Token | by |
Token ID | 416 |
Feature activation | +9.11e+00 |
Pos logit contributions | |
Here | +0.033 |
Watch | +0.030 |
Majesty | +0.029 |
First | +0.029 |
disl | +0.029 |
Neg logit contributions | |
ier | -0.045 |
again | -0.044 |
anymore | -0.043 |
ge | -0.041 |
than | -0.041 |
Token | one |
Token ID | 530 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
Here | +0.161 |
First | +0.154 |
Many | +0.144 |
Watch | +0.141 |
Everyone | +0.137 |
Neg logit contributions | |
ier | -0.175 |
than | -0.147 |
again | -0.146 |
ge | -0.144 |
anymore | -0.144 |
Token | � |
Token ID | 6184 |
Feature activation | +8.89e+00 |
Pos logit contributions | |
Here | +0.115 |
Watch | +0.107 |
Everyone | +0.105 |
Many | +0.105 |
First | +0.104 |
Neg logit contributions | |
ier | -0.083 |
ge | -0.069 |
than | -0.050 |
y | -0.049 |
m | -0.049 |
Token | � |
Token ID | 95 |
Feature activation | +9.28e+00 |
Pos logit contributions | |
Here | +0.114 |
First | +0.113 |
Many | +0.106 |
ossible | +0.099 |
Watch | +0.097 |
Neg logit contributions | |
ier | -0.196 |
than | -0.174 |
anymore | -0.171 |
again | -0.169 |
ge | -0.166 |
Token | € |
Token ID | 26391 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
Here | +0.107 |
First | +0.102 |
Many | +0.093 |
Remy | +0.085 |
Fin | +0.085 |
Neg logit contributions | |
ier | -0.226 |
than | -0.200 |
again | -0.191 |
anymore | -0.191 |
ge | -0.185 |
Token | � |
Token ID | 447 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
First | +0.153 |
Here | +0.149 |
Many | +0.131 |
Watch | +0.126 |
Fin | +0.122 |
Neg logit contributions | |
ier | -0.193 |
than | -0.190 |
again | -0.185 |
anymore | -0.178 |
. | -0.178 |
Token | � |
Token ID | 250 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
First | +0.184 |
Here | +0.177 |
Many | +0.170 |
Watch | +0.156 |
disl | +0.151 |
Neg logit contributions | |
ier | -0.286 |
again | -0.263 |
m | -0.245 |
anymore | -0.244 |
than | -0.240 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Here | +0.153 |
First | +0.144 |
Many | +0.133 |
Watch | +0.130 |
Everyone | +0.127 |
Neg logit contributions | |
ier | -0.238 |
than | -0.203 |
ge | -0.202 |
again | -0.202 |
anymore | -0.199 |
Token | , |
Token ID | 11 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
Here | +0.033 |
First | +0.031 |
Many | +0.030 |
Watch | +0.029 |
Everyone | +0.029 |
Neg logit contributions | |
ier | -0.028 |
ge | -0.023 |
again | -0.022 |
anymore | -0.022 |
than | -0.022 |
Token | 2 |
Token ID | 362 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Here | +0.097 |
First | +0.090 |
Many | +0.084 |
Watch | +0.081 |
Everyone | +0.080 |
Neg logit contributions | |
ier | -0.138 |
again | -0.118 |
than | -0.118 |
ge | -0.116 |
anymore | -0.115 |
Token | , |
Token ID | 11 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
Here | +0.054 |
First | +0.052 |
Many | +0.049 |
Watch | +0.049 |
Everyone | +0.048 |
Neg logit contributions | |
ier | -0.044 |
ge | -0.035 |
anymore | -0.034 |
again | -0.034 |
than | -0.034 |
Token | perfect |
Token ID | 2818 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
Here | +0.165 |
First | +0.156 |
Many | +0.147 |
Watch | +0.146 |
Everyone | +0.142 |
Neg logit contributions | |
ier | -0.174 |
ge | -0.142 |
again | -0.137 |
than | -0.137 |
anymore | -0.136 |
Token | bag |
Token ID | 6131 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
Here | +0.104 |
First | +0.099 |
Watch | +0.095 |
Majesty | +0.093 |
Everyone | +0.091 |
Neg logit contributions | |
ier | -0.096 |
ge | -0.077 |
anymore | -0.069 |
than | -0.068 |
again | -0.066 |
Token | � |
Token ID | 6184 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
Here | +0.017 |
First | +0.016 |
Everyone | +0.016 |
This | +0.016 |
Watch | +0.015 |
Neg logit contributions | |
ier | -0.009 |
ge | -0.008 |
anymore | -0.007 |
than | -0.007 |
again | -0.007 |
Token | � |
Token ID | 95 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
Here | +0.096 |
First | +0.090 |
Many | +0.088 |
disl | +0.083 |
Watch | +0.081 |
Neg logit contributions | |
ier | -0.155 |
again | -0.133 |
than | -0.132 |
anymore | -0.131 |
ge | -0.129 |
Token | € |
Token ID | 26391 |
Feature activation | +9.46e+00 |
Pos logit contributions | |
Here | +0.105 |
First | +0.099 |
Many | +0.093 |
Fin | +0.090 |
Remy | +0.090 |
Neg logit contributions | |
ier | -0.196 |
than | -0.169 |
again | -0.164 |
anymore | -0.161 |
ge | -0.158 |
Token | � |
Token ID | 447 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
Here | +0.141 |
First | +0.141 |
Many | +0.122 |
Fin | +0.116 |
Watch | +0.116 |
Neg logit contributions | |
ier | -0.182 |
than | -0.176 |
again | -0.171 |
on | -0.164 |
anymore | -0.163 |
Token | � |
Token ID | 250 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
First | +0.180 |
Here | +0.173 |
Many | +0.169 |
disl | +0.161 |
Remy | +0.150 |
Neg logit contributions | |
ier | -0.280 |
again | -0.262 |
m | -0.247 |
on | -0.241 |
anymore | -0.234 |
Token | now |
Token ID | 783 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
Here | +0.143 |
First | +0.134 |
Many | +0.124 |
Watch | +0.121 |
Everyone | +0.118 |
Neg logit contributions | |
ier | -0.242 |
than | -0.206 |
ge | -0.205 |
again | -0.205 |
anymore | -0.202 |
Token | I |
Token ID | 314 |
Feature activation | +7.75e+00 |
Pos logit contributions | |
Here | +0.089 |
First | +0.083 |
Many | +0.079 |
Watch | +0.073 |
Everyone | +0.071 |
Neg logit contributions | |
ier | -0.138 |
again | -0.122 |
than | -0.121 |
anymore | -0.118 |
ge | -0.116 |
Token | 'm |
Token ID | 1101 |
Feature activation | +7.46e+00 |
Pos logit contributions | |
Here | +0.119 |
First | +0.114 |
Many | +0.106 |
Watch | +0.104 |
Everyone | +0.102 |
Neg logit contributions | |
ier | -0.168 |
ge | -0.139 |
than | -0.138 |
anymore | -0.136 |
again | -0.135 |
Token | very |
Token ID | 845 |
Feature activation | +9.11e+00 |
Pos logit contributions | |
Here | +0.162 |
First | +0.155 |
Many | +0.148 |
Watch | +0.145 |
Everyone | +0.141 |
Neg logit contributions | |
ier | -0.116 |
again | -0.091 |
than | -0.088 |
anymore | -0.088 |
ge | -0.087 |
Token | it |
Token ID | 340 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Here | +0.096 |
First | +0.090 |
Many | +0.085 |
Watch | +0.082 |
Everyone | +0.079 |
Neg logit contributions | |
ier | -0.144 |
again | -0.123 |
than | -0.122 |
ge | -0.121 |
anymore | -0.121 |
Token | forever |
Token ID | 8097 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
Here | +0.029 |
First | +0.028 |
Watch | +0.026 |
ossible | +0.025 |
The | +0.025 |
Neg logit contributions | |
ier | -0.024 |
ge | -0.019 |
y | -0.017 |
than | -0.017 |
anymore | -0.017 |
Token | � |
Token ID | 6184 |
Feature activation | +8.21e+00 |
Pos logit contributions | |
Here | +0.088 |
First | +0.084 |
Many | +0.078 |
Watch | +0.078 |
The | +0.077 |
Neg logit contributions | |
ier | -0.084 |
ge | -0.066 |
anymore | -0.063 |
than | -0.063 |
y | -0.062 |
Token | � |
Token ID | 95 |
Feature activation | +9.22e+00 |
Pos logit contributions | |
Here | +0.120 |
First | +0.112 |
disl | +0.104 |
Many | +0.104 |
Watch | +0.100 |
Neg logit contributions | |
ier | -0.177 |
again | -0.152 |
anymore | -0.152 |
ge | -0.142 |
than | -0.142 |
Token | € |
Token ID | 26391 |
Feature activation | +9.78e+00 |
Pos logit contributions | |
Here | +0.125 |
First | +0.116 |
Many | +0.110 |
Fin | +0.105 |
Remy | +0.104 |
Neg logit contributions | |
ier | -0.211 |
than | -0.179 |
again | -0.178 |
anymore | -0.175 |
ge | -0.165 |
Token | � |
Token ID | 447 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
First | +0.149 |
Here | +0.146 |
Many | +0.127 |
Watch | +0.120 |
Fin | +0.119 |
Neg logit contributions | |
ier | -0.189 |
than | -0.185 |
again | -0.180 |
anymore | -0.174 |
on | -0.167 |
Token | � |
Token ID | 250 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
First | +0.173 |
Here | +0.167 |
Many | +0.165 |
disl | +0.150 |
Watch | +0.146 |
Neg logit contributions | |
ier | -0.290 |
again | -0.270 |
m | -0.250 |
anymore | -0.243 |
on | -0.239 |
Token | things |
Token ID | 1243 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Here | +0.138 |
First | +0.127 |
Many | +0.118 |
Watch | +0.115 |
Everyone | +0.110 |
Neg logit contributions | |
ier | -0.247 |
anymore | -0.209 |
ge | -0.207 |
again | -0.206 |
than | -0.205 |
Token | are |
Token ID | 389 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
Here | +0.037 |
First | +0.035 |
Watch | +0.033 |
Everyone | +0.032 |
This | +0.032 |
Neg logit contributions | |
ier | -0.046 |
ge | -0.039 |
than | -0.037 |
again | -0.037 |
anymore | -0.037 |
Token | only |
Token ID | 691 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
Here | +0.113 |
First | +0.108 |
Watch | +0.101 |
Everyone | +0.099 |
This | +0.098 |
Neg logit contributions | |
ier | -0.105 |
ge | -0.091 |
y | -0.083 |
again | -0.082 |
anymore | -0.082 |
Token | available |
Token ID | 1695 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Here | +0.091 |
First | +0.087 |
This | +0.081 |
Watch | +0.081 |
Many | +0.079 |
Neg logit contributions | |
ier | -0.081 |
ge | -0.067 |
anymore | -0.064 |
again | -0.062 |
than | -0.058 |
Token | those |
Token ID | 883 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
Here | +0.050 |
First | +0.049 |
Majesty | +0.048 |
Watch | +0.047 |
disl | +0.045 |
Neg logit contributions | |
ier | -0.068 |
again | -0.066 |
anymore | -0.064 |
than | -0.062 |
ever | -0.057 |
Token | in |
Token ID | 287 |
Feature activation | +8.67e+00 |
Pos logit contributions | |
Here | +0.168 |
First | +0.158 |
Everyone | +0.151 |
Many | +0.150 |
Watch | +0.148 |
Neg logit contributions | |
ier | -0.152 |
ge | -0.127 |
again | -0.120 |
anymore | -0.117 |
than | -0.115 |
Token | need |
Token ID | 761 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
Here | +0.139 |
First | +0.133 |
Many | +0.125 |
Watch | +0.122 |
Everyone | +0.122 |
Neg logit contributions | |
ier | -0.183 |
ge | -0.149 |
again | -0.144 |
anymore | -0.143 |
than | -0.143 |
Token | â |
Token ID | 22940 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
Here | +0.095 |
First | +0.094 |
Everyone | +0.087 |
Many | +0.086 |
Watch | +0.084 |
Neg logit contributions | |
ier | -0.094 |
ge | -0.079 |
than | -0.074 |
y | -0.072 |
anymore | -0.072 |
Token | € |
Token ID | 26391 |
Feature activation | +9.68e+00 |
Pos logit contributions | |
Here | +0.161 |
First | +0.150 |
Many | +0.142 |
Watch | +0.139 |
Everyone | +0.133 |
Neg logit contributions | |
ier | -0.226 |
ge | -0.187 |
again | -0.187 |
than | -0.186 |
anymore | -0.185 |
Token | � |
Token ID | 447 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
Here | +0.173 |
First | +0.166 |
Many | +0.152 |
Watch | +0.152 |
Higher | +0.140 |
Neg logit contributions | |
ier | -0.178 |
than | -0.159 |
anymore | -0.155 |
again | -0.155 |
ge | -0.152 |
Token | � |
Token ID | 251 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
Here | +0.149 |
First | +0.141 |
Many | +0.135 |
Watch | +0.127 |
disl | +0.116 |
Neg logit contributions | |
ier | -0.314 |
again | -0.281 |
anymore | -0.268 |
ge | -0.265 |
y | -0.261 |
Token | even |
Token ID | 10197 |
Feature activation | +7.57e+00 |
Pos logit contributions | |
Here | +0.146 |
First | +0.136 |
Many | +0.128 |
Watch | +0.124 |
Majesty | +0.119 |
Neg logit contributions | |
ier | -0.245 |
again | -0.224 |
than | -0.213 |
anymore | -0.210 |
on | -0.207 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
Here | +0.159 |
First | +0.153 |
Many | +0.148 |
Watch | +0.145 |
Everyone | +0.144 |
Neg logit contributions | |
ier | -0.116 |
ge | -0.091 |
than | -0.089 |
anymore | -0.089 |
again | -0.087 |
Token | One |
Token ID | 3198 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
Here | +0.112 |
First | +0.108 |
Many | +0.098 |
Watch | +0.097 |
Majesty | +0.093 |
Neg logit contributions | |
ier | -0.146 |
again | -0.131 |
anymore | -0.126 |
than | -0.123 |
on | -0.121 |
Token | day |
Token ID | 1110 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
Here | +0.123 |
First | +0.118 |
Many | +0.115 |
Everyone | +0.112 |
Watch | +0.111 |
Neg logit contributions | |
ier | -0.083 |
ge | -0.063 |
than | -0.061 |
again | -0.059 |
anymore | -0.059 |
Token | When |
Token ID | 1649 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
Majesty | +0.117 |
lder | +0.115 |
disl | +0.114 |
rac | +0.112 |
majesty | +0.109 |
Neg logit contributions | |
again | -0.189 |
. | -0.181 |
than | -0.178 |
on | -0.176 |
anymore | -0.172 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
Here | +0.134 |
First | +0.126 |
Many | +0.121 |
Watch | +0.118 |
Everyone | +0.115 |
Neg logit contributions | |
ier | -0.127 |
again | -0.106 |
than | -0.103 |
anymore | -0.103 |
ge | -0.102 |
Token | put |
Token ID | 1234 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
Here | +0.073 |
First | +0.069 |
Many | +0.066 |
Watch | +0.065 |
Everyone | +0.064 |
Neg logit contributions | |
ier | -0.068 |
than | -0.055 |
ge | -0.054 |
anymore | -0.053 |
again | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Here | +0.058 |
First | +0.056 |
Watch | +0.052 |
Everyone | +0.052 |
Many | +0.051 |
Neg logit contributions | |
ier | -0.043 |
ge | -0.035 |
than | -0.032 |
anymore | -0.031 |
again | -0.030 |
Token | magn |
Token ID | 7842 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Here | +0.065 |
First | +0.059 |
Watch | +0.058 |
Many | +0.056 |
Everyone | +0.054 |
Neg logit contributions | |
ier | -0.081 |
ge | -0.070 |
anymore | -0.066 |
than | -0.066 |
again | -0.064 |
Token | ifying |
Token ID | 4035 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
Here | +0.008 |
First | +0.007 |
This | +0.007 |
Watch | +0.007 |
Everyone | +0.007 |
Neg logit contributions | |
ier | -0.008 |
than | -0.007 |
ge | -0.007 |
anymore | -0.007 |
again | -0.006 |
Token | glass |
Token ID | 5405 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
Here | +0.243 |
First | +0.229 |
Many | +0.219 |
Watch | +0.217 |
Majesty | +0.211 |
Neg logit contributions | |
ier | -0.208 |
again | -0.191 |
anymore | -0.181 |
than | -0.175 |
y | -0.172 |
Token | down |
Token ID | 866 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
ier | +0.000 |
ge | +0.000 |
than | +0.000 |
anymore | +0.000 |
sooner | +0.000 |
Neg logit contributions | |
First | -0.000 |
Here | -0.000 |
This | -0.000 |
Everyone | -0.000 |
Watch | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
Here | +0.071 |
First | +0.070 |
Everyone | +0.064 |
The | +0.064 |
Watch | +0.063 |
Neg logit contributions | |
ier | -0.067 |
ge | -0.058 |
than | -0.052 |
anymore | -0.051 |
again | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
Here | +0.159 |
First | +0.148 |
Many | +0.143 |
Watch | +0.141 |
Everyone | +0.134 |
Neg logit contributions | |
ier | -0.111 |
again | -0.095 |
anymore | -0.091 |
than | -0.089 |
on | -0.085 |
Token | cater |
Token ID | 20825 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
Here | +0.106 |
First | +0.097 |
Watch | +0.095 |
Many | +0.093 |
Everyone | +0.093 |
Neg logit contributions | |
ier | -0.126 |
ge | -0.108 |
anymore | -0.100 |
than | -0.100 |
again | -0.098 |
Token | twenty |
Token ID | 8208 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
Here | +0.154 |
First | +0.146 |
Watch | +0.137 |
Many | +0.131 |
Dare | +0.129 |
Neg logit contributions | |
ier | -0.143 |
again | -0.128 |
than | -0.127 |
anymore | -0.121 |
on | -0.116 |
Token | - |
Token ID | 12 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
Here | +0.090 |
Many | +0.088 |
Everyone | +0.085 |
First | +0.084 |
Watch | +0.080 |
Neg logit contributions | |
ier | -0.089 |
ge | -0.077 |
anymore | -0.072 |
again | -0.072 |
sooner | -0.069 |
Token | eight |
Token ID | 26022 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
Here | +0.234 |
First | +0.223 |
Many | +0.210 |
Watch | +0.207 |
Everyone | +0.203 |
Neg logit contributions | |
ier | -0.237 |
ge | -0.192 |
than | -0.192 |
again | -0.191 |
anymore | -0.189 |
Token | , |
Token ID | 11 |
Feature activation | +8.81e+00 |
Pos logit contributions | |
Here | +0.071 |
First | +0.069 |
Many | +0.065 |
Everyone | +0.064 |
The | +0.064 |
Neg logit contributions | |
ier | -0.062 |
ge | -0.048 |
anymore | -0.045 |
again | -0.045 |
than | -0.044 |
Token | twenty |
Token ID | 8208 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
Here | +0.164 |
First | +0.153 |
Watch | +0.147 |
Many | +0.138 |
disl | +0.135 |
Neg logit contributions | |
ier | -0.148 |
again | -0.132 |
than | -0.127 |
anymore | -0.121 |
ge | -0.120 |
Token | - |
Token ID | 12 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
Here | +0.121 |
Many | +0.120 |
First | +0.117 |
Everyone | +0.115 |
Watch | +0.111 |
Neg logit contributions | |
ier | -0.081 |
ge | -0.065 |
anymore | -0.063 |
again | -0.062 |
sooner | -0.057 |
Token | nine |
Token ID | 30888 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Here | +0.213 |
First | +0.202 |
Many | +0.188 |
Watch | +0.187 |
Everyone | +0.181 |
Neg logit contributions | |
ier | -0.256 |
ge | -0.212 |
than | -0.212 |
again | -0.211 |
anymore | -0.207 |
Token | , |
Token ID | 11 |
Feature activation | +8.28e+00 |
Pos logit contributions | |
Here | +0.025 |
First | +0.024 |
This | +0.023 |
Many | +0.022 |
The | +0.022 |
Neg logit contributions | |
ier | -0.022 |
anymore | -0.017 |
ge | -0.017 |
again | -0.017 |
than | -0.016 |
Token | thirty |
Token ID | 12277 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
Here | +0.160 |
First | +0.147 |
Watch | +0.145 |
Many | +0.135 |
disl | +0.134 |
Neg logit contributions | |
ier | -0.135 |
again | -0.119 |
than | -0.114 |
on | -0.109 |
ge | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | +7.97e+00 |
Pos logit contributions | |
Here | +0.127 |
Many | +0.124 |
First | +0.122 |
Everyone | +0.120 |
Watch | +0.116 |
Neg logit contributions | |
ier | -0.059 |
anymore | -0.044 |
again | -0.043 |
ge | -0.043 |
anywhere | -0.039 |
Token | thirty |
Token ID | 12277 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
Here | +0.155 |
First | +0.144 |
Watch | +0.140 |
Many | +0.131 |
disl | +0.131 |
Neg logit contributions | |
ier | -0.130 |
again | -0.113 |
than | -0.108 |
on | -0.105 |
ge | -0.103 |
Token | loud |
Token ID | 7812 |
Feature activation | +7.82e+00 |
Pos logit contributions | |
Here | +0.026 |
ossible | +0.026 |
disl | +0.025 |
First | +0.024 |
Deal | +0.024 |
Neg logit contributions | |
ier | -0.052 |
again | -0.050 |
anymore | -0.048 |
than | -0.047 |
on | -0.045 |
Token | noise |
Token ID | 7838 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
Here | +0.165 |
First | +0.158 |
Many | +0.152 |
Watch | +0.150 |
Everyone | +0.148 |
Neg logit contributions | |
ier | -0.123 |
ge | -0.096 |
than | -0.094 |
again | -0.093 |
anymore | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
The | +0.072 |
Everyone | +0.072 |
This | +0.069 |
It | +0.068 |
Watch | +0.068 |
Neg logit contributions | |
ier | -0.050 |
ge | -0.049 |
sooner | -0.037 |
ris | -0.035 |
iest | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
Here | +0.117 |
Majesty | +0.117 |
First | +0.116 |
rac | +0.111 |
lder | +0.109 |
Neg logit contributions | |
again | -0.209 |
anymore | -0.198 |
. | -0.196 |
than | -0.194 |
ier | -0.192 |
Token | sc |
Token ID | 629 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
Here | +0.107 |
First | +0.102 |
Many | +0.097 |
Watch | +0.095 |
Everyone | +0.093 |
Neg logit contributions | |
ier | -0.102 |
again | -0.084 |
than | -0.083 |
ge | -0.083 |
anymore | -0.082 |
Token | run |
Token ID | 5143 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
Here | +0.124 |
First | +0.116 |
Many | +0.111 |
Watch | +0.107 |
This | +0.105 |
Neg logit contributions | |
ier | -0.148 |
ge | -0.122 |
again | -0.120 |
than | -0.118 |
anymore | -0.117 |
Token | ched |
Token ID | 1740 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
Here | +0.254 |
First | +0.235 |
Watch | +0.228 |
Many | +0.226 |
Majesty | +0.221 |
Neg logit contributions | |
ier | -0.216 |
ge | -0.174 |
again | -0.174 |
than | -0.170 |
y | -0.167 |
Token | his |
Token ID | 465 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
Here | +0.073 |
First | +0.069 |
Many | +0.065 |
Watch | +0.064 |
Everyone | +0.062 |
Neg logit contributions | |
ier | -0.084 |
again | -0.070 |
than | -0.070 |
ge | -0.069 |
anymore | -0.069 |
Token | eyes |
Token ID | 2951 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Here | +0.079 |
First | +0.074 |
Watch | +0.070 |
Many | +0.069 |
Everyone | +0.067 |
Neg logit contributions | |
ier | -0.103 |
ge | -0.085 |
anymore | -0.083 |
than | -0.083 |
again | -0.083 |
Token | tightly |
Token ID | 17707 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
ier | +0.006 |
ge | +0.005 |
than | +0.005 |
anymore | +0.004 |
ies | +0.004 |
Neg logit contributions | |
The | -0.008 |
First | -0.008 |
This | -0.008 |
It | -0.008 |
Every | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
The | +0.011 |
First | +0.011 |
This | +0.011 |
Here | +0.010 |
It | +0.010 |
Neg logit contributions | |
ier | -0.008 |
ge | -0.006 |
iness | -0.005 |
iest | -0.005 |
m | -0.005 |
Token | rare |
Token ID | 4071 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Here | +0.106 |
Watch | +0.098 |
First | +0.098 |
Many | +0.097 |
Everyone | +0.094 |
Neg logit contributions | |
