033 |
than | +0.031 |
minutes | +0.030 |
no | +0.029 |
Neg logit contributions | |
glers | -0.037 |
Amen | -0.035 |
aliens | -0.035 |
chers | -0.035 |
Sorry | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
joy | +0.005 |
time | +0.004 |
than | +0.003 |
minutes | +0.003 |
no | +0.003 |
Neg logit contributions | |
glers | -0.008 |
Amen | -0.008 |
aliens | -0.007 |
Sorry | -0.007 |
chers | -0.007 |
Token | gives |
Token ID | 3607 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
glers | +0.015 |
Amen | +0.015 |
Sorry | +0.014 |
hing | +0.014 |
arse | +0.014 |
Neg logit contributions | |
joy | -0.013 |
time | -0.011 |
to | -0.010 |
minutes | -0.010 |
old | -0.009 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
glers | +0.034 |
Amen | +0.034 |
chers | +0.034 |
Sorry | +0.033 |
aliens | +0.033 |
Neg logit contributions | |
joy | -0.016 |
time | -0.012 |
than | -0.010 |
to | -0.010 |
minutes | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
joy | +0.036 |
time | +0.025 |
than | +0.025 |
minutes | +0.024 |
no | +0.024 |
Neg logit contributions | |
glers | -0.057 |
aliens | -0.055 |
chers | -0.054 |
Amen | -0.054 |
girls | -0.053 |
Token | high |
Token ID | 1029 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
joy | +0.016 |
time | +0.013 |
than | +0.013 |
minutes | +0.012 |
no | +0.012 |
Neg logit contributions | |
glers | -0.016 |
aliens | -0.015 |
Amen | -0.015 |
chers | -0.015 |
Sorry | -0.015 |
Token | five |
Token ID | 1936 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
joy | +0.096 |
than | +0.068 |
minutes | +0.068 |
seen | +0.067 |
no | +0.067 |
Neg logit contributions | |
Amen | -0.103 |
maid | -0.097 |
glers | -0.095 |
Sorry | -0.092 |
aliens | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
joy | +0.132 |
no | +0.078 |
time | +0.074 |
deliber | +0.073 |
looking | +0.071 |
Neg logit contributions | |
glers | -0.214 |
aliens | -0.209 |
Amen | -0.206 |
chers | -0.205 |
igators | -0.203 |
Token |
|
Token ID | 198 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
joy | +0.012 |
than | +0.009 |
time | +0.009 |
no | +0.008 |
minutes | +0.008 |
Neg logit contributions | |
glers | -0.019 |
Amen | -0.019 |
aliens | -0.019 |
Sorry | -0.018 |
chers | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
joy | +0.006 |
time | +0.004 |
than | +0.004 |
minutes | +0.003 |
no | +0.003 |
Neg logit contributions | |
glers | -0.012 |
Amen | -0.012 |
aliens | -0.012 |
chers | -0.012 |
Sorry | -0.012 |
Token | They |
Token ID | 2990 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
joy | +0.003 |
time | +0.002 |
than | +0.002 |
minutes | +0.002 |
no | +0.002 |
Neg logit contributions | |
glers | -0.007 |
aliens | -0.007 |
Amen | -0.006 |
chers | -0.006 |
girls | -0.006 |
Token | finish |
Token ID | 5461 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
aliens | +0.010 |
chers | +0.010 |
Amen | +0.009 |
Sorry | +0.009 |
glers | +0.009 |
Neg logit contributions | |
time | -0.007 |
joy | -0.007 |
che | -0.007 |
like | -0.007 |
to | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
joy | +0.019 |
than | +0.014 |
deliber | +0.014 |
looking | +0.013 |
minutes | +0.013 |
Neg logit contributions | |
aliens | -0.023 |
glers | -0.022 |
chers | -0.021 |
girls | -0.021 |
floats | -0.020 |
Token | button |
Token ID | 4936 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
glers | +0.033 |
aliens | +0.031 |
Amen | +0.031 |
chers | +0.031 |
Sorry | +0.031 |
Neg logit contributions | |
joy | -0.032 |
time | -0.024 |
than | -0.024 |
no | -0.022 |
minutes | -0.022 |
Token | with |
Token ID | 351 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
joy | +0.009 |
deliber | +0.006 |
time | +0.006 |
no | +0.005 |
looking | +0.005 |
Neg logit contributions | |
glers | -0.013 |
aliens | -0.013 |
chers | -0.013 |
floats | -0.012 |
hing | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
joy | +0.020 |
than | +0.014 |
looking | +0.013 |
deliber | +0.013 |
-- | +0.013 |
Neg logit contributions | |
aliens | -0.028 |
glers | -0.026 |
floats | -0.026 |
remote | -0.025 |
actresses | -0.025 |
Token | number |
Token ID | 1271 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
joy | +0.067 |
deliber | +0.051 |
than | +0.051 |
-- | +0.050 |
time | +0.048 |
Neg logit contributions | |
remote | -0.061 |
aliens | -0.060 |
glers | -0.060 |
chers | -0.059 |
floats | -0.058 |
Token | six |
Token ID | 2237 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
joy | +0.091 |
time | +0.058 |
deliber | +0.057 |
no | +0.052 |
looking | +0.050 |
Neg logit contributions | |
glers | -0.127 |
aliens | -0.124 |
chers | -0.121 |
floats | -0.120 |
Sorry | -0.116 |
Token | on |
Token ID | 319 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
joy | +0.203 |
deliber | +0.148 |
looking | +0.142 |
late | +0.139 |
no | +0.137 |
Neg logit contributions | |
floats | -0.171 |
aliens | -0.167 |
glers | -0.154 |
chers | -0.153 |
remote | -0.150 |
Token | it |
Token ID | 340 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
joy | +0.083 |
than | +0.060 |
deliber | +0.057 |
looking | +0.056 |
-- | +0.055 |
Neg logit contributions | |
aliens | -0.068 |
floats | -0.063 |
glers | -0.061 |
Sorry | -0.061 |
remote | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
joy | +0.053 |
time | +0.028 |
no | +0.027 |
deliber | +0.027 |
minutes | +0.027 |
Neg logit contributions | |
glers | -0.096 |
aliens | -0.094 |
chers | -0.092 |
Sorry | -0.090 |
girls | -0.090 |
Token | She |
Token ID | 1375 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
joy | +0.002 |
than | +0.002 |
seen | +0.002 |
minutes | +0.002 |
time | +0.002 |
Neg logit contributions | |
Sorry | -0.002 |
aliens | -0.002 |
actresses | -0.002 |
floats | -0.002 |
glers | -0.002 |
Token | hears |
Token ID | 23180 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
glers | +0.019 |
Amen | +0.018 |
aliens | +0.018 |
chers | +0.018 |
Sorry | +0.017 |
Neg logit contributions | |
joy | -0.019 |
time | -0.015 |
than | -0.015 |
minutes | -0.014 |
no | -0.014 |