ier | -0.111 |
ge | -0.093 |
anymore | -0.087 |
than | -0.087 |
again | -0.086 |
Token | silence |
Token ID | 9550 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
Here | +0.047 |
Watch | +0.043 |
First | +0.043 |
Everyone | +0.043 |
Many | +0.042 |
Neg logit contributions | |
ier | -0.048 |
ge | -0.041 |
anymore | -0.036 |
than | -0.036 |
again | -0.036 |
Token | � |
Token ID | 6184 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
ier | +0.012 |
ge | +0.010 |
anymore | +0.009 |
again | +0.009 |
than | +0.009 |
Neg logit contributions | |
Here | -0.014 |
First | -0.013 |
Everyone | -0.013 |
Watch | -0.013 |
This | -0.013 |
Token | � |
Token ID | 95 |
Feature activation | +9.08e+00 |
Pos logit contributions | |
Here | +0.094 |
First | +0.092 |
Many | +0.082 |
ossible | +0.077 |
Watch | +0.076 |
Neg logit contributions | |
ier | -0.141 |
anymore | -0.121 |
again | -0.121 |
than | -0.119 |
ge | -0.115 |
Token | € |
Token ID | 26391 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
Here | +0.111 |
First | +0.109 |
Many | +0.094 |
Remy | +0.090 |
Fin | +0.090 |
Neg logit contributions | |
ier | -0.211 |
than | -0.184 |
anymore | -0.178 |
again | -0.178 |
ge | -0.169 |
Token | � |
Token ID | 447 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
Here | +0.141 |
First | +0.137 |
Many | +0.118 |
Watch | +0.114 |
Deal | +0.112 |
Neg logit contributions | |
ier | -0.164 |
than | -0.159 |
again | -0.149 |
anymore | -0.147 |
y | -0.145 |
Token | � |
Token ID | 250 |
Feature activation | +9.81e+00 |
Pos logit contributions | |
Here | +0.166 |
First | +0.164 |
Many | +0.150 |
disl | +0.140 |
Watch | +0.139 |
Neg logit contributions | |
ier | -0.252 |
again | -0.233 |
anymore | -0.217 |
m | -0.214 |
on | -0.209 |
Token | that |
Token ID | 326 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
Here | +0.136 |
First | +0.127 |
Many | +0.119 |
Watch | +0.116 |
Everyone | +0.112 |
Neg logit contributions | |
ier | -0.228 |
than | -0.192 |
ge | -0.192 |
again | -0.191 |
anymore | -0.191 |
Token | added |
Token ID | 2087 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Here | +0.085 |
First | +0.081 |
Many | +0.076 |
Watch | +0.074 |
Everyone | +0.073 |
Neg logit contributions | |
ier | -0.102 |
ge | -0.085 |
than | -0.084 |
again | -0.084 |
anymore | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
Here | +0.018 |
First | +0.017 |
Watch | +0.016 |
Many | +0.016 |
Everyone | +0.016 |
Neg logit contributions | |
ier | -0.020 |
ge | -0.017 |
anymore | -0.016 |
again | -0.016 |
than | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
Here | +0.096 |
First | +0.090 |
Many | +0.082 |
Watch | +0.080 |
Everyone | +0.077 |
Neg logit contributions | |
ier | -0.113 |
again | -0.100 |
than | -0.098 |
anymore | -0.096 |
ge | -0.095 |
Token | he |
Token ID | 339 |
Feature activation | +6.33e+00 |
Pos logit contributions | |
ier | +0.053 |
ge | +0.046 |
than | +0.046 |
again | +0.046 |
anymore | +0.046 |
Neg logit contributions | |
Here | -0.016 |
First | -0.015 |
Many | -0.013 |
Watch | -0.012 |
Everyone | -0.012 |
Token | got |
Token ID | 1392 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
Here | +0.127 |
First | +0.121 |
Many | +0.115 |
Watch | +0.113 |
Everyone | +0.111 |
Neg logit contributions | |
ier | -0.107 |
again | -0.085 |
than | -0.085 |
ge | -0.085 |
anymore | -0.083 |
Token | even |
Token ID | 772 |
Feature activation | +6.74e+00 |
Pos logit contributions | |
Here | +0.087 |
First | +0.083 |
The | +0.080 |
Everyone | +0.080 |
Many | +0.080 |
Neg logit contributions | |
ier | -0.078 |
than | -0.064 |
ge | -0.064 |
anymore | -0.061 |
y | -0.059 |
Token | mad |
Token ID | 8805 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
Here | +0.159 |
First | +0.156 |
Many | +0.151 |
Watch | +0.151 |
The | +0.144 |
Neg logit contributions | |
ier | -0.079 |
than | -0.058 |
ge | -0.056 |
anymore | -0.055 |
y | -0.050 |
Token | der |
Token ID | 1082 |
Feature activation | +9.58e+00 |
Pos logit contributions | |
Here | +0.062 |
Everyone | +0.061 |
Watch | +0.059 |
First | +0.059 |
This | +0.059 |
Neg logit contributions | |
ier | -0.028 |
ge | -0.024 |
sooner | -0.018 |
bul | -0.018 |
anymore | -0.017 |
Token | ! |
Token ID | 0 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
Here | +0.245 |
First | +0.231 |
Everyone | +0.228 |
disl | +0.225 |
Many | +0.225 |
Neg logit contributions | |
ier | -0.082 |
ge | -0.054 |
anymore | -0.053 |
again | -0.052 |
sooner | -0.046 |
Token | He |
Token ID | 679 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
First | +0.138 |
Here | +0.137 |
Majesty | +0.128 |
disl | +0.127 |
rac | +0.123 |
Neg logit contributions | |
again | -0.247 |
ier | -0.240 |
anymore | -0.233 |
than | -0.222 |
. | -0.219 |
Token | turned |
Token ID | 2900 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Here | +0.110 |
First | +0.105 |
Many | +0.099 |
Watch | +0.098 |
Everyone | +0.097 |
Neg logit contributions | |
ier | -0.109 |
ge | -0.088 |
than | -0.087 |
anymore | -0.086 |
again | -0.084 |
Token | to |
Token ID | 284 |
Feature activation | +7.30e+00 |
Pos logit contributions | |
The | +0.044 |
Everyone | +0.044 |
First | +0.043 |
Here | +0.042 |
Many | +0.042 |
Neg logit contributions | |
ier | -0.031 |
ge | -0.027 |
than | -0.024 |
anymore | -0.022 |
sooner | -0.022 |
Token | Bob |
Token ID | 5811 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
Here | +0.150 |
First | +0.138 |
Watch | +0.128 |
Many | +0.126 |
lder | +0.122 |
Neg logit contributions | |
ier | -0.113 |
again | -0.111 |
anymore | -0.103 |
ge | -0.101 |
than | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
Here | +0.010 |
First | +0.010 |
The | +0.009 |
This | +0.009 |
Many | +0.009 |
Neg logit contributions | |
ier | -0.006 |
than | -0.004 |
anymore | -0.003 |
ge | -0.003 |
iest | -0.003 |
Token | nine |
Token ID | 30888 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Here | +0.213 |
First | +0.202 |
Many | +0.188 |
Watch | +0.187 |
Everyone | +0.181 |
Neg logit contributions | |
ier | -0.256 |
ge | -0.212 |
than | -0.212 |
again | -0.211 |
anymore | -0.207 |
Token | , |
Token ID | 11 |
Feature activation | +8.28e+00 |
Pos logit contributions | |
Here | +0.025 |
First | +0.024 |
This | +0.023 |
Many | +0.022 |
The | +0.022 |
Neg logit contributions | |
ier | -0.022 |
anymore | -0.017 |
ge | -0.017 |
again | -0.017 |
than | -0.016 |
Token | thirty |
Token ID | 12277 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
Here | +0.160 |
First | +0.147 |
Watch | +0.145 |
Many | +0.135 |
disl | +0.134 |
Neg logit contributions | |
ier | -0.135 |
again | -0.119 |
than | -0.114 |
on | -0.109 |
ge | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | +7.97e+00 |
Pos logit contributions | |
Here | +0.127 |
Many | +0.124 |
First | +0.122 |
Everyone | +0.120 |
Watch | +0.116 |
Neg logit contributions | |
ier | -0.059 |
anymore | -0.044 |
again | -0.043 |
ge | -0.043 |
anywhere | -0.039 |
Token | thirty |
Token ID | 12277 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
Here | +0.155 |
First | +0.144 |
Watch | +0.140 |
Many | +0.131 |
disl | +0.131 |
Neg logit contributions | |
ier | -0.130 |
again | -0.113 |
than | -0.108 |
on | -0.105 |
ge | -0.103 |
Token | - |
Token ID | 12 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
Here | +0.120 |
Many | +0.117 |
First | +0.115 |
Everyone | +0.114 |
Watch | +0.110 |
Neg logit contributions | |
ier | -0.056 |
anymore | -0.043 |
again | -0.042 |
ge | -0.041 |
anywhere | -0.038 |
Token | one |
Token ID | 505 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
Here | +0.194 |
First | +0.183 |
Watch | +0.171 |
Many | +0.170 |
Everyone | +0.164 |
Neg logit contributions | |
ier | -0.248 |
ge | -0.207 |
than | -0.207 |
again | -0.205 |
anymore | -0.200 |
Token | , |
Token ID | 11 |
Feature activation | +7.75e+00 |
Pos logit contributions | |
Here | +0.096 |
First | +0.092 |
Many | +0.091 |
Everyone | +0.088 |
This | +0.086 |
Neg logit contributions | |
ier | -0.091 |
ge | -0.074 |
anymore | -0.072 |
again | -0.071 |
than | -0.068 |
Token | thirty |
Token ID | 12277 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
Here | +0.150 |
First | +0.139 |
Watch | +0.135 |
Many | +0.127 |
disl | +0.126 |
Neg logit contributions | |
ier | -0.130 |
again | -0.112 |
than | -0.108 |
on | -0.103 |
ge | -0.102 |
Token | - |
Token ID | 12 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
Here | +0.114 |
Many | +0.112 |
First | +0.110 |
Everyone | +0.109 |
Watch | +0.105 |
Neg logit contributions | |
ier | -0.053 |
anymore | -0.041 |
again | -0.039 |
ge | -0.038 |
anywhere | -0.036 |
Token | two |
Token ID | 11545 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Here | +0.186 |
First | +0.176 |
Many | +0.164 |
Watch | +0.163 |
Everyone | +0.158 |
Neg logit contributions | |
ier | -0.241 |
ge | -0.200 |
than | -0.200 |
again | -0.199 |
anymore | -0.194 |
Token | slowly |
Token ID | 6364 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
Here | +0.029 |
Majesty | +0.028 |
First | +0.027 |
majesty | +0.026 |
Deal | +0.025 |
Neg logit contributions | |
ier | -0.028 |
than | -0.027 |
on | -0.025 |
again | -0.025 |
y | -0.025 |
Token | got |
Token ID | 1392 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
Here | +0.189 |
First | +0.186 |
Watch | +0.175 |
Many | +0.175 |
Everyone | +0.173 |
Neg logit contributions | |
ier | -0.111 |
ge | -0.079 |
than | -0.077 |
anymore | -0.075 |
again | -0.066 |
Token | back |
Token ID | 736 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
Here | +0.135 |
First | +0.131 |
The | +0.125 |
Fin | +0.123 |
Many | +0.123 |
Neg logit contributions | |
ier | -0.099 |
than | -0.083 |
ge | -0.081 |
anymore | -0.074 |
y | -0.071 |
Token | up |
Token ID | 510 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
Here | +0.108 |
The | +0.104 |
First | +0.103 |
This | +0.100 |
Everyone | +0.100 |
Neg logit contributions | |
ier | -0.076 |
ge | -0.051 |
anymore | -0.050 |
iness | -0.048 |
than | -0.047 |
Token | again |
Token ID | 757 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
Here | +0.111 |
The | +0.109 |
First | +0.109 |
Everyone | +0.104 |
This | +0.103 |
Neg logit contributions | |
ier | -0.079 |
ge | -0.055 |
iness | -0.049 |
anymore | -0.048 |
than | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
Here | +0.111 |
First | +0.108 |
The | +0.106 |
Everyone | +0.104 |
This | +0.103 |
Neg logit contributions | |
ier | -0.060 |
ge | -0.039 |
anymore | -0.038 |
iness | -0.034 |
y | -0.033 |
Token | He |
Token ID | 679 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
rac | +0.130 |
First | +0.128 |
Here | +0.127 |
Majesty | +0.124 |
disl | +0.124 |
Neg logit contributions | |
again | -0.245 |
anymore | -0.232 |
ier | -0.226 |
than | -0.223 |
. | -0.214 |
Token | brushed |
Token ID | 31782 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
Here | +0.110 |
First | +0.106 |
Many | +0.100 |
Watch | +0.099 |
Everyone | +0.098 |
Neg logit contributions | |
ier | -0.099 |
ge | -0.078 |
than | -0.077 |
anymore | -0.077 |
again | -0.074 |
Token | off |
Token ID | 572 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
Here | +0.068 |
First | +0.065 |
Many | +0.061 |
Everyone | +0.060 |
Watch | +0.060 |
Neg logit contributions | |
ier | -0.075 |
ge | -0.061 |
than | -0.061 |
anymore | -0.060 |
again | -0.060 |
Token | his |
Token ID | 465 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
Here | +0.051 |
First | +0.050 |
The | +0.049 |
Everyone | +0.048 |
This | +0.047 |
Neg logit contributions | |
ier | -0.089 |
ge | -0.073 |
than | -0.071 |
anymore | -0.070 |
y | -0.068 |
Token | clothes |
Token ID | 8242 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Here | +0.100 |
First | +0.094 |
Many | +0.088 |
Watch | +0.088 |
Everyone | +0.084 |
Neg logit contributions | |
ier | -0.140 |
ge | -0.116 |
than | -0.114 |
anymore | -0.113 |
again | -0.111 |
Token | won |
Token ID | 1839 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
disl | +0.017 |
lder | +0.016 |
Here | +0.016 |
Majesty | +0.015 |
majesty | +0.015 |
Neg logit contributions | |
again | -0.032 |
ier | -0.031 |
anymore | -0.031 |
than | -0.029 |
before | -0.029 |
Token | 't |
Token ID | 470 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
Here | +0.247 |
First | +0.238 |
Many | +0.227 |
Watch | +0.224 |
Everyone | +0.220 |
Neg logit contributions | |
ier | -0.149 |
again | -0.112 |
than | -0.112 |
ge | -0.111 |
anymore | -0.110 |
Token | do |
Token ID | 466 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
Here | +0.156 |
First | +0.147 |
Many | +0.140 |
Watch | +0.136 |
Everyone | +0.134 |
Neg logit contributions | |
ier | -0.227 |
ge | -0.190 |
than | -0.189 |
again | -0.187 |
anymore | -0.185 |
Token | it |
Token ID | 340 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
Here | +0.152 |
First | +0.145 |
Many | +0.137 |
Watch | +0.135 |
Everyone | +0.134 |
Neg logit contributions | |
ier | -0.149 |
ge | -0.121 |
than | -0.120 |
again | -0.118 |
anymore | -0.117 |
Token | again |
Token ID | 757 |
Feature activation | +6.04e+00 |
Pos logit contributions | |
Here | +0.093 |
First | +0.091 |
Everyone | +0.091 |
Watch | +0.090 |
Many | +0.089 |
Neg logit contributions | |
ier | -0.036 |
ge | -0.026 |
than | -0.026 |
y | -0.021 |
beneath | -0.021 |
Token | ." |
Token ID | 526 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
Here | +0.143 |
First | +0.137 |
Watch | +0.133 |
Many | +0.133 |
Everyone | +0.132 |
Neg logit contributions | |
ier | -0.073 |
ge | -0.051 |
than | -0.045 |
anymore | -0.044 |
y | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
Here | +0.157 |
First | +0.155 |
Majesty | +0.150 |
Watch | +0.146 |
majesty | +0.140 |
Neg logit contributions | |
again | -0.236 |
anymore | -0.216 |
. | -0.216 |
ier | -0.213 |
than | -0.208 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
Majesty | +0.213 |
First | +0.211 |
Here | +0.205 |
cient | +0.200 |
majesty | +0.195 |
Neg logit contributions | |
again | -0.169 |
. | -0.165 |
ge | -0.144 |
than | -0.143 |
y | -0.142 |
Token | Her |
Token ID | 9360 |
Feature activation | +8.44e+00 |
Pos logit contributions | |
Here | +0.181 |
First | +0.178 |
Majesty | +0.168 |
cient | +0.164 |
majesty | +0.158 |
Neg logit contributions | |
ge | -0.172 |
ier | -0.170 |
than | -0.169 |
again | -0.168 |
y | -0.159 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Here | +0.110 |
First | +0.102 |
Many | +0.094 |
Watch | +0.092 |
Everyone | +0.089 |
Neg logit contributions | |
ier | -0.203 |
again | -0.174 |
than | -0.174 |
ge | -0.173 |
anymore | -0.172 |
Token | hugged |
Token ID | 41130 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
Here | +0.061 |
First | +0.058 |
Many | +0.054 |
Watch | +0.053 |
Everyone | +0.053 |
Neg logit contributions | |
ier | -0.068 |
than | -0.056 |
ge | -0.056 |
anymore | -0.055 |
again | -0.053 |
Token | softer |
Token ID | 32359 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Here | +0.176 |
First | +0.167 |
Many | +0.159 |
Watch | +0.157 |
Everyone | +0.155 |
Neg logit contributions | |
ier | -0.135 |
ge | -0.111 |
anymore | -0.105 |
than | -0.101 |
again | -0.097 |
Token | than |
Token ID | 621 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
Here | +0.051 |
First | +0.049 |
Watch | +0.048 |
Majesty | +0.047 |
disl | +0.047 |
Neg logit contributions | |
ier | -0.027 |
ge | -0.021 |
m | -0.015 |
emanating | -0.015 |
anymore | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +7.64e+00 |
Pos logit contributions | |
Here | +0.115 |
First | +0.106 |
Many | +0.100 |
Watch | +0.099 |
Everyone | +0.099 |
Neg logit contributions | |
ier | -0.120 |
ge | -0.099 |
than | -0.094 |
y | -0.094 |
anymore | -0.092 |
Token | last |
Token ID | 938 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
Here | +0.134 |
First | +0.122 |
Watch | +0.119 |
Many | +0.118 |
Everyone | +0.116 |
Neg logit contributions | |
ier | -0.143 |
ge | -0.122 |
than | -0.109 |
again | -0.108 |
anymore | -0.107 |
Token | one |
Token ID | 530 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
Here | +0.085 |
First | +0.081 |
Everyone | +0.081 |
Watch | +0.080 |
Many | +0.079 |
Neg logit contributions | |
ier | -0.081 |
ge | -0.062 |
anymore | -0.055 |
than | -0.055 |
again | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
Here | +0.082 |
The | +0.073 |
First | +0.072 |
Everyone | +0.072 |
Watch | +0.072 |
Neg logit contributions | |
ier | -0.058 |
ge | -0.050 |
anymore | -0.039 |
than | -0.036 |
y | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
disl | +0.134 |
rac | +0.132 |
Here | +0.130 |
lder | +0.128 |
First | +0.128 |
Neg logit contributions | |
again | -0.238 |
anymore | -0.224 |
ier | -0.216 |
than | -0.214 |
. | -0.212 |
Token | offered |
Token ID | 4438 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
Here | +0.119 |
First | +0.114 |
Many | +0.108 |
Watch | +0.107 |
Everyone | +0.105 |
Neg logit contributions | |
ier | -0.104 |
ge | -0.082 |
than | -0.082 |
anymore | -0.081 |
again | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
Here | +0.072 |
First | +0.069 |
Many | +0.065 |
Watch | +0.063 |
Everyone | +0.063 |
Neg logit contributions | |
ier | -0.082 |
ge | -0.068 |
than | -0.067 |
anymore | -0.066 |
again | -0.066 |
Token | share |
Token ID | 2648 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Here | +0.118 |
First | +0.111 |
Many | +0.105 |
Watch | +0.102 |
Everyone | +0.096 |
Neg logit contributions | |
ier | -0.130 |
again | -0.118 |
than | -0.112 |
ge | -0.112 |
anymore | -0.111 |
Token | his |
Token ID | 465 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
Here | +0.024 |
First | +0.023 |
Many | +0.021 |
Everyone | +0.021 |
The | +0.021 |
Neg logit contributions | |
ier | -0.033 |
ge | -0.027 |
y | -0.025 |
anymore | -0.025 |
than | -0.025 |
Token | only |
Token ID | 691 |
Feature activation | +8.67e+00 |
Pos logit contributions | |
ier | +0.077 |
than | +0.067 |
ge | +0.066 |
again | +0.066 |
anymore | +0.066 |
Neg logit contributions | |
Here | -0.058 |
First | -0.054 |
Watch | -0.050 |
Many | -0.050 |
Higher | -0.047 |
Token | joy |
Token ID | 8716 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
Here | +0.174 |
First | +0.165 |
Many | +0.158 |
Watch | +0.155 |
Everyone | +0.153 |
Neg logit contributions | |
ier | -0.146 |
ge | -0.114 |
anymore | -0.110 |
again | -0.109 |
than | -0.108 |
Token | and |
Token ID | 290 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
Here | +0.106 |
Everyone | +0.099 |
This | +0.098 |
First | +0.097 |
The | +0.094 |
Neg logit contributions | |
ier | -0.049 |
ge | -0.045 |
sooner | -0.034 |
anymore | -0.032 |
beneath | -0.031 |
Token | content |
Token ID | 2695 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
Here | +0.137 |
First | +0.130 |
Many | +0.122 |
Watch | +0.120 |
Everyone | +0.117 |
Neg logit contributions | |
ier | -0.164 |
than | -0.136 |
again | -0.136 |
ge | -0.136 |
anymore | -0.134 |
Token | ment |
Token ID | 434 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
Here | +0.122 |
Everyone | +0.120 |
First | +0.115 |
The | +0.114 |
This | +0.112 |
Neg logit contributions | |
ier | -0.059 |
ge | -0.050 |
anymore | -0.039 |
again | -0.035 |
sooner | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
Here | +0.120 |
Everyone | +0.117 |
First | +0.114 |
The | +0.113 |
This | +0.111 |
Neg logit contributions | |
ge | -0.055 |
ier | -0.054 |
anymore | -0.042 |
y | -0.038 |
sooner | -0.037 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
Here | +0.134 |
First | +0.133 |
Watch | +0.133 |
disl | +0.133 |
rac | +0.130 |
Neg logit contributions | |
again | -0.234 |
ier | -0.225 |
anymore | -0.218 |
than | -0.217 |
. | -0.209 |
Token | The |
Token ID | 464 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
Here | +0.095 |
First | +0.090 |
Many | +0.082 |
Watch | +0.082 |
disl | +0.076 |
Neg logit contributions | |
ier | -0.142 |
again | -0.125 |
anymore | -0.122 |
than | -0.120 |
ge | -0.118 |
Token | sun |
Token ID | 4252 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
Here | +0.134 |
First | +0.129 |
Many | +0.120 |
Watch | +0.118 |
Everyone | +0.114 |
Neg logit contributions | |
ier | -0.121 |
again | -0.104 |
than | -0.100 |
anymore | -0.099 |
ge | -0.097 |
Token | was |
Token ID | 373 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
Here | +0.019 |
First | +0.018 |
Many | +0.017 |
Watch | +0.017 |
Everyone | +0.016 |
Neg logit contributions | |
ier | -0.012 |
again | -0.009 |
than | -0.009 |
anymore | -0.009 |
y | -0.009 |
Token | very |
Token ID | 845 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
Here | +0.099 |
First | +0.095 |
Many | +0.090 |
Watch | +0.089 |
Everyone | +0.087 |
Neg logit contributions | |
ier | -0.075 |
than | -0.059 |
again | -0.059 |
ge | -0.058 |
anymore | -0.057 |
Token | always |
Token ID | 1464 |
Feature activation | +7.84e+00 |
Pos logit contributions | |
Here | +0.162 |
First | +0.150 |
Many | +0.140 |
Watch | +0.138 |
Everyone | +0.132 |
Neg logit contributions | |
ier | -0.180 |
again | -0.172 |
anymore | -0.167 |
ge | -0.154 |
than | -0.153 |
Token | rely |
Token ID | 8814 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
Here | +0.123 |
First | +0.115 |
Many | +0.108 |
Watch | +0.104 |
Everyone | +0.103 |
Neg logit contributions | |
ier | -0.167 |
again | -0.145 |
than | -0.143 |
ge | -0.141 |
anymore | -0.141 |
Token | on |
Token ID | 319 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
Here | +0.129 |
First | +0.125 |
Many | +0.120 |
Watch | +0.119 |
Everyone | +0.118 |
Neg logit contributions | |
ier | -0.048 |
ge | -0.033 |
anymore | -0.031 |
than | -0.031 |
again | -0.030 |
Token | each |
Token ID | 1123 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
Here | +0.108 |
First | +0.102 |
Many | +0.096 |
Watch | +0.093 |
Everyone | +0.087 |
Neg logit contributions | |
ier | -0.166 |
again | -0.145 |
than | -0.144 |
anymore | -0.142 |
ge | -0.140 |
Token | other |
Token ID | 584 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
Here | +0.117 |
First | +0.114 |
Many | +0.112 |
Everyone | +0.110 |
Watch | +0.109 |
Neg logit contributions | |
ier | -0.124 |
ge | -0.107 |
anymore | -0.096 |
than | -0.096 |
again | -0.089 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
Here | +0.098 |
First | +0.095 |
Watch | +0.090 |
Many | +0.090 |
Everyone | +0.089 |
Neg logit contributions | |
ier | -0.063 |
ge | -0.049 |
anymore | -0.043 |
than | -0.042 |
again | -0.040 |
Token | Tina |
Token ID | 35903 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
Here | +0.146 |
Watch | +0.140 |
Majesty | +0.137 |
First | +0.135 |
disl | +0.132 |
Neg logit contributions | |
again | -0.238 |
ier | -0.230 |
anymore | -0.225 |
than | -0.217 |
ge | -0.213 |
Token | hugged |
Token ID | 41130 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
Here | +0.114 |
First | +0.108 |
Many | +0.104 |
Watch | +0.102 |
Everyone | +0.097 |
Neg logit contributions | |
ier | -0.089 |
again | -0.074 |
than | -0.071 |
anymore | -0.070 |
ge | -0.069 |
Token | her |
Token ID | 607 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
Here | +0.090 |
First | +0.084 |
Many | +0.080 |
Watch | +0.078 |
Everyone | +0.075 |
Neg logit contributions | |
ier | -0.106 |
again | -0.090 |
than | -0.089 |
ge | -0.088 |
anymore | -0.088 |
Token | back |
Token ID | 736 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
Here | +0.094 |
First | +0.089 |
Many | +0.079 |
Watch | +0.079 |
Everyone | +0.078 |
Neg logit contributions | |
ier | -0.167 |
ge | -0.140 |
than | -0.139 |
anymore | -0.138 |
again | -0.136 |
Token | and |
Token ID | 290 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
Here | +0.111 |
First | +0.107 |
Everyone | +0.102 |
The | +0.102 |
Many | +0.099 |
Neg logit contributions | |
ier | -0.062 |
ge | -0.041 |
anymore | -0.038 |
than | -0.035 |
iness | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
Here | +0.070 |
First | +0.067 |
Everyone | +0.063 |
Many | +0.062 |
Watch | +0.061 |
Neg logit contributions | |
ier | -0.087 |
ge | -0.074 |
y | -0.067 |
than | -0.067 |
anymore | -0.067 |
Token | way |
Token ID | 835 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
Here | +0.093 |
First | +0.086 |
Watch | +0.086 |
Majesty | +0.083 |
Many | +0.080 |
Neg logit contributions | |
ier | -0.113 |
ge | -0.090 |
iness | -0.084 |
than | -0.083 |
anymore | -0.082 |
Token | to |
Token ID | 284 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
Here | +0.086 |
First | +0.084 |
This | +0.082 |
Everyone | +0.081 |
The | +0.079 |
Neg logit contributions | |
ier | -0.060 |
ge | -0.044 |
than | -0.040 |
anymore | -0.039 |
again | -0.038 |
Token | get |
Token ID | 651 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
Here | +0.131 |
First | +0.122 |
Many | +0.113 |
Watch | +0.111 |
Everyone | +0.105 |
Neg logit contributions | |
ier | -0.154 |
again | -0.136 |
anymore | -0.132 |
ge | -0.131 |
than | -0.130 |
Token | down |
Token ID | 866 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Here | +0.100 |
First | +0.096 |
Everyone | +0.091 |
Watch | +0.089 |
Many | +0.089 |
Neg logit contributions | |
ier | -0.086 |
ge | -0.070 |
than | -0.068 |
anymore | -0.065 |
y | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
First | +0.059 |
The | +0.059 |
Here | +0.058 |
Everyone | +0.057 |
This | +0.056 |
Neg logit contributions | |
ier | -0.036 |
ge | -0.028 |
y | -0.024 |
iness | -0.022 |
le | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
disl | +0.137 |
rac | +0.133 |
Here | +0.131 |
lder | +0.130 |
Majesty | +0.130 |
Neg logit contributions | |
again | -0.237 |
anymore | -0.221 |
than | -0.214 |
ier | -0.213 |
. | -0.209 |
Token | eventually |
Token ID | 4191 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
Here | +0.106 |
First | +0.101 |
Many | +0.096 |
Watch | +0.094 |
Everyone | +0.093 |
Neg logit contributions | |
ier | -0.084 |
again | -0.068 |
than | -0.067 |
ge | -0.067 |
anymore | -0.066 |
Token | found |
Token ID | 1043 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Here | +0.092 |
First | +0.089 |
Many | +0.084 |
Watch | +0.083 |
Everyone | +0.082 |
Neg logit contributions | |
ier | -0.085 |
ge | -0.069 |
than | -0.069 |
anymore | -0.069 |
again | -0.067 |
Token | one |
Token ID | 530 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
Here | +0.046 |
First | +0.044 |
Many | +0.040 |
Everyone | +0.040 |
Watch | +0.040 |
Neg logit contributions | |
ier | -0.058 |
ge | -0.049 |
than | -0.048 |
anymore | -0.047 |
again | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
Here | +0.011 |
First | +0.010 |
The | +0.010 |
Fred | +0.010 |
Watch | +0.009 |
Neg logit contributions | |
ier | -0.011 |
ge | -0.009 |
iness | -0.008 |
anymore | -0.007 |
m | -0.007 |
Token | far |
Token ID | 1290 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Here | +0.157 |
First | +0.148 |
Many | +0.141 |
Watch | +0.140 |
Everyone | +0.137 |
Neg logit contributions | |
ier | -0.138 |
ge | -0.110 |
again | -0.108 |
anymore | -0.107 |
than | -0.107 |
Token | away |
Token ID | 1497 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
The | +0.009 |
First | +0.009 |
This | +0.008 |
Here | +0.008 |
Every | +0.008 |
Neg logit contributions | |
ier | -0.006 |
ge | -0.005 |
iness | -0.004 |
m | -0.004 |
bul | -0.004 |
Token | � |
Token ID | 6184 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
The | +0.038 |
This | +0.037 |
First | +0.037 |
Here | +0.037 |
Everyone | +0.036 |
Neg logit contributions | |
ier | -0.026 |
ge | -0.019 |
bul | -0.017 |
iness | -0.017 |
m | -0.017 |
Token | � |
Token ID | 95 |
Feature activation | +8.49e+00 |
Pos logit contributions | |
Here | +0.095 |
First | +0.091 |
ossible | +0.082 |
Many | +0.081 |
disl | +0.078 |
Neg logit contributions | |
ier | -0.147 |
anymore | -0.133 |
again | -0.127 |
than | -0.126 |
ge | -0.122 |
Token | € |
Token ID | 26391 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
Here | +0.107 |
First | +0.105 |
Many | +0.095 |
ossible | +0.089 |
Remy | +0.088 |
Neg logit contributions | |
ier | -0.197 |
than | -0.172 |
anymore | -0.166 |
again | -0.165 |
ge | -0.155 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
First | +0.126 |
Here | +0.125 |
Many | +0.109 |
Watch | +0.107 |
Deal | +0.102 |
Neg logit contributions | |
ier | -0.149 |
than | -0.145 |
again | -0.136 |
anymore | -0.135 |
on | -0.130 |
Token | � |
Token ID | 250 |
Feature activation | +9.34e+00 |
Pos logit contributions | |
First | +0.167 |
Here | +0.163 |
Many | +0.149 |
disl | +0.145 |
Watch | +0.144 |
Neg logit contributions | |
ier | -0.242 |
again | -0.223 |
m | -0.209 |
anymore | -0.209 |
on | -0.201 |
Token | it |
Token ID | 340 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
Here | +0.127 |
First | +0.118 |
Many | +0.111 |
Watch | +0.108 |
Everyone | +0.104 |
Neg logit contributions | |
ier | -0.221 |
anymore | -0.186 |
again | -0.186 |
ge | -0.185 |
than | -0.185 |
Token | is |
Token ID | 318 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
Here | +0.056 |
First | +0.053 |
Watch | +0.049 |
Many | +0.049 |
Everyone | +0.048 |
Neg logit contributions | |
ier | -0.071 |
ge | -0.060 |
than | -0.059 |
anymore | -0.058 |
again | -0.058 |
Token | distant |
Token ID | 12899 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Here | +0.105 |
First | +0.101 |
Watch | +0.095 |
Many | +0.094 |
Everyone | +0.092 |
Neg logit contributions | |
ier | -0.093 |
ge | -0.076 |
anymore | -0.070 |
again | -0.069 |
y | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +9.26e+00 |
Pos logit contributions | |
ier | +0.007 |
ge | +0.006 |
anymore | +0.005 |
than | +0.005 |
again | +0.005 |
Neg logit contributions | |
Here | -0.008 |
First | -0.008 |
Watch | -0.008 |
Everyone | -0.007 |
Many | -0.007 |
Token | worrying |
Token ID | 18916 |
Feature activation | +7.45e+00 |
Pos logit contributions | |
ier | +0.083 |
ge | +0.059 |
anymore | +0.052 |
again | +0.047 |
sooner | +0.047 |
Neg logit contributions | |
Here | -0.134 |
First | -0.132 |
Everyone | -0.128 |
This | -0.127 |
The | -0.127 |
Token | won |
Token ID | 1839 |
Feature activation | +8.90e+00 |
Pos logit contributions | |
Here | +0.164 |
First | +0.157 |
Everyone | +0.154 |
Many | +0.153 |
Watch | +0.151 |
Neg logit contributions | |
ier | -0.104 |
ge | -0.083 |
than | -0.075 |
again | -0.074 |
anymore | -0.071 |
Token | 't |
Token ID | 470 |
Feature activation | +9.35e+00 |
Pos logit contributions | |
Here | +0.174 |
First | +0.168 |
Many | +0.161 |
Everyone | +0.159 |
Watch | +0.158 |
Neg logit contributions | |
ier | -0.149 |
ge | -0.119 |
than | -0.118 |
again | -0.114 |
anymore | -0.114 |
Token | solve |
Token ID | 8494 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
Here | +0.126 |
First | +0.118 |
Many | +0.114 |
Watch | +0.112 |
Everyone | +0.111 |
Neg logit contributions | |
ier | -0.212 |
ge | -0.176 |
than | -0.175 |
anymore | -0.170 |
again | -0.170 |
Token | anything |
Token ID | 1997 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
Here | +0.067 |
First | +0.064 |
Everyone | +0.062 |
Many | +0.060 |
The | +0.060 |
Neg logit contributions | |
ier | -0.077 |
ge | -0.060 |
m | -0.060 |
y | -0.059 |
iness | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
Here | +0.103 |
Everyone | +0.101 |
Many | +0.098 |
Watch | +0.097 |
This | +0.097 |
Neg logit contributions | |
ier | -0.060 |
ge | -0.048 |
y | -0.043 |
le | -0.039 |
m | -0.038 |
Token | It |
Token ID | 632 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
rac | +0.136 |
majesty | +0.135 |
lder | +0.134 |
First | +0.134 |
Majesty | +0.133 |
Neg logit contributions | |
again | -0.235 |
anymore | -0.218 |
. | -0.208 |
ier | -0.204 |
than | -0.202 |
Token | 's |
Token ID | 338 |
Feature activation | +7.29e+00 |
Pos logit contributions | |
Here | +0.111 |
First | +0.107 |
Watch | +0.101 |
Everyone | +0.100 |
Many | +0.100 |
Neg logit contributions | |
ier | -0.101 |
ge | -0.084 |
than | -0.081 |
anymore | -0.079 |
again | -0.075 |
Token | best |
Token ID | 1266 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
Here | +0.146 |
First | +0.140 |
Many | +0.131 |
Watch | +0.129 |
Everyone | +0.128 |
Neg logit contributions | |
ier | -0.125 |
ge | -0.101 |
than | -0.097 |
again | -0.096 |
anymore | -0.096 |
Token | to |
Token ID | 284 |
Feature activation | +8.63e+00 |
Pos logit contributions | |
Here | +0.071 |
First | +0.068 |
Watch | +0.065 |
Everyone | +0.064 |
Many | +0.062 |
Neg logit contributions | |
ier | -0.063 |
ge | -0.054 |
y | -0.048 |
anymore | -0.047 |
le | -0.046 |
Token | stay |
Token ID | 2652 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Here | +0.155 |
First | +0.141 |
Many | +0.137 |
Watch | +0.134 |
Everyone | +0.126 |
Neg logit contributions | |
ier | -0.163 |
again | -0.142 |
anymore | -0.136 |
ge | -0.135 |
than | -0.135 |
Token | more |
Token ID | 517 |
Feature activation | +7.72e+00 |
Pos logit contributions | |
ier | +0.018 |
than | +0.015 |
again | +0.015 |
ge | +0.014 |
anymore | +0.014 |
Neg logit contributions | |
Here | -0.021 |
First | -0.020 |
Many | -0.019 |
Watch | -0.019 |
Everyone | -0.018 |
Token | spark |
Token ID | 9009 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Here | +0.158 |
disl | +0.148 |
First | +0.148 |
Many | +0.148 |
Watch | +0.146 |
Neg logit contributions | |
ier | -0.118 |
ge | -0.092 |
again | -0.078 |
y | -0.077 |
anymore | -0.077 |
Token | ly |
Token ID | 306 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
Everyone | +0.030 |
Here | +0.030 |
Watch | +0.029 |
The | +0.029 |
Now | +0.027 |
Neg logit contributions | |
ge | -0.023 |
ier | -0.017 |
sooner | -0.016 |
m | -0.015 |
emanating | -0.015 |
Token | than |
Token ID | 621 |
Feature activation | +6.76e+00 |
Pos logit contributions | |
Here | +0.130 |
Everyone | +0.124 |
Watch | +0.123 |
First | +0.122 |
The | +0.120 |
Neg logit contributions | |
ier | -0.077 |
ge | -0.069 |
anymore | -0.051 |
sooner | -0.048 |
m | -0.048 |
Token | before |
Token ID | 878 |
Feature activation | +8.96e+00 |
Pos logit contributions | |
Here | +0.120 |
First | +0.109 |
Everyone | +0.107 |
The | +0.106 |
Watch | +0.103 |
Neg logit contributions | |
ier | -0.115 |
ge | -0.099 |
y | -0.092 |
than | -0.086 |
anymore | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
Here | +0.176 |
First | +0.169 |
Many | +0.160 |
Everyone | +0.160 |
Watch | +0.157 |
Neg logit contributions | |
ier | -0.153 |
ge | -0.121 |
than | -0.118 |
anymore | -0.114 |
again | -0.112 |
Token | The |
Token ID | 383 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
rac | +0.133 |
disl | +0.127 |
Here | +0.126 |
lder | +0.126 |
Majesty | +0.122 |
Neg logit contributions | |
again | -0.235 |
anymore | -0.222 |
. | -0.213 |
ier | -0.213 |
than | -0.211 |
Token | gray |
Token ID | 12768 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
Here | +0.132 |
First | +0.124 |
Many | +0.120 |
Watch | +0.118 |
Everyone | +0.117 |
Neg logit contributions | |
ier | -0.151 |
ge | -0.125 |
than | -0.123 |
anymore | -0.120 |
again | -0.117 |
Token | bear |
Token ID | 6842 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Here | +0.085 |
First | +0.079 |
Many | +0.078 |
Everyone | +0.077 |
Watch | +0.075 |
Neg logit contributions | |
ier | -0.098 |
ge | -0.081 |
than | -0.077 |
anymore | -0.076 |
again | -0.074 |
Token | smiled |
Token ID | 13541 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
Here | +0.037 |
First | +0.035 |
Many | +0.034 |
Watch | +0.034 |
Everyone | +0.033 |
Neg logit contributions | |
ier | -0.038 |
ge | -0.030 |
than | -0.029 |
anymore | -0.029 |
again | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
The | +0.082 |
Here | +0.078 |
Everyone | +0.077 |
First | +0.076 |
It | +0.075 |
Neg logit contributions | |
ier | -0.050 |
ge | -0.045 |
anymore | -0.033 |
iest | -0.033 |
iness | -0.032 |
Token | let |
Token ID | 1309 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
Here | +0.162 |
Many | +0.154 |
First | +0.150 |
Watch | +0.150 |
The | +0.150 |
Neg logit contributions | |
ier | -0.103 |
ge | -0.075 |
bul | -0.065 |
than | -0.065 |
y | -0.063 |
Token | it |
Token ID | 340 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
Here | +0.115 |
First | +0.110 |
Many | +0.104 |
Watch | +0.101 |
Everyone | +0.097 |
Neg logit contributions | |
ier | -0.119 |
again | -0.100 |
anymore | -0.098 |
than | -0.096 |
ge | -0.096 |
Token | become |
Token ID | 1716 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
Here | +0.077 |
First | +0.074 |
Watch | +0.072 |
Everyone | +0.071 |
Many | +0.071 |
Neg logit contributions | |
ier | -0.059 |
ge | -0.046 |
than | -0.045 |
anymore | -0.043 |
y | -0.042 |
Token | old |
Token ID | 1468 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Here | +0.110 |
First | +0.103 |
The | +0.101 |
Fin | +0.099 |
Watch | +0.098 |
Neg logit contributions | |
ier | -0.105 |
ge | -0.085 |
iness | -0.081 |
y | -0.080 |
than | -0.079 |
Token | again |
Token ID | 757 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
Here | +0.030 |
First | +0.029 |
The | +0.029 |
Majesty | +0.028 |
Watch | +0.028 |
Neg logit contributions | |
ier | -0.018 |
ge | -0.015 |
iness | -0.012 |
m | -0.011 |
emanating | -0.011 |
Token | ! |
Token ID | 0 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
Here | +0.075 |
The | +0.071 |
First | +0.071 |
Everyone | +0.070 |
This | +0.069 |
Neg logit contributions | |
ier | -0.040 |
ge | -0.028 |
iness | -0.025 |
anymore | -0.024 |
y | -0.023 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
Majesty | +0.168 |
First | +0.163 |
majesty | +0.161 |
disl | +0.160 |
Watch | +0.158 |
Neg logit contributions | |
again | -0.209 |
anymore | -0.192 |
ier | -0.184 |
than | -0.181 |
ever | -0.181 |
Token | Once |
Token ID | 7454 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
Here | +0.084 |
First | +0.079 |
Many | +0.072 |
Watch | +0.071 |
disl | +0.066 |
Neg logit contributions | |
ier | -0.146 |
again | -0.130 |
anymore | -0.127 |
than | -0.125 |
ge | -0.124 |
Token | upon |
Token ID | 2402 |
Feature activation | +7.42e+00 |
Pos logit contributions | |
Here | +0.153 |
First | +0.148 |
Watch | +0.142 |
Many | +0.140 |
Everyone | +0.135 |
Neg logit contributions | |
ier | -0.083 |
again | -0.065 |
anymore | -0.064 |
ge | -0.063 |
than | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
Here | +0.147 |
First | +0.141 |
Watch | +0.130 |
Many | +0.125 |
Everyone | +0.124 |
Neg logit contributions | |
ier | -0.125 |
again | -0.107 |
than | -0.104 |
anymore | -0.102 |
ge | -0.099 |
Token | time |
Token ID | 640 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
Here | +0.171 |
First | +0.164 |
Watch | +0.156 |
Everyone | +0.155 |
Many | +0.154 |
Neg logit contributions | |
ier | -0.060 |
than | -0.046 |
anymore | -0.045 |
again | -0.044 |
y | -0.040 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
on | +0.013 |
inside | +0.013 |
ier | +0.013 |
again | +0.013 |
in | +0.012 |
Neg logit contributions | |
Here | -0.020 |
Many | -0.019 |
Watch | -0.019 |
First | -0.018 |
Everyone | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
ier | +0.066 |
again | +0.058 |
on | +0.058 |
anymore | +0.052 |
more | +0.051 |
Neg logit contributions | |
Here | -0.110 |
Deal | -0.103 |
First | -0.103 |
Watch | -0.101 |
Majesty | -0.100 |
Token | man |
Token ID | 582 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
ier | +0.105 |
ge | +0.087 |
than | +0.085 |
anymore | +0.084 |
again | +0.083 |
Neg logit contributions | |
Here | -0.080 |
First | -0.073 |
Many | -0.072 |
Watch | -0.072 |
Everyone | -0.069 |
Token | selling |
Token ID | 6301 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
ier | +0.214 |
iness | +0.160 |
iest | +0.152 |
than | +0.151 |
anymore | +0.140 |
Neg logit contributions | |
Here | -0.194 |
The | -0.179 |
This | -0.178 |
Many | -0.175 |
ossible | -0.168 |
Token | colorful |
Token ID | 20239 |
Feature activation | -8.61e+00 |
Pos logit contributions | |
ier | +0.163 |
ge | +0.134 |
than | +0.131 |
again | +0.131 |
anymore | +0.130 |
Neg logit contributions | |
Here | -0.157 |
First | -0.149 |
Many | -0.142 |
Watch | -0.138 |
Everyone | -0.137 |
Token | fireworks |
Token ID | 26056 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
ier | +0.178 |
ge | +0.149 |
anymore | +0.141 |
again | +0.139 |
than | +0.136 |
Neg logit contributions | |
Here | -0.143 |
First | -0.136 |
Many | -0.135 |
Everyone | -0.128 |
Watch | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ier | +0.225 |
ge | +0.203 |
iness | +0.190 |
lessness | +0.170 |
unsolved | +0.161 |
Neg logit contributions | |
This | -0.239 |
Here | -0.225 |
The | -0.223 |
Everyone | -0.218 |
First | -0.213 |
Token | She |
Token ID | 1375 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
Majesty | +0.029 |
majesty | +0.026 |
heit | +0.026 |
rac | +0.026 |
Here | +0.025 |
Neg logit contributions | |
again | -0.029 |
. | -0.027 |
and | -0.026 |
anymore | -0.025 |
y | -0.025 |
Token | asked |
Token ID | 1965 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
ier | +0.050 |
again | +0.045 |
y | +0.044 |
than | +0.042 |
ge | +0.041 |
Neg logit contributions | |
Here | -0.080 |
First | -0.076 |
Watch | -0.073 |
Deal | -0.071 |
Many | -0.070 |
Token | her |
Token ID | 607 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
ier | +0.075 |
again | +0.069 |
anymore | +0.064 |
than | +0.060 |
ge | +0.059 |
Neg logit contributions | |
Here | -0.090 |
First | -0.084 |
Watch | -0.082 |
Many | -0.077 |
disl | -0.076 |
Token | mom |
Token ID | 1995 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
ier | +0.080 |
ge | +0.069 |
than | +0.069 |
anymore | +0.068 |
again | +0.068 |
Neg logit contributions | |
Here | -0.039 |
First | -0.036 |
Many | -0.033 |
Watch | -0.031 |
Everyone | -0.031 |
Token | found |
Token ID | 1043 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
ier | +0.076 |
again | +0.060 |
than | +0.060 |
ge | +0.060 |
anymore | +0.059 |
Neg logit contributions | |
Here | -0.096 |
First | -0.091 |
Many | -0.087 |
Watch | -0.086 |
Everyone | -0.084 |
Token | a |
Token ID | 257 |
Feature activation | -6.92e+00 |
Pos logit contributions | |
ier | +0.085 |
again | +0.073 |
on | +0.071 |
more | +0.065 |
inside | +0.065 |
Neg logit contributions | |
Here | -0.140 |
disl | -0.129 |
First | -0.128 |
Watch | -0.128 |
Majesty | -0.127 |
Token | big |
Token ID | 1263 |
Feature activation | -7.91e+00 |
Pos logit contributions | |
ier | +0.156 |
ge | +0.127 |
than | +0.124 |
anymore | +0.122 |
again | +0.121 |
Neg logit contributions | |
Here | -0.102 |
First | -0.092 |
Watch | -0.092 |
Many | -0.090 |
This | -0.086 |
Token | roll |
Token ID | 4836 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
ier | +0.163 |
ge | +0.134 |
than | +0.126 |
anymore | +0.123 |
again | +0.123 |
Neg logit contributions | |
Here | -0.129 |
First | -0.123 |
Watch | -0.117 |
Many | -0.117 |
This | -0.115 |
Token | of |
Token ID | 286 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
ier | +0.200 |
ge | +0.180 |
than | +0.163 |
again | +0.151 |
knowing | +0.151 |
Neg logit contributions | |
First | -0.200 |
Here | -0.194 |
This | -0.189 |
Watch | -0.189 |
Everyone | -0.188 |
Token | tape |
Token ID | 9154 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
ier | +0.108 |
ge | +0.089 |
than | +0.088 |
again | +0.088 |
anymore | +0.087 |
Neg logit contributions | |
Here | -0.096 |
First | -0.091 |
Many | -0.086 |
Watch | -0.085 |
Everyone | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
ier | +0.191 |
ge | +0.146 |
iness | +0.140 |
sm | +0.137 |
lessness | +0.132 |
Neg logit contributions | |
First | -0.243 |
This | -0.240 |
Here | -0.233 |
The | -0.230 |
Ben | -0.218 |
Token | He |
Token ID | 679 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
Majesty | +0.009 |
majesty | +0.008 |
disl | +0.008 |
cient | +0.007 |
Deal | +0.007 |
Neg logit contributions | |
again | -0.009 |
. | -0.009 |
on | -0.009 |
and | -0.009 |
anymore | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
ier | +0.061 |
again | +0.051 |
than | +0.050 |
ge | +0.049 |
y | +0.048 |
Neg logit contributions | |
Here | -0.092 |
First | -0.086 |
Watch | -0.083 |
Many | -0.083 |
Everyone | -0.081 |
Token | very |
Token ID | 845 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
ier | +0.087 |
ge | +0.065 |
again | +0.063 |
anymore | +0.063 |
than | +0.061 |
Neg logit contributions | |
Here | -0.140 |
First | -0.135 |
Many | -0.131 |
Watch | -0.128 |
Everyone | -0.125 |
Token | happy |
Token ID | 3772 |
Feature activation | -8.50e+00 |
Pos logit contributions | |
ier | +0.046 |
than | +0.039 |
ge | +0.035 |
on | +0.034 |
again | +0.033 |
Neg logit contributions | |
Here | -0.064 |
First | -0.064 |
Many | -0.059 |
Everyone | -0.058 |
Watch | -0.058 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
ier | +0.062 |
than | +0.049 |
anymore | +0.049 |
ge | +0.049 |
again | +0.048 |
Neg logit contributions | |
Here | -0.065 |
First | -0.064 |
Many | -0.060 |
Watch | -0.059 |
Everyone | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
ier | +0.095 |
again | +0.079 |
anymore | +0.076 |
than | +0.076 |
ge | +0.073 |
Neg logit contributions | |
Here | -0.096 |
First | -0.089 |
Many | -0.083 |
Watch | -0.083 |
Everyone | -0.080 |
Token | big |
Token ID | 1263 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
ier | +0.148 |
ge | +0.128 |
anymore | +0.122 |
than | +0.122 |
again | +0.117 |
Neg logit contributions | |
Here | -0.087 |
Watch | -0.082 |
First | -0.078 |
Many | -0.076 |
Everyone | -0.075 |
Token | bottle |
Token ID | 9294 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
ier | +0.155 |
ge | +0.132 |
than | +0.121 |
anymore | +0.120 |
again | +0.116 |
Neg logit contributions | |
Here | -0.114 |
First | -0.108 |
Watch | -0.107 |
Many | -0.101 |
This | -0.099 |
Token | of |
Token ID | 286 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
ier | +0.156 |
ge | +0.145 |
anymore | +0.119 |
sooner | +0.117 |
than | +0.112 |
Neg logit contributions | |
Here | -0.228 |
This | -0.226 |
First | -0.225 |
Everyone | -0.218 |
The | -0.218 |
Token | shampoo |
Token ID | 47259 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
ier | +0.118 |
ge | +0.097 |
than | +0.096 |
again | +0.096 |
anymore | +0.095 |
Neg logit contributions | |
Here | -0.109 |
First | -0.104 |
Many | -0.098 |
Watch | -0.096 |
Everyone | -0.094 |
Token | on |
Token ID | 319 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
ge | +0.190 |
ier | +0.190 |
sooner | +0.163 |
anymore | +0.151 |
again | +0.142 |
Neg logit contributions | |
This | -0.231 |
First | -0.229 |
Here | -0.222 |
Ben | -0.220 |
Watch | -0.217 |
Token | the |
Token ID | 262 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
ier | +0.107 |
ge | +0.089 |
than | +0.088 |
again | +0.088 |
anymore | +0.087 |
Neg logit contributions | |
Here | -0.082 |
First | -0.078 |
Many | -0.073 |
Watch | -0.071 |
Everyone | -0.070 |
Token | shelf |
Token ID | 18316 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
ier | +0.080 |
ge | +0.070 |
than | +0.066 |
anymore | +0.065 |
again | +0.065 |
Neg logit contributions | |
Here | -0.058 |
First | -0.056 |
Watch | -0.052 |
Everyone | -0.052 |
Many | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ier | +0.134 |
ge | +0.117 |
iness | +0.091 |
le | +0.089 |
sooner | +0.089 |
Neg logit contributions | |
First | -0.198 |
The | -0.197 |
Here | -0.196 |
This | -0.196 |
Everyone | -0.184 |
Token | It |
Token ID | 632 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
Majesty | +0.021 |
disl | +0.021 |
majesty | +0.019 |
cient | +0.019 |
lder | +0.019 |
Neg logit contributions | |
again | -0.022 |
on | -0.021 |
. | -0.020 |
and | -0.020 |
y | -0.020 |
Token | wild |
Token ID | 4295 |
Feature activation | -9.74e+00 |
Pos logit contributions | |
ier | +0.185 |
ge | +0.165 |
iness | +0.150 |
sooner | +0.144 |
anymore | +0.140 |
Neg logit contributions | |
Here | -0.094 |
This | -0.091 |
Watch | -0.090 |
It | -0.090 |
The | -0.086 |
Token | - |
Token ID | 532 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
ier | +0.161 |
ge | +0.146 |
sooner | +0.117 |
iness | +0.106 |
iest | +0.106 |
Neg logit contributions | |
It | -0.182 |
The | -0.179 |
This | -0.179 |
Here | -0.169 |
Fin | -0.167 |
Token | it |
Token ID | 340 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
ier | +0.114 |
ge | +0.095 |
than | +0.092 |
anymore | +0.092 |
again | +0.091 |
Neg logit contributions | |
Here | -0.087 |
First | -0.084 |
Many | -0.080 |
Watch | -0.078 |
Everyone | -0.076 |
Token | was |
Token ID | 373 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
ier | +0.105 |
ge | +0.085 |
than | +0.081 |
anymore | +0.080 |
again | +0.077 |
Neg logit contributions | |
Here | -0.111 |
First | -0.107 |
Watch | -0.103 |
Many | -0.102 |
Everyone | -0.101 |
Token | a |
Token ID | 257 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
ier | +0.163 |
ge | +0.148 |
iness | +0.135 |
anymore | +0.134 |
le | +0.133 |
Neg logit contributions | |
First | -0.060 |
The | -0.059 |
Here | -0.058 |
Watch | -0.053 |
Many | -0.053 |
Token | shrink |
Token ID | 22085 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
ier | +0.145 |
ge | +0.123 |
anymore | +0.116 |
than | +0.115 |
again | +0.113 |
Neg logit contributions | |
Here | -0.092 |
Watch | -0.085 |
Many | -0.081 |
First | -0.079 |
Everyone | -0.076 |
Token | y |
Token ID | 88 |
Feature activation | -9.00e+00 |
Pos logit contributions | |
ge | +0.241 |
ier | +0.221 |
m | +0.186 |
sooner | +0.177 |
ably | +0.174 |
Neg logit contributions | |
Watch | -0.179 |
It | -0.170 |
This | -0.165 |
I | -0.162 |
Ben | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ier | +0.200 |
ge | +0.175 |
iness | +0.144 |
anymore | +0.142 |
m | +0.142 |
Neg logit contributions | |
Here | -0.129 |
Watch | -0.125 |
This | -0.120 |
The | -0.117 |
Everyone | -0.113 |
Token | She |
Token ID | 1375 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
Majesty | +0.010 |
majesty | +0.009 |
disl | +0.009 |
Deal | +0.009 |
heit | +0.009 |
Neg logit contributions | |
again | -0.014 |
on | -0.014 |
. | -0.014 |
and | -0.014 |
inside | -0.013 |
Token | didn |
Token ID | 1422 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
ier | +0.068 |
again | +0.055 |
than | +0.055 |
ge | +0.054 |
anymore | +0.053 |
Neg logit contributions | |
Here | -0.085 |
First | -0.082 |
Many | -0.077 |
Watch | -0.076 |
Everyone | -0.075 |
Token | 't |
Token ID | 470 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
ier | +0.056 |
again | +0.049 |
ge | +0.048 |
anymore | +0.048 |
than | +0.048 |
Neg logit contributions | |
Here | -0.028 |
First | -0.025 |
Many | -0.023 |
Watch | -0.023 |
Everyone | -0.021 |
Token | 's |
Token ID | 338 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
ier | +0.086 |
ge | +0.067 |
anymore | +0.066 |
than | +0.066 |
again | +0.066 |
Neg logit contributions | |
Here | -0.113 |
First | -0.108 |
Many | -0.103 |
Watch | -0.101 |
Everyone | -0.100 |
Token | dad |
Token ID | 9955 |
Feature activation | -7.74e+00 |
Pos logit contributions | |
ier | +0.094 |
than | +0.082 |
again | +0.082 |
ge | +0.081 |
anymore | +0.081 |
Neg logit contributions | |
Here | -0.042 |
First | -0.039 |
Many | -0.035 |
Watch | -0.034 |
Everyone | -0.033 |
Token | took |
Token ID | 1718 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
ier | +0.157 |
anymore | +0.130 |
ge | +0.124 |
than | +0.124 |
again | +0.117 |
Neg logit contributions | |
Here | -0.127 |
First | -0.122 |
Many | -0.114 |
The | -0.114 |
Everyone | -0.112 |
Token | out |
Token ID | 503 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
ier | +0.119 |
ge | +0.098 |
than | +0.097 |
anymore | +0.096 |
again | +0.096 |
Neg logit contributions | |
Here | -0.099 |
First | -0.095 |
Many | -0.090 |
Everyone | -0.087 |
Watch | -0.087 |
Token | a |
Token ID | 257 |
Feature activation | -5.68e+00 |
Pos logit contributions | |
ier | +0.134 |
ge | +0.113 |
than | +0.111 |
anymore | +0.109 |
again | +0.103 |
Neg logit contributions | |
First | -0.067 |
Many | -0.061 |
Here | -0.061 |
The | -0.060 |
Everyone | -0.058 |
Token | microscope |
Token ID | 36396 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
ier | +0.131 |
than | +0.106 |
ge | +0.102 |
anymore | +0.101 |
again | +0.098 |
Neg logit contributions | |
Here | -0.087 |
First | -0.082 |
Many | -0.078 |
Watch | -0.076 |
This | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ier | +0.207 |
ge | +0.181 |
iness | +0.153 |
m | +0.149 |
anymore | +0.138 |
Neg logit contributions | |
First | -0.232 |
This | -0.227 |
The | -0.215 |
Here | -0.209 |
Every | -0.204 |
Token | He |
Token ID | 679 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
Here | +0.011 |
disl | +0.010 |
Remy | +0.010 |
Watch | +0.010 |
Majesty | +0.010 |
Neg logit contributions | |
ier | -0.024 |
again | -0.024 |
than | -0.023 |
anymore | -0.022 |
y | -0.022 |
Token | looked |
Token ID | 3114 |
Feature activation | -5.94e+00 |
Pos logit contributions | |
ier | +0.093 |
anymore | +0.075 |
ge | +0.074 |
than | +0.073 |
again | +0.071 |
Neg logit contributions | |
Here | -0.093 |
First | -0.090 |
Many | -0.084 |
Watch | -0.083 |
Everyone | -0.081 |
Token | at |
Token ID | 379 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
ier | +0.108 |
ge | +0.087 |
iness | +0.077 |
y | +0.071 |
anymore | +0.071 |
Neg logit contributions | |
Here | -0.116 |
The | -0.113 |
First | -0.113 |
Many | -0.107 |
Watch | -0.105 |
Token | Katy |
Token ID | 36715 |
Feature activation | -9.55e+00 |
Pos logit contributions | |
ier | +0.080 |
ge | +0.066 |
than | +0.064 |
again | +0.063 |
anymore | +0.063 |
Neg logit contributions | |
Here | -0.063 |
First | -0.061 |
Many | -0.057 |
Everyone | -0.055 |
Watch | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
ier | +0.046 |
ge | +0.038 |
than | +0.036 |
again | +0.034 |
anymore | +0.033 |
Neg logit contributions | |
Here | -0.051 |
First | -0.049 |
Many | -0.048 |
Everyone | -0.046 |
This | -0.046 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
Here | +0.005 |
First | +0.005 |
Many | +0.004 |
Watch | +0.004 |
Everyone | +0.004 |
Neg logit contributions | |
ier | -0.008 |
ge | -0.007 |
than | -0.006 |
anymore | -0.006 |
again | -0.006 |
Token | found |
Token ID | 1043 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
ier | +0.078 |
again | +0.063 |
than | +0.063 |
ge | +0.062 |
anymore | +0.062 |
Neg logit contributions | |
Here | -0.089 |
First | -0.084 |
Many | -0.080 |
Watch | -0.079 |
Everyone | -0.078 |
Token | a |
Token ID | 257 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
ier | +0.086 |
again | +0.073 |
on | +0.069 |
anymore | +0.066 |
inside | +0.064 |
Neg logit contributions | |
Here | -0.115 |
First | -0.105 |
Watch | -0.105 |
disl | -0.102 |
Majesty | -0.101 |
Token | magic |
Token ID | 5536 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
ier | +0.140 |
ge | +0.115 |
than | +0.110 |
anymore | +0.109 |
iness | +0.106 |
Neg logit contributions | |
Here | -0.093 |
Watch | -0.085 |
First | -0.081 |
Many | -0.079 |
This | -0.075 |
Token | potion |
Token ID | 26572 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
ier | +0.226 |
ge | +0.217 |
m | +0.184 |
iness | +0.179 |
lling | +0.178 |
Neg logit contributions | |
Watch | -0.151 |
Here | -0.147 |
This | -0.131 |
It | -0.131 |
name | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ge | +0.218 |
ier | +0.207 |
sooner | +0.168 |
again | +0.152 |
anymore | +0.150 |
Neg logit contributions | |
This | -0.225 |
Here | -0.214 |
It | -0.202 |
The | -0.201 |
Watch | -0.198 |
Token | She |
Token ID | 1375 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
Majesty | +0.017 |
disl | +0.016 |
majesty | +0.015 |
ossible | +0.015 |
Fin | +0.015 |
Neg logit contributions | |
again | -0.023 |
on | -0.022 |
. | -0.021 |
anymore | -0.021 |
ier | -0.021 |
Token | drank |
Token ID | 24070 |
Feature activation | -7.40e+00 |
Pos logit contributions | |
ier | +0.065 |
again | +0.053 |
than | +0.052 |
ge | +0.052 |
anymore | +0.050 |
Neg logit contributions | |
Here | -0.080 |
First | -0.076 |
Many | -0.073 |
Watch | -0.072 |
Everyone | -0.071 |
Token | it |
Token ID | 340 |
Feature activation | -8.70e+00 |
Pos logit contributions | |
ier | +0.176 |
ge | +0.165 |
than | +0.142 |
iness | +0.136 |
anymore | +0.136 |
Neg logit contributions | |
Here | -0.093 |
First | -0.091 |
The | -0.091 |
Everyone | -0.085 |
It | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
ier | +0.157 |
ge | +0.149 |
ruck | +0.118 |
iness | +0.116 |
outage | +0.111 |
Neg logit contributions | |
First | -0.152 |
The | -0.147 |
This | -0.143 |
Every | -0.135 |
Here | -0.135 |
Token | do |
Token ID | 466 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
ier | +0.049 |
than | +0.042 |
anymore | +0.042 |
again | +0.041 |
ge | +0.040 |
Neg logit contributions | |
Here | -0.047 |
First | -0.045 |
Many | -0.041 |
Watch | -0.041 |
Everyone | -0.040 |
Token | not |
Token ID | 407 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
ier | +0.096 |
ge | +0.080 |
than | +0.079 |
again | +0.078 |
anymore | +0.077 |
Neg logit contributions | |
Here | -0.051 |
First | -0.048 |
Many | -0.045 |
Watch | -0.043 |
Everyone | -0.043 |
Token | like |
Token ID | 588 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
ier | +0.069 |
ge | +0.056 |
beneath | +0.055 |
again | +0.055 |
iest | +0.053 |
Neg logit contributions | |
Many | -0.045 |
Here | -0.045 |
First | -0.043 |
Everyone | -0.043 |
The | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
ier | +0.086 |
ge | +0.064 |
than | +0.061 |
again | +0.059 |
anymore | +0.058 |
Neg logit contributions | |
Here | -0.108 |
First | -0.104 |
Many | -0.103 |
Watch | -0.099 |
Everyone | -0.098 |
Token | eat |
Token ID | 4483 |
Feature activation | -8.94e+00 |
Pos logit contributions | |
ier | +0.090 |
ge | +0.076 |
than | +0.076 |
again | +0.076 |
anymore | +0.075 |
Neg logit contributions | |
Here | -0.052 |
First | -0.049 |
Many | -0.045 |
Watch | -0.044 |
Everyone | -0.043 |
Token | salad |
Token ID | 20698 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
ier | +0.185 |
ge | +0.153 |
iness | +0.137 |
than | +0.136 |
y | +0.135 |
Neg logit contributions | |
Here | -0.136 |
First | -0.134 |
Many | -0.133 |
Everyone | -0.130 |
The | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ier | +0.176 |
ge | +0.174 |
bul | +0.167 |
ruck | +0.152 |
visible | +0.150 |
Neg logit contributions | |
Ben | -0.230 |
First | -0.217 |
Remy | -0.215 |
Fin | -0.212 |
Leo | -0.209 |
Token | Salad |
Token ID | 42706 |
Feature activation | -8.75e+00 |
Pos logit contributions | |
Majesty | +0.016 |
majesty | +0.015 |
cient | +0.014 |
lder | +0.014 |
Here | +0.014 |
Neg logit contributions | |
anymore | -0.022 |
again | -0.021 |
. | -0.019 |
than | -0.019 |
ier | -0.019 |
Token | is |
Token ID | 318 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
ier | +0.196 |
ge | +0.174 |
again | +0.159 |
anymore | +0.159 |
than | +0.155 |
Neg logit contributions | |
Here | -0.117 |
First | -0.109 |
Watch | -0.101 |
This | -0.101 |
The | -0.098 |
Token | green |
Token ID | 4077 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
ier | +0.095 |
ge | +0.081 |
again | +0.075 |
than | +0.074 |
anymore | +0.074 |
Neg logit contributions | |
Here | -0.096 |
First | -0.090 |
Many | -0.085 |
Watch | -0.084 |
Everyone | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
ier | +0.152 |
ge | +0.146 |
visible | +0.105 |
sooner | +0.098 |
emanating | +0.098 |
Neg logit contributions | |
First | -0.194 |
Here | -0.193 |
The | -0.190 |
This | -0.189 |
Every | -0.180 |
Token | day |
Token ID | 1110 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
ier | +0.088 |
ge | +0.076 |
than | +0.063 |
anymore | +0.063 |
again | +0.058 |
Neg logit contributions | |
Here | -0.078 |
Many | -0.076 |
The | -0.071 |
First | -0.071 |
ossible | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ier | +0.057 |
ge | +0.047 |
than | +0.045 |
anymore | +0.041 |
again | +0.041 |
Neg logit contributions | |
Here | -0.068 |
First | -0.067 |
Many | -0.064 |
Everyone | -0.062 |
Watch | -0.062 |
Token | Max |
Token ID | 5436 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
ier | +0.004 |
ge | +0.004 |
than | +0.004 |
anymore | +0.004 |
again | +0.004 |
Neg logit contributions | |
Here | -0.002 |
First | -0.001 |
Many | -0.001 |
Watch | -0.001 |
Everyone | -0.001 |
Token | started |
Token ID | 2067 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
ier | +0.103 |
ge | +0.083 |
than | +0.083 |
again | +0.082 |
anymore | +0.081 |
Neg logit contributions | |
Here | -0.111 |
First | -0.106 |
Many | -0.100 |
Watch | -0.098 |
Everyone | -0.096 |
Token | smoking |
Token ID | 9216 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
ier | +0.122 |
iest | +0.096 |
iness | +0.089 |
than | +0.086 |
ge | +0.085 |
Neg logit contributions | |
The | -0.095 |
Many | -0.090 |
First | -0.089 |
Mitt | -0.089 |
This | -0.088 |
Token | cigarettes |
Token ID | 17626 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
ier | +0.205 |
ge | +0.194 |
iness | +0.157 |
than | +0.150 |
ever | +0.148 |
Neg logit contributions | |
The | -0.167 |
First | -0.159 |
It | -0.152 |
Everyone | -0.151 |
Many | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
ier | +0.160 |
able | +0.150 |
ge | +0.146 |
iest | +0.131 |
unsolved | +0.130 |
Neg logit contributions | |
This | -0.233 |
First | -0.226 |
The | -0.219 |
Here | -0.207 |
It | -0.207 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
Here | +0.011 |
First | +0.010 |
ossible | +0.010 |
rac | +0.010 |
Majesty | +0.009 |
Neg logit contributions | |
again | -0.015 |
ier | -0.015 |
anymore | -0.014 |
on | -0.013 |
than | -0.013 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
ier | +0.097 |
ge | +0.078 |
than | +0.077 |
anymore | +0.076 |
again | +0.074 |
Neg logit contributions | |
Here | -0.100 |
First | -0.096 |
Many | -0.091 |
Watch | -0.089 |
Everyone | -0.088 |
Token | 't |
Token ID | 470 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
ier | +0.040 |
again | +0.035 |
anymore | +0.035 |
ge | +0.034 |
than | +0.033 |
Neg logit contributions | |
Here | -0.024 |
First | -0.021 |
Majesty | -0.020 |
Watch | -0.020 |
Many | -0.019 |
Token | know |
Token ID | 760 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
ier | +0.081 |
again | +0.071 |
ge | +0.071 |
anymore | +0.069 |
beneath | +0.068 |
Neg logit contributions | |
Many | -0.045 |
Everyone | -0.040 |
Watch | -0.040 |
First | -0.039 |
Here | -0.039 |
Token | all |
Token ID | 477 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
ier | +0.162 |
ge | +0.140 |
than | +0.132 |
anymore | +0.127 |
again | +0.126 |
Neg logit contributions | |
Here | -0.106 |
First | -0.102 |
Everyone | -0.098 |
Many | -0.097 |
The | -0.094 |
Token | of |
Token ID | 286 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ier | +0.060 |
ge | +0.048 |
again | +0.046 |
anymore | +0.046 |
than | +0.046 |
Neg logit contributions | |
Here | -0.087 |
First | -0.082 |
Many | -0.079 |
Everyone | -0.078 |
Watch | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
ier | +0.045 |
again | +0.038 |
than | +0.037 |
anymore | +0.037 |
ge | +0.037 |
Neg logit contributions | |
Here | -0.047 |
First | -0.044 |
Watch | -0.042 |
Many | -0.041 |
Everyone | -0.039 |
Token | man |
Token ID | 582 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
ier | +0.073 |
ge | +0.066 |
again | +0.061 |
than | +0.060 |
anymore | +0.059 |
Neg logit contributions | |
Here | -0.058 |
Many | -0.057 |
First | -0.054 |
Everyone | -0.052 |
Watch | -0.049 |
Token | 's |
Token ID | 338 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
ier | +0.230 |
iness | +0.177 |
than | +0.176 |
anymore | +0.172 |
ge | +0.171 |
Neg logit contributions | |
Here | -0.142 |
This | -0.142 |
The | -0.136 |
Many | -0.126 |
Everyone | -0.123 |
Token | cakes |
Token ID | 30849 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
ier | +0.081 |
ge | +0.068 |
again | +0.066 |
anymore | +0.065 |
than | +0.065 |
Neg logit contributions | |
Here | -0.073 |
First | -0.068 |
Many | -0.066 |
Everyone | -0.063 |
Watch | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ier | +0.171 |
ge | +0.138 |
iest | +0.127 |
le | +0.125 |
bul | +0.122 |
Neg logit contributions | |
This | -0.253 |
The | -0.240 |
Here | -0.238 |
First | -0.236 |
Jerry | -0.234 |
Token | The |
Token ID | 383 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Majesty | +0.021 |
Deal | +0.021 |
majesty | +0.020 |
Here | +0.019 |
disl | +0.018 |
Neg logit contributions | |
again | -0.030 |
. | -0.030 |
than | -0.028 |
anymore | -0.028 |
and | -0.028 |
Token | man |
Token ID | 582 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
ier | +0.031 |
ge | +0.027 |
than | +0.025 |
again | +0.025 |
anymore | +0.025 |
Neg logit contributions | |
Here | -0.030 |
First | -0.028 |
Many | -0.028 |
Everyone | -0.027 |
Watch | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
ier | +0.104 |
ge | +0.085 |
than | +0.084 |
anymore | +0.082 |
again | +0.077 |
Neg logit contributions | |
Here | -0.105 |
First | -0.100 |
Many | -0.099 |
Everyone | -0.096 |
The | -0.095 |
Token | very |
Token ID | 845 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ier | +0.057 |
ge | +0.043 |
than | +0.040 |
again | +0.040 |
anymore | +0.039 |
Neg logit contributions | |
Here | -0.100 |
First | -0.096 |
Many | -0.095 |
Watch | -0.092 |
Everyone | -0.091 |
Token | Fred |
Token ID | 8559 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
ier | +0.033 |
ge | +0.025 |
than | +0.025 |
again | +0.025 |
anymore | +0.024 |
Neg logit contributions | |
Here | -0.054 |
First | -0.052 |
Many | -0.050 |
Watch | -0.049 |
Everyone | -0.049 |
Token | spotted |
Token ID | 13489 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
ier | +0.083 |
ge | +0.067 |
than | +0.067 |
anymore | +0.066 |
again | +0.066 |
Neg logit contributions | |
Here | -0.080 |
First | -0.076 |
Many | -0.072 |
Watch | -0.071 |
Everyone | -0.069 |
Token | a |
Token ID | 257 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
ier | +0.078 |
again | +0.072 |
anymore | +0.065 |
on | +0.062 |
than | +0.061 |
Neg logit contributions | |
Here | -0.112 |
First | -0.103 |
Watch | -0.099 |
Deal | -0.098 |
Many | -0.097 |
Token | jar |
Token ID | 17379 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
ier | +0.119 |
ge | +0.098 |
than | +0.095 |
anymore | +0.094 |
again | +0.092 |
Neg logit contributions | |
Here | -0.080 |
Watch | -0.073 |
First | -0.073 |
Many | -0.071 |
Everyone | -0.067 |
Token | of |
Token ID | 286 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
ier | +0.145 |
ge | +0.125 |
anymore | +0.112 |
than | +0.105 |
again | +0.098 |
Neg logit contributions | |
Here | -0.225 |
First | -0.217 |
ossible | -0.215 |
This | -0.215 |
Watch | -0.213 |
Token | glue |
Token ID | 22749 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
ier | +0.108 |
ge | +0.091 |
anymore | +0.087 |
again | +0.087 |
than | +0.087 |
Neg logit contributions | |
Here | -0.094 |
First | -0.089 |
Many | -0.084 |
Watch | -0.083 |
Everyone | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ier | +0.170 |
ge | +0.127 |
sooner | +0.122 |
than | +0.114 |
anymore | +0.113 |
Neg logit contributions | |
Pip | -0.232 |
Fin | -0.231 |
Harry | -0.223 |
This | -0.221 |
Remy | -0.221 |
Token | He |
Token ID | 679 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
Deal | +0.018 |
disl | +0.017 |
Majesty | +0.017 |
ossible | +0.017 |
majesty | +0.016 |
Neg logit contributions | |
again | -0.019 |
than | -0.017 |
and | -0.017 |
ier | -0.017 |
. | -0.016 |
Token | thought |
Token ID | 1807 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
ier | +0.052 |
again | +0.045 |
than | +0.044 |
y | +0.043 |
ge | +0.043 |
Neg logit contributions | |
Here | -0.072 |
First | -0.068 |
Many | -0.064 |
Everyone | -0.064 |
Watch | -0.063 |
Token | it |
Token ID | 340 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
ier | +0.074 |
ge | +0.060 |
than | +0.059 |
anymore | +0.057 |
again | +0.057 |
Neg logit contributions | |
Here | -0.081 |
First | -0.077 |
Many | -0.074 |
Watch | -0.072 |
Everyone | -0.070 |
Token | looked |
Token ID | 3114 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
ier | +0.073 |
ge | +0.059 |
than | +0.057 |
anymore | +0.055 |
again | +0.052 |
Neg logit contributions | |
Here | -0.084 |
First | -0.083 |
This | -0.076 |
Watch | -0.076 |
Many | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
ier | +0.087 |
ge | +0.073 |
than | +0.072 |
again | +0.071 |
anymore | +0.070 |
Neg logit contributions | |
Here | -0.068 |
First | -0.065 |
Many | -0.061 |
Everyone | -0.059 |
Watch | -0.059 |
Token | booth |
Token ID | 18600 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
ier | +0.127 |
ge | +0.107 |
than | +0.102 |
anymore | +0.100 |
iness | +0.100 |
Neg logit contributions | |
Here | -0.076 |
Many | -0.072 |
Watch | -0.072 |
Everyone | -0.068 |
First | -0.066 |
Token | giving |
Token ID | 3501 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
ier | +0.185 |
ge | +0.148 |
iness | +0.142 |
le | +0.138 |
iest | +0.133 |
Neg logit contributions | |
Here | -0.184 |
The | -0.179 |
This | -0.176 |
Everyone | -0.169 |
Many | -0.169 |
Token | out |
Token ID | 503 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
ier | +0.137 |
ge | +0.119 |
than | +0.111 |
anymore | +0.107 |
iness | +0.103 |
Neg logit contributions | |
Here | -0.110 |
First | -0.108 |
Everyone | -0.102 |
Many | -0.099 |
The | -0.098 |
Token | free |
Token ID | 1479 |
Feature activation | -8.92e+00 |
Pos logit contributions | |
ier | +0.114 |
ge | +0.098 |
than | +0.093 |
anymore | +0.090 |
again | +0.090 |
Neg logit contributions | |
Here | -0.074 |
First | -0.070 |
Many | -0.070 |
Everyone | -0.068 |
The | -0.065 |
Token | balloons |
Token ID | 35485 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
ier | +0.137 |
ge | +0.109 |
iness | +0.085 |
m | +0.084 |
web | +0.079 |
Neg logit contributions | |
Everyone | -0.183 |
First | -0.181 |
Here | -0.178 |
The | -0.177 |
Many | -0.174 |
Token | to |
Token ID | 284 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
ier | +0.197 |
ge | +0.160 |
le | +0.133 |
iness | +0.133 |
iest | +0.130 |
Neg logit contributions | |
First | -0.229 |
ossible | -0.227 |
This | -0.225 |
Here | -0.223 |
The | -0.222 |
Token | kids |
Token ID | 3988 |
Feature activation | -9.76e+00 |
Pos logit contributions | |
ier | +0.092 |
ge | +0.076 |
than | +0.076 |
again | +0.075 |
anymore | +0.074 |
Neg logit contributions | |
Here | -0.070 |
First | -0.066 |
Many | -0.063 |
Everyone | -0.060 |
Watch | -0.060 |
Token | who |
Token ID | 508 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
ier | +0.137 |
iness | +0.088 |
iest | +0.085 |
ge | +0.085 |
than | +0.082 |
Neg logit contributions | |
Here | -0.223 |
First | -0.219 |
Everyone | -0.210 |
This | -0.207 |
Many | -0.205 |
Token | played |
Token ID | 2826 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
ier | +0.104 |
ge | +0.085 |
anymore | +0.084 |
than | +0.082 |
again | +0.081 |
Neg logit contributions | |
Here | -0.080 |
Everyone | -0.075 |
First | -0.075 |
Many | -0.074 |
The | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
ier | +0.127 |
ge | +0.100 |
than | +0.094 |
anymore | +0.093 |
again | +0.092 |
Neg logit contributions | |
Here | -0.157 |
First | -0.151 |
Many | -0.147 |
Everyone | -0.143 |
Watch | -0.142 |
Token | and |
Token ID | 290 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
ier | +0.111 |
anymore | +0.085 |
iness | +0.079 |
iest | +0.076 |
than | +0.074 |
Neg logit contributions | |
The | -0.117 |
First | -0.113 |
This | -0.111 |
Here | -0.111 |
Watch | -0.107 |
Token | stole |
Token ID | 18240 |
Feature activation | -7.67e+00 |
Pos logit contributions | |
ier | +0.063 |
anymore | +0.050 |
than | +0.050 |
ge | +0.050 |
again | +0.049 |
Neg logit contributions | |
Here | -0.063 |
First | -0.060 |
Many | -0.057 |
Watch | -0.056 |
Everyone | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
ier | +0.172 |
ge | +0.151 |
than | +0.138 |
anymore | +0.132 |
y | +0.131 |
Neg logit contributions | |
Here | -0.111 |
First | -0.105 |
Everyone | -0.103 |
The | -0.101 |
Many | -0.100 |
Token | pocket |
Token ID | 10000 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
ier | +0.089 |
ge | +0.082 |
than | +0.074 |
y | +0.071 |
again | +0.071 |
Neg logit contributions | |
Here | -0.055 |
First | -0.053 |
Many | -0.052 |
Watch | -0.048 |
This | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
ier | +0.145 |
ge | +0.099 |
iness | +0.097 |
than | +0.094 |
bul | +0.093 |
Neg logit contributions | |
This | -0.228 |
Here | -0.221 |
The | -0.220 |
First | -0.216 |
Many | -0.208 |
Token | cookies |
Token ID | 14746 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ier | +0.081 |
ge | +0.067 |
than | +0.066 |
again | +0.066 |
anymore | +0.065 |
Neg logit contributions | |
Here | -0.065 |
First | -0.061 |
Many | -0.058 |
Watch | -0.056 |
Everyone | -0.055 |
Token | ! |
Token ID | 0 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ier | +0.175 |
ge | +0.140 |
iest | +0.133 |
bul | +0.130 |
sooner | +0.117 |
Neg logit contributions | |
This | -0.252 |
The | -0.243 |
First | -0.241 |
Here | -0.240 |
Jerry | -0.236 |
Token | It |
Token ID | 632 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
Here | +0.017 |
Majesty | +0.016 |
majesty | +0.015 |
disl | +0.014 |
First | +0.014 |
Neg logit contributions | |
ier | -0.049 |
again | -0.048 |
anymore | -0.047 |
. | -0.045 |
than | -0.045 |
Token | jumped |
Token ID | 11687 |
Feature activation | -8.89e+00 |
Pos logit contributions | |
ier | +0.072 |
ge | +0.059 |
than | +0.056 |
anymore | +0.056 |
again | +0.055 |
Neg logit contributions | |
Here | -0.073 |
First | -0.071 |
Many | -0.068 |
Watch | -0.067 |
Everyone | -0.066 |
Token | away |
Token ID | 1497 |
Feature activation | -8.34e+00 |
Pos logit contributions | |
ier | +0.122 |
ge | +0.100 |
than | +0.088 |
iness | +0.082 |
iest | +0.080 |
Neg logit contributions | |
First | -0.191 |
Here | -0.187 |
The | -0.185 |
This | -0.184 |
Watch | -0.182 |
Token | with |
Token ID | 351 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ier | +0.138 |
iest | +0.119 |
iness | +0.119 |
le | +0.117 |
ge | +0.112 |
Neg logit contributions | |
The | -0.142 |
This | -0.122 |
Fred | -0.115 |
Fin | -0.111 |
| -0.110 |
Token | found |
Token ID | 1043 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
ier | +0.058 |
again | +0.047 |
than | +0.047 |
ge | +0.046 |
anymore | +0.046 |
Neg logit contributions | |
Here | -0.068 |
First | -0.064 |
Many | -0.061 |
Watch | -0.060 |
Everyone | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
ier | +0.089 |
again | +0.075 |
on | +0.071 |
anymore | +0.068 |
inside | +0.065 |
Neg logit contributions | |
Here | -0.119 |
Watch | -0.110 |
First | -0.109 |
disl | -0.106 |
Majesty | -0.104 |
Token | sp |
Token ID | 599 |
Feature activation | -8.01e+00 |
Pos logit contributions | |
ier | +0.145 |
ge | +0.117 |
than | +0.114 |
anymore | +0.113 |
iness | +0.113 |
Neg logit contributions | |
Here | -0.086 |
Watch | -0.078 |
Many | -0.074 |
First | -0.074 |
This | -0.072 |
Token | ool |
Token ID | 970 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
ier | +0.139 |
again | +0.135 |
ge | +0.131 |
anymore | +0.125 |
sooner | +0.123 |
Neg logit contributions | |
Here | -0.127 |
First | -0.114 |
Watch | -0.114 |
Everyone | -0.112 |
Many | -0.111 |
Token | of |
Token ID | 286 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
ier | +0.115 |
ge | +0.115 |
than | +0.099 |
sooner | +0.091 |
anymore | +0.088 |
Neg logit contributions | |
First | -0.221 |
Here | -0.220 |
The | -0.214 |
This | -0.210 |
Everyone | -0.206 |
Token | thread |
Token ID | 4704 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ier | +0.110 |
ge | +0.091 |
anymore | +0.090 |
again | +0.090 |
than | +0.089 |
Neg logit contributions | |
Here | -0.090 |
First | -0.086 |
Many | -0.081 |
Watch | -0.079 |
Everyone | -0.076 |
Token | on |
Token ID | 319 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
ier | +0.177 |
ge | +0.148 |
sooner | +0.147 |
iness | +0.133 |
anymore | +0.129 |
Neg logit contributions | |
This | -0.212 |
The | -0.205 |
It | -0.196 |
First | -0.191 |
Pip | -0.189 |
Token | the |
Token ID | 262 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ier | +0.114 |
ge | +0.093 |
than | +0.093 |
again | +0.091 |
anymore | +0.091 |
Neg logit contributions | |
Here | -0.074 |
First | -0.072 |
Many | -0.067 |
Everyone | -0.064 |
The | -0.063 |
Token | floor |
Token ID | 4314 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
ier | +0.065 |
ge | +0.055 |
than | +0.052 |
anymore | +0.052 |
again | +0.052 |
Neg logit contributions | |
Here | -0.051 |
First | -0.048 |
Many | -0.045 |
Watch | -0.045 |
Everyone | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ier | +0.137 |
ge | +0.115 |
bul | +0.095 |
le | +0.093 |
iest | +0.093 |
Neg logit contributions | |
The | -0.176 |
This | -0.172 |
First | -0.166 |
Here | -0.165 |
Every | -0.161 |
Token | It |
Token ID | 632 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
Majesty | +0.026 |
disl | +0.024 |
majesty | +0.024 |
heit | +0.022 |
Deal | +0.021 |
Neg logit contributions | |
again | -0.022 |
on | -0.020 |
and | -0.020 |
. | -0.020 |
inside | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
ier | +0.057 |
again | +0.049 |
anymore | +0.046 |
on | +0.045 |
than | +0.044 |
Neg logit contributions | |
Here | -0.075 |
First | -0.071 |
Watch | -0.068 |
Deal | -0.066 |
Many | -0.065 |
Token | it |
Token ID | 340 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
ier | +0.068 |
ge | +0.057 |
than | +0.054 |
anymore | +0.053 |
again | +0.052 |
Neg logit contributions | |
Here | -0.054 |
First | -0.051 |
Many | -0.048 |
Everyone | -0.047 |
Watch | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
ier | +0.112 |
ge | +0.097 |
than | +0.092 |
anymore | +0.085 |
iness | +0.082 |
Neg logit contributions | |
Here | -0.082 |
The | -0.082 |
This | -0.079 |
First | -0.079 |
Everyone | -0.078 |
Token | full |
Token ID | 1336 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
ier | +0.104 |
ge | +0.093 |
iness | +0.083 |
le | +0.082 |
y | +0.081 |
Neg logit contributions | |
The | -0.070 |
Here | -0.068 |
First | -0.067 |
Every | -0.065 |
Mitt | -0.063 |
Token | of |
Token ID | 286 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
ge | +0.136 |
ier | +0.128 |
lling | +0.097 |
than | +0.093 |
anymore | +0.093 |
Neg logit contributions | |
The | -0.123 |
Everyone | -0.120 |
Here | -0.120 |
Many | -0.118 |
Every | -0.115 |
Token | ink |
Token ID | 16882 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ier | +0.115 |
ge | +0.097 |
y | +0.087 |
again | +0.086 |
anymore | +0.084 |
Neg logit contributions | |
Here | -0.084 |
Many | -0.084 |
Everyone | -0.076 |
Watch | -0.075 |
First | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ge | +0.194 |
ier | +0.172 |
sooner | +0.145 |
away | +0.126 |
iness | +0.126 |
Neg logit contributions | |
This | -0.235 |
Everyone | -0.222 |
First | -0.219 |
Watch | -0.214 |
Here | -0.212 |
Token | She |
Token ID | 1375 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
ossible | +0.020 |
Here | +0.019 |
Majesty | +0.018 |
disl | +0.018 |
rac | +0.017 |
Neg logit contributions | |
again | -0.028 |
anymore | -0.028 |
ier | -0.027 |
than | -0.027 |
inside | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
ier | +0.044 |
again | +0.039 |
than | +0.037 |
y | +0.037 |
ge | +0.036 |
Neg logit contributions | |
Here | -0.064 |
First | -0.061 |
Many | -0.057 |
Watch | -0.057 |
Everyone | -0.056 |
Token | so |
Token ID | 523 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ier | +0.072 |
ge | +0.056 |
than | +0.054 |
again | +0.054 |
anymore | +0.054 |
Neg logit contributions | |
Here | -0.100 |
First | -0.096 |
Many | -0.093 |
Watch | -0.091 |
Everyone | -0.089 |
Token | excited |
Token ID | 6568 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
ier | +0.024 |
than | +0.020 |
again | +0.018 |
ge | +0.018 |
anymore | +0.018 |
Neg logit contributions | |
Here | -0.030 |
First | -0.029 |
Watch | -0.027 |
Many | -0.027 |
Everyone | -0.026 |
Token | my |
Token ID | 1820 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
ier | +0.074 |
than | +0.062 |
ge | +0.060 |
anymore | +0.059 |
again | +0.055 |
Neg logit contributions | |
Here | -0.056 |
First | -0.055 |
ossible | -0.054 |
Watch | -0.050 |
Many | -0.050 |
Token | accidentally |
Token ID | 14716 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
ier | +0.099 |
ge | +0.082 |
than | +0.081 |
anymore | +0.079 |
again | +0.074 |
Neg logit contributions | |
Here | -0.078 |
First | -0.075 |
Many | -0.073 |
Watch | -0.072 |
The | -0.071 |
Token | spilled |
Token ID | 31896 |
Feature activation | -7.77e+00 |
Pos logit contributions | |
ier | +0.077 |
than | +0.065 |
anymore | +0.063 |
ge | +0.062 |
again | +0.060 |
Neg logit contributions | |
Here | -0.068 |
First | -0.066 |
Many | -0.062 |
Watch | -0.062 |
Everyone | -0.060 |
Token | some |
Token ID | 617 |
Feature activation | -7.38e+00 |
Pos logit contributions | |
ier | +0.168 |
ge | +0.156 |
than | +0.143 |
y | +0.137 |
iness | +0.130 |
Neg logit contributions | |
First | -0.107 |
Here | -0.104 |
Everyone | -0.101 |
The | -0.101 |
Many | -0.098 |
Token | hot |
Token ID | 3024 |
Feature activation | -8.11e+00 |
Pos logit contributions | |
ge | +0.154 |
ier | +0.148 |
than | +0.126 |
again | +0.126 |
anymore | +0.126 |
Neg logit contributions | |
Many | -0.100 |
Everyone | -0.100 |
Here | -0.099 |
First | -0.096 |
The | -0.088 |
Token | soup |
Token ID | 17141 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ge | +0.169 |
ier | +0.167 |
anymore | +0.141 |
forever | +0.141 |
again | +0.137 |
Neg logit contributions | |
First | -0.115 |
Here | -0.111 |
Many | -0.105 |
Everyone | -0.105 |
Now | -0.102 |
Token | on |
Token ID | 319 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
ge | +0.169 |
ier | +0.153 |
sooner | +0.123 |
conflicts | +0.117 |
owing | +0.110 |
Neg logit contributions | |
This | -0.238 |
The | -0.228 |
First | -0.227 |
Ben | -0.223 |
Mitt | -0.222 |
Token | his |
Token ID | 465 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
ier | +0.076 |
ge | +0.063 |
than | +0.062 |
again | +0.061 |
anymore | +0.061 |
Neg logit contributions | |
Here | -0.056 |
First | -0.054 |
Many | -0.050 |
Everyone | -0.049 |
Watch | -0.049 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
ier | +0.101 |
ge | +0.086 |
than | +0.082 |
anymore | +0.081 |
again | +0.081 |
Neg logit contributions | |
Here | -0.066 |
First | -0.062 |
Many | -0.058 |
Watch | -0.057 |
Everyone | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ier | +0.138 |
ge | +0.125 |
conflicts | +0.098 |
anymore | +0.091 |
sooner | +0.091 |
Neg logit contributions | |
This | -0.201 |
The | -0.199 |
It | -0.192 |
First | -0.188 |
Here | -0.187 |
Token | It |
Token ID | 632 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
Here | +0.019 |
Deal | +0.018 |
ossible | +0.018 |
First | +0.017 |
Majesty | +0.017 |
Neg logit contributions | |
ier | -0.031 |
again | -0.031 |
anymore | -0.030 |
. | -0.028 |
on | -0.028 |
Token | liked |
Token ID | 8288 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
ier | +0.072 |
ge | +0.057 |
again | +0.056 |
anymore | +0.056 |
than | +0.056 |
Neg logit contributions | |
Here | -0.082 |
First | -0.078 |
Many | -0.074 |
Watch | -0.072 |
Everyone | -0.072 |
Token | to |
Token ID | 284 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ier | +0.071 |
ge | +0.052 |
than | +0.050 |
anymore | +0.049 |
again | +0.048 |
Neg logit contributions | |
Here | -0.118 |
First | -0.114 |
Many | -0.110 |
Watch | -0.108 |
Everyone | -0.106 |
Token | look |
Token ID | 804 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
ier | +0.043 |
again | +0.039 |
anymore | +0.037 |
than | +0.037 |
ge | +0.036 |
Neg logit contributions | |
Here | -0.042 |
First | -0.037 |
Watch | -0.035 |
Many | -0.034 |
Deal | -0.034 |
Token | at |
Token ID | 379 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
ier | +0.074 |
ge | +0.057 |
than | +0.051 |
again | +0.048 |
y | +0.048 |
Neg logit contributions | |
Here | -0.121 |
First | -0.117 |
Everyone | -0.112 |
Many | -0.111 |
Watch | -0.110 |
Token | the |
Token ID | 262 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
ier | +0.087 |
ge | +0.072 |
than | +0.070 |
again | +0.069 |
anymore | +0.069 |
Neg logit contributions | |
Here | -0.069 |
First | -0.066 |
Many | -0.062 |
Everyone | -0.060 |
Watch | -0.059 |
Token | stars |
Token ID | 5788 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ier | +0.081 |
ge | +0.072 |
than | +0.063 |
again | +0.063 |
anymore | +0.062 |
Neg logit contributions | |
Here | -0.062 |
Many | -0.057 |
Everyone | -0.056 |
Watch | -0.055 |
First | -0.054 |
Token | at |
Token ID | 379 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
ier | +0.170 |
ge | +0.162 |
less | +0.140 |
sm | +0.137 |
cancelled | +0.136 |
Neg logit contributions | |
The | -0.231 |
This | -0.216 |
Everyone | -0.213 |
It | -0.208 |
Here | -0.207 |
Token | night |
Token ID | 1755 |
Feature activation | -8.36e+00 |
Pos logit contributions | |
ier | +0.055 |
ge | +0.043 |
than | +0.041 |
again | +0.040 |
anymore | +0.040 |
Neg logit contributions | |
Here | -0.070 |
First | -0.068 |
Many | -0.065 |
Everyone | -0.064 |
The | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ier | +0.119 |
ge | +0.095 |
iness | +0.077 |
m | +0.066 |
sooner | +0.065 |
Neg logit contributions | |
Everyone | -0.188 |
This | -0.187 |
The | -0.186 |
Many | -0.179 |
Here | -0.178 |
Token | He |
Token ID | 679 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
Here | +0.023 |
Majesty | +0.023 |
majesty | +0.021 |
lder | +0.021 |
cient | +0.020 |
Neg logit contributions | |
anymore | -0.038 |
ier | -0.038 |
again | -0.036 |
than | -0.036 |
. | -0.034 |
Token | would |
Token ID | 561 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
ier | +0.065 |
ge | +0.051 |
anymore | +0.050 |
than | +0.050 |
again | +0.049 |
Neg logit contributions | |
Here | -0.077 |
First | -0.074 |
Many | -0.071 |
Watch | -0.069 |
Everyone | -0.068 |
Token | it |
Token ID | 340 |
Feature activation | -7.17e+00 |
Pos logit contributions | |
ier | +0.097 |
ge | +0.087 |
than | +0.082 |
anymore | +0.078 |
y | +0.077 |
Neg logit contributions | |
Here | -0.070 |
First | -0.067 |
Many | -0.065 |
Everyone | -0.065 |
The | -0.064 |
Token | was |
Token ID | 373 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
ier | +0.167 |
than | +0.138 |
ge | +0.131 |
iness | +0.131 |
iest | +0.129 |
Neg logit contributions | |
The | -0.085 |
Every | -0.072 |
It | -0.072 |
His | -0.069 |
| -0.067 |
Token | an |
Token ID | 281 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
ier | +0.086 |
ge | +0.074 |
y | +0.070 |
iness | +0.068 |
than | +0.067 |
Neg logit contributions | |
Here | -0.059 |
The | -0.058 |
First | -0.057 |
Fin | -0.054 |
Pip | -0.053 |
Token | old |
Token ID | 1468 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
ier | +0.070 |
again | +0.059 |
ge | +0.059 |
anymore | +0.058 |
than | +0.057 |
Neg logit contributions | |
Here | -0.060 |
First | -0.058 |
Many | -0.057 |
Watch | -0.054 |
Everyone | -0.052 |
Token | hamb |
Token ID | 41478 |
Feature activation | -7.88e+00 |
Pos logit contributions | |
ier | +0.162 |
ge | +0.136 |
le | +0.126 |
anymore | +0.123 |
iness | +0.122 |
Neg logit contributions | |
Here | -0.099 |
The | -0.095 |
Many | -0.093 |
This | -0.091 |
Watch | -0.091 |
Token | urger |
Token ID | 32650 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ier | +0.168 |
again | +0.147 |
ge | +0.147 |
than | +0.145 |
anymore | +0.143 |
Neg logit contributions | |
Here | -0.115 |
First | -0.107 |
Many | -0.100 |
Watch | -0.098 |
Everyone | -0.098 |
Token | wrapper |
Token ID | 29908 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
ge | +0.186 |
conflicts | +0.179 |
ier | +0.167 |
able | +0.166 |
away | +0.159 |
Neg logit contributions | |
Ben | -0.202 |
It | -0.200 |
This | -0.199 |
The | -0.197 |
Tom | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
conflicts | +0.145 |
ge | +0.140 |
ier | +0.140 |
sooner | +0.126 |
away | +0.124 |
Neg logit contributions | |
This | -0.194 |
It | -0.191 |
The | -0.188 |
Ben | -0.187 |
Pip | -0.185 |
Token | The |
Token ID | 383 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
disl | +0.028 |
Deal | +0.028 |
Majesty | +0.028 |
majesty | +0.026 |
ossible | +0.025 |
Neg logit contributions | |
again | -0.046 |
. | -0.043 |
and | -0.043 |
too | -0.042 |
ier | -0.041 |
Token | car |
Token ID | 1097 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
ier | +0.023 |
ge | +0.019 |
than | +0.019 |
again | +0.018 |
anymore | +0.018 |
Neg logit contributions | |
Here | -0.019 |
First | -0.018 |
Many | -0.018 |
Watch | -0.017 |
Everyone | -0.017 |
Token | zoom |
Token ID | 19792 |
Feature activation | -7.48e+00 |
Pos logit contributions | |
ier | +0.128 |
anymore | +0.103 |
ge | +0.102 |
than | +0.100 |
iness | +0.092 |
Neg logit contributions | |
Here | -0.104 |
First | -0.102 |
The | -0.101 |
Many | -0.101 |
Everyone | -0.096 |
Token | a |
Token ID | 257 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
ier | +0.066 |
again | +0.058 |
on | +0.055 |
than | +0.055 |
anymore | +0.054 |
Neg logit contributions | |
Here | -0.093 |
First | -0.086 |
Watch | -0.081 |
Deal | -0.081 |
Many | -0.079 |
Token | big |
Token ID | 1263 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
ier | +0.125 |
ge | +0.105 |
than | +0.102 |
anymore | +0.098 |
again | +0.097 |
Neg logit contributions | |
Here | -0.081 |
Watch | -0.074 |
Many | -0.073 |
First | -0.071 |
Everyone | -0.069 |
Token | tree |
Token ID | 5509 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
ier | +0.149 |
ge | +0.125 |
than | +0.117 |
again | +0.115 |
anymore | +0.115 |
Neg logit contributions | |
Here | -0.104 |
First | -0.096 |
Watch | -0.093 |
Many | -0.093 |
This | -0.089 |
Token | with |
Token ID | 351 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
ier | +0.168 |
iness | +0.112 |
ge | +0.108 |
iest | +0.103 |
anymore | +0.097 |
Neg logit contributions | |
Here | -0.223 |
This | -0.218 |
The | -0.218 |
First | -0.204 |
Every | -0.201 |
Token | many |
Token ID | 867 |
Feature activation | -7.32e+00 |
Pos logit contributions | |
ier | +0.096 |
ge | +0.079 |
again | +0.078 |
than | +0.078 |
anymore | +0.077 |
Neg logit contributions | |
Here | -0.086 |
First | -0.082 |
Many | -0.078 |
Watch | -0.076 |
Everyone | -0.075 |
Token | nuts |
Token ID | 14380 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ier | +0.176 |
ge | +0.151 |
y | +0.138 |
anymore | +0.138 |
again | +0.138 |
Neg logit contributions | |
Many | -0.094 |
Here | -0.093 |
First | -0.088 |
Everyone | -0.082 |
Watch | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ier | +0.180 |
bul | +0.145 |
sooner | +0.142 |
iness | +0.132 |
ge | +0.129 |
Neg logit contributions | |
Here | -0.224 |
This | -0.222 |
Fin | -0.218 |
The | -0.213 |
ossible | -0.213 |
Token | They |
Token ID | 1119 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Majesty | +0.017 |
majesty | +0.015 |
Here | +0.015 |
disl | +0.015 |
cient | +0.015 |
Neg logit contributions | |
again | -0.026 |
anymore | -0.025 |
ier | -0.024 |
on | -0.024 |
than | -0.024 |
Token | want |
Token ID | 765 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
ier | +0.043 |
than | +0.040 |
again | +0.038 |
ge | +0.038 |
y | +0.037 |
Neg logit contributions | |
Here | -0.060 |
First | -0.053 |
Watch | -0.052 |
Many | -0.051 |
Everyone | -0.051 |
Token | to |
Token ID | 284 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
ier | +0.090 |
ge | +0.066 |
iness | +0.066 |
than | +0.063 |
y | +0.059 |
Neg logit contributions | |
Here | -0.106 |
First | -0.106 |
Many | -0.104 |
The | -0.101 |
This | -0.099 |
Token | eat |
Token ID | 4483 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
ge | +0.044 |
again | +0.044 |
ever | +0.044 |
anymore | +0.044 |
than | +0.043 |
Neg logit contributions | |
Here | -0.069 |
Deal | -0.062 |
Acc | -0.061 |
Now | -0.061 |
First | -0.061 |
Token | to |
Token ID | 284 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
ier | +0.115 |
iness | +0.096 |
iest | +0.095 |
le | +0.089 |
ge | +0.080 |
Neg logit contributions | |
The | -0.082 |
This | -0.077 |
Here | -0.076 |
Remy | -0.076 |
Fin | -0.076 |
Token | take |
Token ID | 1011 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
ier | +0.053 |
ge | +0.049 |
again | +0.047 |
than | +0.045 |
anymore | +0.045 |
Neg logit contributions | |
Here | -0.061 |
First | -0.056 |
Many | -0.053 |
Everyone | -0.052 |
Watch | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
ier | +0.112 |
again | +0.092 |
than | +0.092 |
ge | +0.092 |
anymore | +0.092 |
Neg logit contributions | |
Here | -0.095 |
First | -0.090 |
Many | -0.085 |
Watch | -0.083 |
Everyone | -0.081 |
Token | knight |
Token ID | 22062 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
ier | +0.078 |
ge | +0.066 |
y | +0.065 |
than | +0.060 |
anymore | +0.059 |
Neg logit contributions | |
Here | -0.077 |
Watch | -0.071 |
First | -0.067 |
Many | -0.067 |
Majesty | -0.063 |
Token | 's |
Token ID | 338 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
ier | +0.187 |
than | +0.118 |
iness | +0.118 |
m | +0.115 |
iest | +0.115 |
Neg logit contributions | |
This | -0.231 |
First | -0.221 |
The | -0.217 |
Here | -0.217 |
Harry | -0.214 |
Token | sword |
Token ID | 8429 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
ier | +0.111 |
y | +0.087 |
ge | +0.086 |
m | +0.081 |
anymore | +0.081 |
Neg logit contributions | |
Here | -0.098 |
Watch | -0.088 |
First | -0.086 |
Majesty | -0.083 |
Many | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ier | +0.183 |
iest | +0.136 |
m | +0.132 |
bul | +0.121 |
inches | +0.119 |
Neg logit contributions | |
First | -0.234 |
This | -0.233 |
The | -0.222 |
Jerry | -0.222 |
Harry | -0.221 |
Token | But |
Token ID | 887 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
Majesty | +0.020 |
Deal | +0.019 |
Here | +0.019 |
majesty | +0.019 |
disl | +0.018 |
Neg logit contributions | |
again | -0.037 |
. | -0.034 |
ier | -0.033 |
and | -0.033 |
anymore | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
ier | +0.083 |
ge | +0.073 |
than | +0.070 |
y | +0.069 |
anymore | +0.068 |
Neg logit contributions | |
Here | -0.050 |
First | -0.047 |
The | -0.045 |
Many | -0.044 |
Everyone | -0.043 |
Token | knight |
Token ID | 22062 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
ier | +0.052 |
ge | +0.046 |
than | +0.043 |
y | +0.043 |
anymore | +0.042 |
Neg logit contributions | |
Here | -0.045 |
Watch | -0.043 |
First | -0.043 |
Many | -0.043 |
Everyone | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
ier | +0.164 |
ge | +0.138 |
than | +0.137 |
anymore | +0.131 |
sooner | +0.122 |
Neg logit contributions | |
Here | -0.106 |
The | -0.102 |
Many | -0.100 |
Fin | -0.099 |
First | -0.099 |
Token | couldn |
Token ID | 3521 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ier | +0.055 |
anymore | +0.045 |
than | +0.044 |
ge | +0.043 |
again | +0.041 |
Neg logit contributions | |
First | -0.047 |
Here | -0.046 |
Many | -0.044 |
Watch | -0.044 |
Everyone | -0.043 |
Token | 't |
Token ID | 470 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Here | +0.013 |
Majesty | +0.012 |
disl | +0.012 |
First | +0.012 |
majesty | +0.012 |
Neg logit contributions | |
ier | -0.015 |
again | -0.014 |
anymore | -0.013 |
on | -0.013 |
ever | -0.013 |
Token | find |
Token ID | 1064 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
ier | +0.077 |
than | +0.065 |
ge | +0.064 |
y | +0.064 |
again | +0.062 |
Neg logit contributions | |
First | -0.036 |
Many | -0.036 |
Here | -0.035 |
Everyone | -0.034 |
The | -0.033 |
Token | any |
Token ID | 597 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
ier | +0.127 |
ge | +0.114 |
y | +0.103 |
than | +0.102 |
m | +0.100 |
Neg logit contributions | |
First | -0.095 |
Here | -0.094 |
Many | -0.092 |
Everyone | -0.090 |
The | -0.089 |
Token | new |
Token ID | 649 |
Feature activation | -6.78e+00 |
Pos logit contributions | |
ier | +0.139 |
ge | +0.125 |
y | +0.122 |
m | +0.115 |
ably | +0.111 |
Neg logit contributions | |
Many | -0.092 |
Everyone | -0.088 |
First | -0.087 |
Watch | -0.087 |
Here | -0.080 |
Token | planets |
Token ID | 14705 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
ier | +0.149 |
ge | +0.123 |
m | +0.121 |
less | +0.117 |
y | +0.114 |
Neg logit contributions | |
First | -0.094 |
Watch | -0.088 |
Everyone | -0.088 |
Many | -0.087 |
Here | -0.084 |
Token | around |
Token ID | 1088 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
ier | +0.196 |
ge | +0.181 |
ud | +0.163 |
amount | +0.161 |
m | +0.146 |
Neg logit contributions | |
I | -0.198 |
This | -0.187 |
The | -0.187 |
It | -0.182 |
Fred | -0.179 |
Token | her |
Token ID | 607 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
ier | +0.147 |
ge | +0.124 |
than | +0.113 |
m | +0.109 |
less | +0.109 |
Neg logit contributions | |
The | -0.066 |
Everyone | -0.061 |
It | -0.058 |
This | -0.058 |
Many | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ier | +0.077 |
ge | +0.060 |
y | +0.049 |
iness | +0.048 |
m | +0.047 |
Neg logit contributions | |
The | -0.104 |
Here | -0.102 |
Everyone | -0.100 |
Majesty | -0.100 |
This | -0.098 |
Token | But |
Token ID | 887 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Here | +0.020 |
disl | +0.020 |
ossible | +0.019 |
Deal | +0.018 |
Fin | +0.018 |
Neg logit contributions | |
ier | -0.037 |
again | -0.036 |
anymore | -0.035 |
than | -0.034 |
y | -0.032 |
Token | then |
Token ID | 788 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ier | +0.054 |
ge | +0.043 |
than | +0.041 |
anymore | +0.039 |
y | +0.039 |
Neg logit contributions | |
First | -0.040 |
Here | -0.039 |
The | -0.036 |
Many | -0.036 |
Everyone | -0.034 |
Token | help |
Token ID | 1037 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
Here | +0.098 |
First | +0.088 |
Many | +0.085 |
Watch | +0.082 |
Everyone | +0.080 |
Neg logit contributions | |
ier | -0.112 |
again | -0.097 |
ge | -0.097 |
than | -0.095 |
anymore | -0.094 |
Token | me |
Token ID | 502 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
Here | +0.029 |
First | +0.027 |
Many | +0.025 |
Watch | +0.024 |
Everyone | +0.023 |
Neg logit contributions | |
ier | -0.063 |
again | -0.055 |
than | -0.055 |
ge | -0.055 |
anymore | -0.055 |
Token | pay |
Token ID | 1414 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Here | +0.019 |
First | +0.019 |
Watch | +0.017 |
Many | +0.017 |
Everyone | +0.017 |
Neg logit contributions | |
ier | -0.017 |
than | -0.013 |
ge | -0.013 |
anymore | -0.013 |
y | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
Here | +0.025 |
First | +0.024 |
Watch | +0.022 |
Everyone | +0.022 |
Many | +0.022 |
Neg logit contributions | |
ier | -0.021 |
ge | -0.017 |
anymore | -0.016 |
than | -0.016 |
again | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Here | +0.067 |
First | +0.064 |
Many | +0.060 |
Watch | +0.059 |
Everyone | +0.057 |
Neg logit contributions | |
ier | -0.078 |
again | -0.065 |
than | -0.065 |
ge | -0.065 |
anymore | -0.064 |
Token | ." |
Token ID | 526 |
Feature activation | +9.74e+00 |
Pos logit contributions | |
ier | +0.014 |
ge | +0.012 |
than | +0.010 |
y | +0.010 |
bul | +0.009 |
Neg logit contributions | |
First | -0.022 |
Here | -0.021 |
This | -0.020 |
The | -0.020 |
Everyone | -0.019 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
Here | +0.124 |
First | +0.121 |
Majesty | +0.119 |
Watch | +0.117 |
majesty | +0.111 |
Neg logit contributions | |
again | -0.197 |
. | -0.180 |
anymore | -0.177 |
ier | -0.175 |
than | -0.171 |
Token | was |
Token ID | 373 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
Here | +0.086 |
First | +0.082 |
Many | +0.079 |
Watch | +0.077 |
Everyone | +0.076 |
Neg logit contributions | |
ier | -0.062 |
again | -0.050 |
ge | -0.048 |
than | -0.048 |
anymore | -0.047 |
Token | very |
Token ID | 845 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
Here | +0.111 |
First | +0.106 |
Watch | +0.100 |
Many | +0.100 |
Everyone | +0.096 |
Neg logit contributions | |
ier | -0.074 |
again | -0.059 |
than | -0.057 |
anymore | -0.057 |
ge | -0.055 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Here | +0.160 |
First | +0.156 |
Many | +0.145 |
Watch | +0.145 |
Everyone | +0.140 |
Neg logit contributions | |
ier | -0.115 |
than | -0.091 |
again | -0.090 |
ge | -0.086 |
anymore | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
The | +0.033 |
Here | +0.032 |
This | +0.032 |
Ben | +0.031 |
Dad | +0.030 |
Neg logit contributions | |
ier | -0.031 |
ge | -0.023 |
iest | -0.022 |
le | -0.020 |
visible | -0.020 |
Token | bring |
Token ID | 2222 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
ier | +0.065 |
ge | +0.053 |
anymore | +0.052 |
than | +0.052 |
again | +0.051 |
Neg logit contributions | |
Here | -0.062 |
First | -0.060 |
Many | -0.056 |
Watch | -0.055 |
Everyone | -0.054 |
Token | trouble |
Token ID | 5876 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Here | +0.108 |
First | +0.102 |
Many | +0.097 |
Watch | +0.095 |
Everyone | +0.091 |
Neg logit contributions | |
ier | -0.128 |
again | -0.107 |
than | -0.106 |
anymore | -0.105 |
ge | -0.104 |
Token | , |
Token ID | 11 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
Here | +0.058 |
First | +0.055 |
Everyone | +0.054 |
Watch | +0.053 |
disl | +0.053 |
Neg logit contributions | |
ier | -0.029 |
ge | -0.021 |
y | -0.019 |
anymore | -0.018 |
than | -0.017 |
Token | he |
Token ID | 339 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
Here | +0.144 |
First | +0.138 |
Watch | +0.132 |
Many | +0.132 |
Everyone | +0.129 |
Neg logit contributions | |
ier | -0.108 |
ge | -0.083 |
anymore | -0.079 |
than | -0.078 |
again | -0.077 |
Token | refused |
Token ID | 6520 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
Here | +0.085 |
First | +0.081 |
Many | +0.076 |
Watch | +0.076 |
Everyone | +0.075 |
Neg logit contributions | |
ier | -0.074 |
ge | -0.059 |
than | -0.058 |
anymore | -0.058 |
again | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
Here | +0.132 |
First | +0.127 |
Everyone | +0.123 |
This | +0.121 |
The | +0.121 |
Neg logit contributions | |
ier | -0.096 |
ge | -0.074 |
y | -0.068 |
than | -0.067 |
anymore | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
Here | +0.122 |
First | +0.121 |
disl | +0.118 |
rac | +0.114 |
Majesty | +0.113 |
Neg logit contributions | |
again | -0.224 |
ier | -0.211 |
anymore | -0.209 |
than | -0.202 |
. | -0.198 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
cient | +0.184 |
Sorry | +0.183 |
Here | +0.182 |
Majesty | +0.182 |
First | +0.178 |
Neg logit contributions | |
again | -0.162 |
. | -0.149 |
ier | -0.146 |
ge | -0.144 |
on | -0.141 |
Token | John |
Token ID | 7554 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
Here | +0.172 |
First | +0.166 |
cient | +0.162 |
Majesty | +0.160 |
sed | +0.158 |
Neg logit contributions | |
ier | -0.164 |
ge | -0.157 |
again | -0.155 |
than | -0.152 |
ever | -0.141 |
Token | looked |
Token ID | 3114 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
Here | +0.069 |
First | +0.067 |
Many | +0.063 |
Everyone | +0.063 |
Watch | +0.062 |
Neg logit contributions | |
ier | -0.067 |
than | -0.054 |
anymore | -0.054 |
ge | -0.053 |
again | -0.049 |
Token | around |
Token ID | 1088 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
Here | +0.091 |
First | +0.089 |
The | +0.085 |
Watch | +0.084 |
Everyone | +0.083 |
Neg logit contributions | |
ier | -0.066 |
ge | -0.055 |
than | -0.048 |
anymore | -0.045 |
y | -0.044 |
Token | belt |
Token ID | 10999 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Here | +0.072 |
First | +0.068 |
Watch | +0.065 |
Everyone | +0.064 |
This | +0.063 |
Neg logit contributions | |
ier | -0.072 |
ge | -0.059 |
anymore | -0.054 |
than | -0.053 |
again | -0.052 |
Token | for |
Token ID | 329 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
Here | +0.003 |
First | +0.003 |
Everyone | +0.003 |
This | +0.003 |
Watch | +0.003 |
Neg logit contributions | |
ier | -0.002 |
ge | -0.002 |
than | -0.002 |
anymore | -0.002 |
again | -0.002 |
Token | when |
Token ID | 618 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
Here | +0.085 |
First | +0.080 |
Many | +0.074 |
Watch | +0.073 |
Everyone | +0.069 |
Neg logit contributions | |
ier | -0.120 |
again | -0.103 |
than | -0.102 |
ge | -0.101 |
anymore | -0.101 |
Token | I |
Token ID | 314 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
Here | +0.077 |
First | +0.071 |
Many | +0.066 |
Watch | +0.064 |
Everyone | +0.062 |
Neg logit contributions | |
ier | -0.133 |
again | -0.114 |
than | -0.114 |
ge | -0.113 |
anymore | -0.113 |
Token | chew |
Token ID | 34722 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Here | +0.105 |
First | +0.100 |
Many | +0.094 |
Watch | +0.093 |
Everyone | +0.091 |
Neg logit contributions | |
ier | -0.124 |
than | -0.102 |
ge | -0.102 |
anymore | -0.101 |
again | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +9.54e+00 |
Pos logit contributions | |
Here | +0.022 |
First | +0.021 |
Watch | +0.020 |
Everyone | +0.020 |
This | +0.020 |
Neg logit contributions | |
ier | -0.017 |
ge | -0.014 |
than | -0.013 |
anymore | -0.013 |
again | -0.012 |
Token | I |
Token ID | 314 |
Feature activation | +7.34e+00 |
Pos logit contributions | |
Majesty | +0.110 |
lder | +0.109 |
disl | +0.107 |
cient | +0.103 |
ossible | +0.101 |
Neg logit contributions | |
than | -0.167 |
again | -0.164 |
too | -0.162 |
on | -0.161 |
ier | -0.159 |
Token | have |
Token ID | 423 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
Here | +0.121 |
First | +0.115 |
Many | +0.108 |
Watch | +0.106 |
Everyone | +0.103 |
Neg logit contributions | |
ier | -0.151 |
ge | -0.123 |
than | -0.123 |
anymore | -0.122 |
again | -0.121 |
Token | bad |
Token ID | 2089 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
Here | +0.078 |
First | +0.075 |
Many | +0.071 |
Watch | +0.070 |
Everyone | +0.068 |
Neg logit contributions | |
ier | -0.076 |
ge | -0.061 |
than | -0.061 |
again | -0.061 |
anymore | -0.060 |
Token | teeth |
Token ID | 9941 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Here | +0.059 |
First | +0.057 |
Watch | +0.053 |
Many | +0.053 |
Everyone | +0.052 |
Neg logit contributions | |
ier | -0.058 |
ge | -0.049 |
anymore | -0.047 |
again | -0.047 |
than | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
ier | +0.027 |
ge | +0.024 |
beneath | +0.021 |
anymore | +0.020 |
bul | +0.020 |
Neg logit contributions | |
Here | -0.032 |
First | -0.030 |
This | -0.029 |
Everyone | -0.029 |
The | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +9.33e+00 |
Pos logit contributions | |
First | +0.147 |
Here | +0.145 |
Many | +0.137 |
The | +0.137 |
Everyone | +0.137 |
Neg logit contributions | |
ier | -0.127 |
ge | -0.094 |
than | -0.090 |
anymore | -0.088 |
iest | -0.083 |
Token | set |
Token ID | 900 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
Here | +0.159 |
First | +0.146 |
Many | +0.140 |
Watch | +0.136 |
Everyone | +0.132 |
Neg logit contributions | |
ier | -0.183 |
again | -0.159 |
anymore | -0.156 |
ge | -0.155 |
than | -0.155 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
First | +0.072 |
Here | +0.072 |
Everyone | +0.068 |
Watch | +0.066 |
The | +0.065 |
Neg logit contributions | |
ier | -0.057 |
ge | -0.044 |
than | -0.043 |
anymore | -0.042 |
y | -0.041 |
Token | |
Token ID | 220 |
Feature activation | +9.90e+00 |
Pos logit contributions | |
Here | +0.112 |
Majesty | +0.109 |
disl | +0.105 |
majesty | +0.104 |
rac | +0.103 |
Neg logit contributions | |
again | -0.226 |
ier | -0.217 |
anymore | -0.213 |
than | -0.209 |
. | -0.206 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
Here | +0.156 |
Majesty | +0.155 |
Watch | +0.153 |
disl | +0.150 |
lder | +0.148 |
Neg logit contributions | |
ier | -0.180 |
again | -0.168 |
. | -0.160 |
anymore | -0.160 |
y | -0.154 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
Majesty | +0.177 |
Here | +0.175 |
majesty | +0.169 |
Sorry | +0.165 |
cient | +0.164 |
Neg logit contributions | |
again | -0.174 |
ier | -0.166 |
ge | -0.165 |
y | -0.158 |
. | -0.157 |
Token | When |
Token ID | 2215 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
Here | +0.169 |
Majesty | +0.158 |
First | +0.154 |
majesty | +0.152 |
cient | +0.151 |
Neg logit contributions | |
ier | -0.166 |
ge | -0.162 |
again | -0.157 |
than | -0.155 |
y | -0.150 |
Token | it |
Token ID | 340 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Here | +0.113 |
First | +0.110 |
Many | +0.099 |
Everyone | +0.099 |
Watch | +0.098 |
Neg logit contributions | |
ier | -0.166 |
ge | -0.140 |
than | -0.139 |
anymore | -0.135 |
again | -0.133 |
Token | was |
Token ID | 373 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
First | +0.050 |
Everyone | +0.048 |
Many | +0.047 |
Here | +0.047 |
The | +0.046 |
Neg logit contributions | |
ier | -0.057 |
than | -0.053 |
ge | -0.048 |
anymore | -0.047 |
sooner | -0.041 |
Token | time |
Token ID | 640 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Here | +0.147 |
First | +0.145 |
Many | +0.136 |
Watch | +0.134 |
Everyone | +0.133 |
Neg logit contributions | |
ier | -0.094 |
ge | -0.074 |
than | -0.072 |
anymore | -0.069 |
again | -0.069 |
Token | to |
Token ID | 284 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
First | +0.046 |
Here | +0.045 |
This | +0.044 |
The | +0.042 |
ossible | +0.042 |
Neg logit contributions | |
ier | -0.038 |
than | -0.031 |
ge | -0.031 |
anymore | -0.029 |
bul | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
First | +0.079 |
Here | +0.079 |
Many | +0.077 |
Everyone | +0.075 |
The | +0.074 |
Neg logit contributions | |
ier | -0.142 |
ge | -0.114 |
than | -0.111 |
anymore | -0.110 |
again | -0.108 |
Token | bush |
Token ID | 24484 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Here | +0.053 |
Watch | +0.050 |
Many | +0.050 |
Everyone | +0.048 |
First | +0.047 |
Neg logit contributions | |
ier | -0.078 |
ge | -0.064 |
than | -0.062 |
anymore | -0.058 |
iness | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +9.71e+00 |
Pos logit contributions | |
ier | +0.005 |
ge | +0.004 |
than | +0.003 |
iest | +0.003 |
iness | +0.003 |
Neg logit contributions | |
This | -0.008 |
Here | -0.008 |
The | -0.008 |
First | -0.008 |
Everyone | -0.008 |
Token | |
Token ID | 220 |
Feature activation | +9.04e+00 |
Pos logit contributions | |
disl | +0.119 |
rac | +0.118 |
Majesty | +0.113 |
lder | +0.111 |
cient | +0.108 |
Neg logit contributions | |
again | -0.189 |
anymore | -0.173 |
. | -0.170 |
before | -0.166 |
ier | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Majesty | +0.150 |
Here | +0.150 |
disl | +0.147 |
Watch | +0.145 |
lder | +0.145 |
Neg logit contributions | |
ier | -0.150 |
again | -0.146 |
anymore | -0.141 |
. | -0.137 |
on | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | +9.69e+00 |
Pos logit contributions | |
Majesty | +0.176 |
cient | +0.169 |
Here | +0.169 |
majesty | +0.165 |
Sorry | +0.165 |
Neg logit contributions | |
again | -0.156 |
. | -0.139 |
ge | -0.139 |
ier | -0.136 |
y | -0.135 |
Token | When |
Token ID | 2215 |
Feature activation | +6.88e+00 |
Pos logit contributions | |
Here | +0.162 |
Majesty | +0.157 |
First | +0.156 |
cient | +0.154 |
majesty | +0.150 |
Neg logit contributions | |
again | -0.142 |
ier | -0.140 |
ge | -0.138 |
than | -0.137 |
y | -0.132 |
Token | Sally |
Token ID | 25737 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
Here | +0.109 |
First | +0.104 |
Many | +0.096 |
Watch | +0.095 |
Everyone | +0.094 |
Neg logit contributions | |
ier | -0.148 |
ge | -0.124 |
than | -0.123 |
anymore | -0.120 |
again | -0.119 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
Here | +0.058 |
First | +0.056 |
The | +0.053 |
Many | +0.053 |
Watch | +0.051 |
Neg logit contributions | |
ier | -0.067 |
than | -0.057 |
anymore | -0.053 |
ge | -0.052 |
iness | -0.048 |
Token | inside |
Token ID | 2641 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Here | +0.067 |
First | +0.066 |
Watch | +0.061 |
The | +0.061 |
Many | +0.061 |
Neg logit contributions | |
ier | -0.049 |
ge | -0.041 |
than | -0.039 |
iness | -0.033 |
anymore | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
Here | +0.035 |
First | +0.033 |
The | +0.032 |
Everyone | +0.031 |
This | +0.030 |
Neg logit contributions | |
ier | -0.047 |
ge | -0.038 |
than | -0.038 |
anymore | -0.036 |
y | -0.034 |
Token | When |
Token ID | 1649 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
disl | +0.091 |
Here | +0.084 |
Many | +0.079 |
Watch | +0.078 |
Fin | +0.077 |
Neg logit contributions | |
ier | -0.153 |
again | -0.153 |
anymore | -0.137 |
. | -0.136 |
than | -0.136 |
Token | she |
Token ID | 673 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Here | +0.068 |
First | +0.067 |
Everyone | +0.063 |
The | +0.061 |
Many | +0.061 |
Neg logit contributions | |
ier | -0.084 |
ge | -0.071 |
than | -0.070 |
anymore | -0.066 |
y | -0.065 |
Token | opened |
Token ID | 4721 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
Here | +0.026 |
The | +0.026 |
First | +0.025 |
Watch | +0.024 |
Many | +0.024 |
Neg logit contributions | |
ier | -0.045 |
than | -0.040 |
ge | -0.037 |
anymore | -0.036 |
iness | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Here | +0.006 |
First | +0.006 |
Many | +0.005 |
Everyone | +0.005 |
The | +0.005 |
Neg logit contributions | |
ier | -0.008 |
ge | -0.007 |
than | -0.007 |
anymore | -0.006 |
again | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
ier | +0.033 |
ge | +0.028 |
than | +0.027 |
iness | +0.025 |
anymore | +0.023 |
Neg logit contributions | |
First | -0.033 |
Here | -0.032 |
This | -0.031 |
The | -0.031 |
Everyone | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
Here | +0.079 |
First | +0.075 |
Many | +0.070 |
Watch | +0.070 |
Everyone | +0.069 |
Neg logit contributions | |
ier | -0.078 |
ge | -0.063 |
than | -0.063 |
anymore | -0.063 |
again | -0.061 |
Token | jelly |
Token ID | 27644 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
Here | +0.053 |
Watch | +0.049 |
First | +0.048 |
Everyone | +0.046 |
Many | +0.046 |
Neg logit contributions | |
ier | -0.072 |
ge | -0.064 |
anymore | -0.059 |
than | -0.058 |
y | -0.055 |
Token | came |
Token ID | 1625 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
ier | +0.064 |
ge | +0.061 |
anymore | +0.056 |
than | +0.054 |
sooner | +0.050 |
Neg logit contributions | |
Here | -0.061 |
Watch | -0.058 |
First | -0.056 |
Everyone | -0.055 |
Remy | -0.053 |
Token | out |
Token ID | 503 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
ier | +0.015 |
ge | +0.012 |
than | +0.012 |
anymore | +0.012 |
iness | +0.011 |
Neg logit contributions | |
Here | -0.018 |
The | -0.018 |
First | -0.018 |
Watch | -0.017 |
This | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
ier | +0.015 |
iness | +0.012 |
ge | +0.012 |
conflicts | +0.011 |
anymore | +0.011 |
Neg logit contributions | |
The | -0.018 |
Every | -0.015 |
This | -0.015 |
It | -0.015 |
Watch | -0.014 |
Token | perfect |
Token ID | 2818 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
The | +0.033 |
First | +0.030 |
Every | +0.029 |
| +0.029 |
This | +0.028 |
Neg logit contributions | |
ier | -0.050 |
ge | -0.038 |
iness | -0.038 |
owing | -0.036 |
anymore | -0.035 |
Token | threw |
Token ID | 9617 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
Here | +0.009 |
First | +0.009 |
Many | +0.008 |
Watch | +0.008 |
Everyone | +0.008 |
Neg logit contributions | |
ier | -0.010 |
ge | -0.008 |
anymore | -0.008 |
than | -0.008 |
again | -0.008 |
Token | them |
Token ID | 606 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
ier | +0.083 |
ge | +0.072 |
than | +0.067 |
iness | +0.063 |
anymore | +0.062 |
Neg logit contributions | |
First | -0.047 |
Here | -0.045 |
Many | -0.043 |
Everyone | -0.042 |
The | -0.042 |
Token | on |
Token ID | 319 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ier | +0.088 |
iest | +0.068 |
ge | +0.065 |
iness | +0.063 |
cest | +0.061 |
Neg logit contributions | |
First | -0.086 |
The | -0.084 |
This | -0.081 |
ossible | -0.079 |
Here | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ier | +0.039 |
iness | +0.031 |
ge | +0.031 |
than | +0.030 |
iest | +0.030 |
Neg logit contributions | |
The | -0.015 |
First | -0.015 |
Everyone | -0.013 |
Many | -0.013 |
Here | -0.013 |
Token | floor |
Token ID | 4314 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
Here | +0.012 |
First | +0.012 |
Watch | +0.011 |
Everyone | +0.011 |
The | +0.011 |
Neg logit contributions | |
ier | -0.025 |
ge | -0.022 |
y | -0.021 |
than | -0.020 |
anymore | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
ier | +0.099 |
ge | +0.083 |
iest | +0.078 |
le | +0.077 |
bul | +0.076 |
Neg logit contributions | |
The | -0.110 |
First | -0.103 |
This | -0.102 |
Ben | -0.097 |
Everyone | -0.095 |
Token | He |
Token ID | 679 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Here | +0.060 |
rac | +0.055 |
lder | +0.054 |
ossible | +0.054 |
disl | +0.052 |
Neg logit contributions | |
ier | -0.088 |
again | -0.082 |
anymore | -0.081 |
than | -0.076 |
on | -0.074 |
Token | took |
Token ID | 1718 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ier | +0.006 |
anymore | +0.005 |
ge | +0.005 |
than | +0.004 |
again | +0.004 |
Neg logit contributions | |
Here | -0.005 |
First | -0.005 |
Many | -0.005 |
Watch | -0.004 |
Everyone | -0.004 |
Token | out |
Token ID | 503 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
ier | +0.023 |
ge | +0.019 |
than | +0.019 |
anymore | +0.018 |
again | +0.017 |
Neg logit contributions | |
Here | -0.023 |
First | -0.023 |
Many | -0.021 |
Everyone | -0.021 |
Watch | -0.021 |
Token | his |
Token ID | 465 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ier | +0.056 |
ge | +0.048 |
than | +0.048 |
anymore | +0.046 |
iness | +0.043 |
Neg logit contributions | |
Many | -0.026 |
First | -0.026 |
The | -0.026 |
Everyone | -0.024 |
Here | -0.024 |
Token | toys |
Token ID | 14958 |
Feature activation | -8.82e+00 |
Pos logit contributions | |
ier | +0.024 |
ge | +0.019 |
again | +0.018 |
y | +0.018 |
anymore | +0.018 |
Neg logit contributions | |
Here | -0.017 |
First | -0.016 |
ossible | -0.015 |
Many | -0.015 |
The | -0.015 |
Token | set |
Token ID | 900 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
First | +0.034 |
Here | +0.033 |
Many | +0.030 |
Everyone | +0.030 |
Watch | +0.029 |
Neg logit contributions | |
ier | -0.039 |
anymore | -0.032 |
than | -0.032 |
ge | -0.031 |
again | -0.031 |
Token | off |
Token ID | 572 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
Here | +0.003 |
First | +0.003 |
Many | +0.003 |
Watch | +0.003 |
Everyone | +0.003 |
Neg logit contributions | |
ier | -0.002 |
than | -0.001 |
ge | -0.001 |
again | -0.001 |
anymore | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
ier | +0.007 |
iness | +0.006 |
than | +0.005 |
iest | +0.005 |
ge | +0.005 |
Neg logit contributions | |
The | -0.009 |
This | -0.009 |
First | -0.009 |
Everyone | -0.008 |
| -0.008 |
Token | |
Token ID | 220 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
disl | +0.111 |
lder | +0.109 |
Majesty | +0.107 |
rac | +0.100 |
majesty | +0.100 |
Neg logit contributions | |
again | -0.134 |
on | -0.127 |
anymore | -0.124 |
. | -0.121 |
before | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | +7.45e+00 |
Pos logit contributions | |
disl | +0.112 |
Majesty | +0.112 |
Watch | +0.110 |
Here | +0.109 |
lder | +0.106 |
Neg logit contributions | |
ier | -0.110 |
again | -0.102 |
. | -0.100 |
on | -0.097 |
anymore | -0.095 |
Token |
|
Token ID | 198 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
Majesty | +0.141 |
Here | +0.136 |
disl | +0.135 |
majesty | +0.130 |
cient | +0.127 |
Neg logit contributions | |
again | -0.111 |
ier | -0.109 |
on | -0.105 |
ge | -0.103 |
m | -0.101 |
Token | When |
Token ID | 2215 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
Here | +0.137 |
Majesty | +0.126 |
First | +0.123 |
majesty | +0.121 |
disl | +0.120 |
Neg logit contributions | |
ier | -0.111 |
ge | -0.100 |
again | -0.098 |
than | -0.097 |
y | -0.093 |
Token | they |
Token ID | 484 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
First | +0.056 |
Here | +0.055 |
Everyone | +0.050 |
The | +0.049 |
Many | +0.048 |
Neg logit contributions | |
ier | -0.083 |
ge | -0.070 |
than | -0.069 |
y | -0.064 |
anymore | -0.064 |
Token | arrived |
Token ID | 5284 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
First | +0.038 |
Here | +0.037 |
Many | +0.035 |
Everyone | +0.034 |
The | +0.033 |
Neg logit contributions | |
ier | -0.043 |
than | -0.037 |
ge | -0.035 |
anymore | -0.034 |
again | -0.034 |
Token | at |
Token ID | 379 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
Here | +0.014 |
First | +0.014 |
Everyone | +0.013 |
The | +0.013 |
Many | +0.013 |
Neg logit contributions | |
ier | -0.009 |
ge | -0.007 |
than | -0.007 |
anymore | -0.006 |
again | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
Here | +0.055 |
First | +0.052 |
Many | +0.049 |
Watch | +0.048 |
Everyone | +0.047 |
Neg logit contributions | |
ier | -0.067 |
again | -0.056 |
than | -0.055 |
ge | -0.055 |
anymore | -0.055 |
Token | it |
Token ID | 340 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
First | +0.013 |
Everyone | +0.013 |
Here | +0.013 |
The | +0.012 |
This | +0.012 |
Neg logit contributions | |
ier | -0.021 |
ge | -0.018 |
y | -0.017 |
iness | -0.017 |
than | -0.016 |
Token | home |
Token ID | 1363 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ier | +0.039 |
m | +0.028 |
iness | +0.027 |
y | +0.026 |
bul | +0.026 |
Neg logit contributions | |
First | -0.038 |
This | -0.035 |
Pip | -0.033 |
Harry | -0.033 |
Sammy | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +9.49e+00 |
Pos logit contributions | |
ier | +0.027 |
iness | +0.020 |
anymore | +0.018 |
bul | +0.018 |
ge | +0.018 |
Neg logit contributions | |
First | -0.034 |
The | -0.034 |
This | -0.033 |
Here | -0.032 |
Everyone | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +8.84e+00 |
Pos logit contributions | |
disl | +0.145 |
rac | +0.138 |
lder | +0.136 |
Majesty | +0.134 |
majesty | +0.133 |
Neg logit contributions | |
again | -0.164 |
anymore | -0.146 |
. | -0.145 |
than | -0.136 |
before | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | +8.71e+00 |
Pos logit contributions | |
Here | +0.157 |
Majesty | +0.155 |
Sorry | +0.151 |
disl | +0.151 |
First | +0.146 |
Neg logit contributions | |
again | -0.140 |
ier | -0.130 |
ge | -0.128 |
on | -0.125 |
. | -0.124 |
Token | Anna |
Token ID | 31160 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Here | +0.154 |
First | +0.140 |
Majesty | +0.137 |
majesty | +0.133 |
disl | +0.133 |
Neg logit contributions | |
ier | -0.142 |
ge | -0.134 |
again | -0.132 |
than | -0.128 |
y | -0.123 |
Token | 's |
Token ID | 338 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
Here | +0.041 |
First | +0.039 |
Many | +0.037 |
Watch | +0.037 |
Everyone | +0.036 |
Neg logit contributions | |
ier | -0.038 |
anymore | -0.030 |
ge | -0.030 |
than | -0.030 |
again | -0.029 |
Token | mummy |
Token ID | 38567 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Here | +0.049 |
First | +0.046 |
Many | +0.042 |
Watch | +0.042 |
Everyone | +0.040 |
Neg logit contributions | |
ier | -0.085 |
again | -0.074 |
than | -0.073 |
anymore | -0.073 |
ge | -0.073 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ier | +0.025 |
than | +0.020 |
anymore | +0.020 |
ge | +0.020 |
again | +0.018 |
Neg logit contributions | |
Here | -0.024 |
First | -0.024 |
Many | -0.022 |
Everyone | -0.022 |
The | -0.022 |
Token | what |
Token ID | 644 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
Here | +0.046 |
First | +0.043 |
Many | +0.041 |
Everyone | +0.039 |
Watch | +0.039 |
Neg logit contributions | |
ier | -0.060 |
ge | -0.050 |
than | -0.050 |
anymore | -0.048 |
again | -0.047 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Here | +0.061 |
Everyone | +0.058 |
First | +0.058 |
Many | +0.058 |
The | +0.056 |
Neg logit contributions | |
ier | -0.074 |
ge | -0.065 |
than | -0.058 |
again | -0.056 |
anymore | -0.056 |
Token | without |
Token ID | 1231 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
Here | +0.035 |
First | +0.034 |
Everyone | +0.033 |
Many | +0.032 |
The | +0.032 |
Neg logit contributions | |
ier | -0.021 |
ge | -0.015 |
than | -0.014 |
anymore | -0.013 |
again | -0.012 |
Token | permission |
Token ID | 7170 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Here | +0.090 |
First | +0.086 |
Many | +0.081 |
Watch | +0.080 |
Everyone | +0.080 |
Neg logit contributions | |
ier | -0.089 |
ge | -0.070 |
anymore | -0.070 |
than | -0.070 |
again | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
Here | +0.024 |
First | +0.024 |
Everyone | +0.022 |
This | +0.022 |
Many | +0.022 |
Neg logit contributions | |
ier | -0.012 |
ge | -0.009 |
than | -0.008 |
anymore | -0.008 |
again | -0.008 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
Here | +0.120 |
Majesty | +0.119 |
lder | +0.118 |
rac | +0.116 |
majesty | +0.114 |
Neg logit contributions | |
again | -0.199 |
anymore | -0.197 |
ier | -0.196 |
than | -0.190 |
ge | -0.183 |
Token | Once |
Token ID | 7454 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
Here | +0.075 |
First | +0.071 |
Many | +0.065 |
Watch | +0.065 |
disl | +0.061 |
Neg logit contributions | |
ier | -0.109 |
again | -0.096 |
anymore | -0.094 |
than | -0.092 |
ge | -0.091 |
Token | upon |
Token ID | 2402 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
Here | +0.148 |
First | +0.142 |
Watch | +0.138 |
Many | +0.136 |
Everyone | +0.130 |
Neg logit contributions | |
ier | -0.078 |
again | -0.061 |
anymore | -0.060 |
ge | -0.058 |
y | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
Here | +0.134 |
First | +0.128 |
Watch | +0.118 |
Many | +0.115 |
Everyone | +0.114 |
Neg logit contributions | |
ier | -0.119 |
again | -0.102 |
than | -0.099 |
anymore | -0.098 |
ge | -0.095 |
Token | time |
Token ID | 640 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
Here | +0.148 |
First | +0.142 |
Watch | +0.135 |
Many | +0.135 |
Everyone | +0.134 |
Neg logit contributions | |
ier | -0.060 |
than | -0.044 |
again | -0.044 |
anymore | -0.044 |
ge | -0.041 |
Token | there |
Token ID | 612 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
Here | +0.103 |
First | +0.099 |
Watch | +0.095 |
Many | +0.094 |
Everyone | +0.092 |
Neg logit contributions | |
ier | -0.041 |
again | -0.032 |
anymore | -0.032 |
than | -0.030 |
ge | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
Here | +0.084 |
First | +0.081 |
Many | +0.077 |
Watch | +0.076 |
Everyone | +0.075 |
Neg logit contributions | |
ier | -0.050 |
again | -0.038 |
than | -0.038 |
ge | -0.038 |
anymore | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
Here | +0.091 |
First | +0.085 |
Watch | +0.084 |
disl | +0.081 |
Majesty | +0.081 |
Neg logit contributions | |
ier | -0.064 |
on | -0.056 |
than | -0.055 |
again | -0.053 |
anymore | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
ier | +0.105 |
ge | +0.088 |
than | +0.080 |
iest | +0.079 |
sooner | +0.077 |
Neg logit contributions | |
The | -0.133 |
This | -0.131 |
It | -0.131 |
Everyone | -0.130 |
Many | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
disl | +0.079 |
Majesty | +0.077 |
Here | +0.077 |
Amen | +0.073 |
majesty | +0.073 |
Neg logit contributions | |
again | -0.085 |
. | -0.082 |
anymore | -0.082 |
ier | -0.080 |
on | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
Majesty | +0.113 |
Here | +0.106 |
majesty | +0.103 |
disl | +0.102 |
cient | +0.102 |
Neg logit contributions | |
again | -0.078 |
. | -0.078 |
on | -0.071 |
ier | -0.070 |
ge | -0.070 |
Token | " |
Token ID | 1 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
Here | +0.094 |
First | +0.084 |
Majesty | +0.084 |
Many | +0.080 |
disl | +0.080 |
Neg logit contributions | |
ier | -0.091 |
ge | -0.083 |
than | -0.082 |
y | -0.077 |
on | -0.077 |
Token | Mom |
Token ID | 29252 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Here | +0.054 |
First | +0.049 |
Many | +0.046 |
Everyone | +0.044 |
Watch | +0.044 |
Neg logit contributions | |
ier | -0.081 |
again | -0.072 |
than | -0.070 |
ge | -0.070 |
y | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
ier | +0.037 |
ge | +0.028 |
than | +0.028 |
again | +0.028 |
anymore | +0.028 |
Neg logit contributions | |
Here | -0.060 |
First | -0.057 |
Many | -0.055 |
Watch | -0.054 |
Everyone | -0.053 |
Token | why |
Token ID | 1521 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
ier | +0.002 |
again | +0.002 |
anymore | +0.001 |
than | +0.001 |
on | +0.001 |
Neg logit contributions | |
Here | -0.002 |
First | -0.002 |
Many | -0.002 |
Everyone | -0.002 |
Watch | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
ier | +0.002 |
ge | +0.001 |
again | +0.001 |
than | +0.001 |
anymore | +0.001 |
Neg logit contributions | |
Here | -0.001 |
First | -0.001 |
Many | -0.001 |
Watch | -0.001 |
Everyone | -0.001 |
Token | we |
Token ID | 356 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Here | +0.012 |
First | +0.011 |
Many | +0.011 |
Watch | +0.011 |
Everyone | +0.010 |
Neg logit contributions | |
ier | -0.013 |
anymore | -0.011 |
on | -0.011 |
again | -0.011 |
than | -0.010 |
Token | not |
Token ID | 407 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
ier | +0.033 |
than | +0.028 |
ge | +0.027 |
again | +0.026 |
anymore | +0.025 |
Neg logit contributions | |
Here | -0.036 |
First | -0.035 |
Many | -0.034 |
Watch | -0.033 |
ossible | -0.033 |
Token | moving |
Token ID | 3867 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
ier | +0.016 |
anymore | +0.013 |
le | +0.012 |
again | +0.012 |
ge | +0.012 |
Neg logit contributions | |
Here | -0.015 |
Watch | -0.015 |
The | -0.014 |
This | -0.014 |
Many | -0.014 |
Token | let |
Token ID | 1309 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Here | +0.047 |
First | +0.045 |
Many | +0.042 |
Watch | +0.040 |
Everyone | +0.039 |
Neg logit contributions | |
ier | -0.068 |
again | -0.058 |
than | -0.058 |
anymore | -0.057 |
ge | -0.057 |
Token | 's |
Token ID | 338 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
Here | +0.052 |
disl | +0.049 |
Many | +0.049 |
Higher | +0.047 |
First | +0.047 |
Neg logit contributions | |
again | -0.021 |
ier | -0.018 |
- | -0.018 |
on | -0.018 |
away | -0.017 |
Token | go |
Token ID | 467 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Here | +0.069 |
Many | +0.063 |
First | +0.062 |
Watch | +0.059 |
disl | +0.058 |
Neg logit contributions | |
ier | -0.067 |
again | -0.062 |
on | -0.059 |
anymore | -0.059 |
ge | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
ier | +0.020 |
than | +0.015 |
anymore | +0.015 |
ge | +0.015 |
again | +0.015 |
Neg logit contributions | |
Here | -0.029 |
First | -0.028 |
Many | -0.026 |
Watch | -0.026 |
Everyone | -0.026 |
Token | show |
Token ID | 905 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Here | +0.081 |
Many | +0.077 |
First | +0.075 |
Watch | +0.070 |
Everyone | +0.070 |
Neg logit contributions | |
ier | -0.088 |
again | -0.088 |
on | -0.080 |
ge | -0.079 |
anymore | -0.078 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Here | +0.029 |
Many | +0.027 |
First | +0.026 |
disl | +0.025 |
Watch | +0.025 |
Neg logit contributions | |
ier | -0.030 |
again | -0.029 |
anymore | -0.026 |
on | -0.026 |
than | -0.025 |
Token | my |
Token ID | 616 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ier | +0.036 |
ge | +0.030 |
anymore | +0.028 |
than | +0.027 |
again | +0.027 |
Neg logit contributions | |
Here | -0.032 |
First | -0.029 |
Everyone | -0.028 |
This | -0.027 |
Watch | -0.027 |
Token | new |
Token ID | 649 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
Here | +0.035 |
First | +0.033 |
Many | +0.032 |
Everyone | +0.031 |
Watch | +0.031 |
Neg logit contributions | |
ier | -0.038 |
ge | -0.031 |
than | -0.029 |
y | -0.028 |
again | -0.028 |
Token | skirt |
Token ID | 23967 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
Here | +0.001 |
First | +0.001 |
Watch | +0.000 |
Many | +0.000 |
Everyone | +0.000 |
Neg logit contributions | |
ier | -0.001 |
ge | -0.000 |
anymore | -0.000 |
than | -0.000 |
again | -0.000 |
Token | !" |
Token ID | 2474 |
Feature activation | +7.42e+00 |
Pos logit contributions | |
ier | +0.092 |
ge | +0.085 |
anymore | +0.075 |
than | +0.073 |
again | +0.073 |
Neg logit contributions | |
Here | -0.083 |
First | -0.078 |
Everyone | -0.073 |
Watch | -0.073 |
This | -0.072 |
Token | So |
Token ID | 1406 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
Here | +0.069 |
First | +0.059 |
Many | +0.054 |
Watch | +0.053 |
Majesty | +0.050 |
Neg logit contributions | |
ier | -0.193 |
again | -0.180 |
anymore | -0.176 |
than | -0.175 |
y | -0.169 |
Token | were |
Token ID | 547 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ier | +0.021 |
ge | +0.018 |
anymore | +0.017 |
than | +0.017 |
again | +0.016 |
Neg logit contributions | |
Here | -0.014 |
First | -0.014 |
Many | -0.014 |
The | -0.014 |
Everyone | -0.013 |
Token | friends |
Token ID | 2460 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
ier | +0.031 |
ge | +0.027 |
anymore | +0.026 |
again | +0.025 |
than | +0.025 |
Neg logit contributions | |
Here | -0.028 |
First | -0.027 |
Many | -0.025 |
Watch | -0.025 |
Everyone | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
ge | +0.093 |
ier | +0.091 |
bul | +0.076 |
iful | +0.074 |
ruck | +0.073 |
Neg logit contributions | |
The | -0.104 |
I | -0.091 |
Everyone | -0.091 |
It | -0.090 |
Leave | -0.088 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Majesty | +0.053 |
Here | +0.050 |
cient | +0.050 |
First | +0.049 |
lder | +0.048 |
Neg logit contributions | |
than | -0.063 |
anymore | -0.061 |
again | -0.059 |
ier | -0.059 |
. | -0.057 |
Token | Tim |
Token ID | 14967 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
ier | +0.037 |
again | +0.032 |
than | +0.032 |
ge | +0.032 |
anymore | +0.031 |
Neg logit contributions | |
Here | -0.022 |
First | -0.021 |
Many | -0.019 |
Watch | -0.019 |
Everyone | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
ier | +0.036 |
ge | +0.026 |
anymore | +0.024 |
than | +0.024 |
again | +0.023 |
Neg logit contributions | |
Here | -0.067 |
First | -0.065 |
Many | -0.062 |
The | -0.061 |
Everyone | -0.061 |
Token | Jen |
Token ID | 13364 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Majesty | +0.022 |
Deal | +0.021 |
Here | +0.020 |
First | +0.020 |
majesty | +0.020 |
Neg logit contributions | |
on | -0.012 |
ever | -0.011 |
in | -0.011 |
than | -0.010 |
from | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ier | +0.038 |
ge | +0.030 |
than | +0.029 |
anymore | +0.029 |
again | +0.029 |
Neg logit contributions | |
Here | -0.038 |
First | -0.036 |
Many | -0.035 |
Everyone | -0.034 |
The | -0.033 |
Token | twins |
Token ID | 20345 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
ier | +0.029 |
again | +0.023 |
on | +0.023 |
anymore | +0.022 |
than | +0.022 |
Neg logit contributions | |
Here | -0.049 |
First | -0.047 |
Watch | -0.046 |
disl | -0.045 |
Many | -0.045 |
Token | who |
Token ID | 508 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ier | +0.074 |
ge | +0.053 |
iness | +0.049 |
iest | +0.048 |
than | +0.042 |
Neg logit contributions | |
The | -0.123 |
Here | -0.120 |
Everyone | -0.115 |
Many | -0.113 |
This | -0.112 |
Token | liked |
Token ID | 8288 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
ier | +0.044 |
ge | +0.037 |
again | +0.036 |
anymore | +0.035 |
than | +0.034 |
Neg logit contributions | |
Here | -0.033 |
First | -0.031 |
Many | -0.031 |
Everyone | -0.030 |
The | -0.030 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
cient | +0.093 |
lder | +0.088 |
rac | +0.088 |
Majesty | +0.083 |
heit | +0.083 |
Neg logit contributions | |
than | -0.081 |
. | -0.071 |
again | -0.070 |
ier | -0.068 |
anymore | -0.065 |
Token | Tom |
Token ID | 13787 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
ier | +0.002 |
again | +0.001 |
than | +0.001 |
anymore | +0.001 |
ge | +0.001 |
Neg logit contributions | |
Here | -0.001 |
First | -0.001 |
Many | -0.001 |
Watch | -0.001 |
Everyone | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ier | +0.014 |
ge | +0.011 |
anymore | +0.010 |
than | +0.010 |
again | +0.010 |
Neg logit contributions | |
Here | -0.018 |
First | -0.017 |
Many | -0.016 |
Watch | -0.016 |
Everyone | -0.015 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
Majesty | +0.052 |
Deal | +0.050 |
Here | +0.049 |
First | +0.048 |
majesty | +0.047 |
Neg logit contributions | |
on | -0.031 |
ever | -0.028 |
in | -0.028 |
from | -0.026 |
than | -0.026 |
Token | were |
Token ID | 547 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
ier | +0.011 |
than | +0.009 |
again | +0.009 |
ge | +0.009 |
anymore | +0.009 |
Neg logit contributions | |
Here | -0.011 |
First | -0.011 |
Many | -0.010 |
Watch | -0.010 |
Everyone | -0.010 |
Token | playing |
Token ID | 2712 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
ier | +0.011 |
again | +0.009 |
on | +0.009 |
anymore | +0.009 |
than | +0.008 |
Neg logit contributions | |
Here | -0.018 |
First | -0.018 |
Watch | -0.017 |
Many | -0.017 |
disl | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
ier | +0.042 |
ge | +0.028 |
than | +0.026 |
anymore | +0.025 |
again | +0.024 |
Neg logit contributions | |
Here | -0.111 |
First | -0.108 |
Many | -0.103 |
Watch | -0.103 |
Everyone | -0.101 |
Token | the |
Token ID | 262 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
again | +0.000 |
ier | +0.000 |
than | +0.000 |
ge | +0.000 |
on | +0.000 |
Neg logit contributions | |
Here | -0.000 |
First | -0.000 |
Watch | -0.000 |
Majesty | -0.000 |
Many | -0.000 |
Token | park |
Token ID | 3952 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
Here | +0.034 |
Many | +0.032 |
First | +0.031 |
Deal | +0.030 |
Watch | +0.030 |
Neg logit contributions | |
again | -0.022 |
on | -0.021 |
ier | -0.021 |
y | -0.020 |
inside | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
ier | +0.082 |
ge | +0.059 |
iness | +0.055 |
bul | +0.049 |
iest | +0.048 |
Neg logit contributions | |
First | -0.105 |
Here | -0.104 |
The | -0.104 |
This | -0.100 |
Everyone | -0.099 |
Token | They |
Token ID | 1119 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Here | +0.048 |
Majesty | +0.046 |
cient | +0.045 |
rac | +0.043 |
Watch | +0.043 |
Neg logit contributions | |
anymore | -0.076 |
ier | -0.074 |
again | -0.074 |
than | -0.073 |
on | -0.069 |
Token | Mama |
Token ID | 40084 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Here | +0.112 |
disl | +0.103 |
Majesty | +0.100 |
lder | +0.098 |
majesty | +0.096 |
Neg logit contributions | |
again | -0.191 |
ier | -0.185 |
anymore | -0.178 |
than | -0.174 |
. | -0.169 |
Token | was |
Token ID | 373 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
Here | +0.021 |
First | +0.020 |
Everyone | +0.019 |
Many | +0.019 |
The | +0.019 |
Neg logit contributions | |
ier | -0.016 |
than | -0.013 |
ge | -0.013 |
anymore | -0.013 |
again | -0.011 |
Token | so |
Token ID | 523 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
Here | +0.080 |
First | +0.077 |
Many | +0.075 |
Everyone | +0.074 |
Watch | +0.074 |
Neg logit contributions | |
ier | -0.073 |
ge | -0.060 |
than | -0.058 |
anymore | -0.057 |
again | -0.056 |
Token | proud |
Token ID | 6613 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Here | +0.114 |
First | +0.107 |
Many | +0.103 |
Watch | +0.100 |
Everyone | +0.099 |
Neg logit contributions | |
ier | -0.127 |
ge | -0.105 |
anymore | -0.104 |
again | -0.104 |
than | -0.104 |
Token | of |
Token ID | 286 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
Everyone | +0.057 |
The | +0.054 |
Here | +0.053 |
First | +0.053 |
Dad | +0.053 |
Neg logit contributions | |
ier | -0.051 |
ge | -0.046 |
anywhere | -0.038 |
anymore | -0.036 |
sooner | -0.036 |
Token | them |
Token ID | 606 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
Here | +0.092 |
First | +0.087 |
Many | +0.081 |
Watch | +0.079 |
Everyone | +0.077 |
Neg logit contributions | |
ier | -0.124 |
again | -0.104 |
than | -0.104 |
ge | -0.104 |
anymore | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | +9.14e+00 |
Pos logit contributions | |
ier | +0.002 |
ge | +0.001 |
bul | +0.001 |
iest | +0.001 |
web | +0.001 |
Neg logit contributions | |
The | -0.002 |
Everyone | -0.002 |
This | -0.002 |
First | -0.002 |
Here | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
Here | +0.125 |
disl | +0.121 |
Ta | +0.120 |
Watch | +0.117 |
rac | +0.117 |
Neg logit contributions | |
again | -0.154 |
. | -0.147 |
ier | -0.146 |
than | -0.141 |
and | -0.140 |
Token | said |
Token ID | 531 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
Here | +0.074 |
First | +0.070 |
Many | +0.066 |
Watch | +0.065 |
Everyone | +0.064 |
Neg logit contributions | |
ier | -0.077 |
than | -0.062 |
again | -0.062 |
ge | -0.062 |
anymore | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
Here | +0.093 |
First | +0.090 |
Many | +0.084 |
Watch | +0.084 |
Everyone | +0.080 |
Neg logit contributions | |
ier | -0.065 |
again | -0.052 |
anymore | -0.049 |
than | -0.048 |
ge | -0.046 |
Token | " |
Token ID | 366 |
Feature activation | +7.32e+00 |
Pos logit contributions | |
Here | +0.061 |
First | +0.058 |
Many | +0.053 |
Watch | +0.051 |
Everyone | +0.047 |
Neg logit contributions | |
ier | -0.111 |
again | -0.100 |
than | -0.097 |
ge | -0.095 |
anymore | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ier | +0.164 |
iest | +0.114 |
ge | +0.113 |
m | +0.108 |
inches | +0.098 |
Neg logit contributions | |
First | -0.209 |
ossible | -0.207 |
The | -0.206 |
This | -0.203 |
Here | -0.200 |
Token | The |
Token ID | 383 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
disl | +0.023 |
Here | +0.023 |
Deal | +0.023 |
ossible | +0.022 |
rac | +0.022 |
Neg logit contributions | |
again | -0.057 |
ier | -0.053 |
anymore | -0.053 |
than | -0.051 |
before | -0.051 |
Token | bunny |
Token ID | 44915 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
Here | +0.000 |
First | +0.000 |
Many | +0.000 |
Watch | +0.000 |
Everyone | +0.000 |
Neg logit contributions | |
ier | -0.000 |
ge | -0.000 |
than | -0.000 |
anymore | -0.000 |
again | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
ier | +0.098 |
ge | +0.079 |
than | +0.077 |
anymore | +0.077 |
again | +0.071 |
Neg logit contributions | |
Here | -0.096 |
First | -0.093 |
Many | -0.090 |
Everyone | -0.088 |
Watch | -0.088 |
Token | very |
Token ID | 845 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
ier | +0.054 |
ge | +0.044 |
than | +0.042 |
anymore | +0.041 |
y | +0.040 |
Neg logit contributions | |
Here | -0.059 |
Many | -0.057 |
First | -0.057 |
The | -0.055 |
Watch | -0.054 |
Token | sad |
Token ID | 6507 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
ier | +0.011 |
than | +0.008 |
ge | +0.008 |
again | +0.008 |
anymore | +0.008 |
Neg logit contributions | |
Here | -0.013 |
First | -0.012 |
Many | -0.012 |
Watch | -0.011 |
Everyone | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
ier | +0.119 |
ge | +0.110 |
iest | +0.103 |
lling | +0.101 |
pr | +0.100 |
Neg logit contributions | |
The | -0.101 |
Remy | -0.091 |
It | -0.091 |
Fin | -0.090 |
Ben | -0.089 |
Token | scared |
Token ID | 12008 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
ier | +0.016 |
again | +0.013 |
than | +0.013 |
ge | +0.013 |
anymore | +0.013 |
Neg logit contributions | |
Here | -0.019 |
First | -0.019 |
Many | -0.018 |
Watch | -0.017 |
Everyone | -0.017 |
Token | again |
Token ID | 757 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
ier | +0.088 |
ge | +0.086 |
iest | +0.063 |
bul | +0.063 |
iness | +0.061 |
Neg logit contributions | |
The | -0.117 |
Everyone | -0.110 |
Fin | -0.107 |
It | -0.105 |
Remy | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
ier | +0.090 |
iest | +0.063 |
iness | +0.059 |
ge | +0.055 |
bul | +0.052 |
Neg logit contributions | |
The | -0.120 |
Remy | -0.111 |
Fin | -0.110 |
This | -0.110 |
Everyone | -0.106 |
Token | The |
Token ID | 383 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
disl | +0.036 |
Here | +0.035 |
Deal | +0.033 |
First | +0.033 |
rac | +0.033 |
Neg logit contributions | |
again | -0.063 |
anymore | -0.059 |
than | -0.057 |
. | -0.056 |
before | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
Majesty | +0.069 |
Here | +0.063 |
majesty | +0.062 |
disl | +0.061 |
cient | +0.060 |
Neg logit contributions | |
again | -0.050 |
. | -0.047 |
on | -0.045 |
and | -0.044 |
inside | -0.041 |
Token | " |
Token ID | 1 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
Here | +0.058 |
Majesty | +0.057 |
Fin | +0.057 |
First | +0.057 |
Dod | +0.054 |
Neg logit contributions | |
again | -0.045 |
y | -0.043 |
ier | -0.043 |
than | -0.042 |
- | -0.041 |
Token | I |
Token ID | 40 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
Majesty | +0.016 |
Here | +0.016 |
First | +0.016 |
majesty | +0.015 |
Remy | +0.014 |
Neg logit contributions | |
ier | -0.016 |
than | -0.014 |
on | -0.013 |
m | -0.013 |
y | -0.013 |
Token | 'm |
Token ID | 1101 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ier | +0.008 |
anymore | +0.006 |
again | +0.006 |
ge | +0.006 |
than | +0.006 |
Neg logit contributions | |
Here | -0.005 |
First | -0.005 |
Many | -0.005 |
Watch | -0.005 |
This | -0.005 |
Token | decor |
Token ID | 11705 |
Feature activation | -5.64e+00 |
Pos logit contributions | |
ier | +0.043 |
than | +0.034 |
again | +0.034 |
ge | +0.034 |
anymore | +0.034 |
Neg logit contributions | |
Here | -0.051 |
First | -0.049 |
Many | -0.047 |
Watch | -0.046 |
Everyone | -0.045 |
Token | ating |
Token ID | 803 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
ier | +0.109 |
again | +0.090 |
than | +0.088 |
anymore | +0.086 |
ge | +0.085 |
Neg logit contributions | |
Here | -0.103 |
First | -0.098 |
Many | -0.094 |
Watch | -0.091 |
Everyone | -0.087 |
Token | my |
Token ID | 616 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
ier | +0.140 |
ge | +0.118 |
anymore | +0.113 |
than | +0.113 |
again | +0.111 |
Neg logit contributions | |
Here | -0.103 |
First | -0.098 |
Many | -0.089 |
Watch | -0.089 |
Everyone | -0.089 |
Token | door |
Token ID | 3420 |
Feature activation | -9.50e+00 |
Pos logit contributions | |
ier | +0.078 |
ge | +0.063 |
y | +0.059 |
iness | +0.059 |
anymore | +0.057 |
Neg logit contributions | |
Here | -0.062 |
First | -0.056 |
The | -0.053 |
Watch | -0.053 |
Many | -0.052 |
Token | with |
Token ID | 351 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
ier | +0.180 |
ge | +0.147 |
anymore | +0.142 |
iness | +0.140 |
again | +0.135 |
Neg logit contributions | |
Here | -0.164 |
First | -0.162 |
This | -0.144 |
The | -0.141 |
Watch | -0.141 |
Token | this |
Token ID | 428 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
ier | +0.093 |
ge | +0.078 |
than | +0.076 |
anymore | +0.076 |
again | +0.075 |
Neg logit contributions | |
Here | -0.078 |
First | -0.075 |
Many | -0.070 |
Watch | -0.068 |
Everyone | -0.067 |
Token | pretty |
Token ID | 2495 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
ier | +0.094 |
ge | +0.083 |
anymore | +0.075 |
y | +0.075 |
than | +0.074 |
Neg logit contributions | |
Here | -0.078 |
First | -0.077 |
Everyone | -0.070 |
Watch | -0.069 |
This | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
ier | +0.120 |
ge | +0.092 |
iness | +0.086 |
iest | +0.076 |
anymore | +0.071 |
Neg logit contributions | |
This | -0.149 |
The | -0.148 |
Here | -0.147 |
Everyone | -0.145 |
First | -0.145 |
Token | loved |
Token ID | 6151 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
ier | +0.045 |
ge | +0.037 |
than | +0.036 |
anymore | +0.036 |
again | +0.036 |
Neg logit contributions | |
Here | -0.044 |
First | -0.042 |
Many | -0.040 |
Watch | -0.039 |
Everyone | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
ier | +0.113 |
ge | +0.089 |
than | +0.081 |
iness | +0.080 |
anymore | +0.080 |
Neg logit contributions | |
Here | -0.110 |
First | -0.104 |
Many | -0.103 |
Everyone | -0.101 |
Watch | -0.099 |
Token | learn |
Token ID | 2193 |
Feature activation | -7.98e+00 |
Pos logit contributions | |
ier | +0.059 |
again | +0.052 |
anymore | +0.050 |
than | +0.050 |
ge | +0.049 |
Neg logit contributions | |
Here | -0.048 |
First | -0.044 |
Many | -0.039 |
Watch | -0.039 |
Everyone | -0.037 |
Token | new |
Token ID | 649 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
ier | +0.172 |
ge | +0.152 |
y | +0.134 |
iness | +0.133 |
ever | +0.128 |
Neg logit contributions | |
Everyone | -0.120 |
Here | -0.117 |
Many | -0.112 |
Watch | -0.111 |
First | -0.110 |
Token | things |
Token ID | 1243 |
Feature activation | -8.79e+00 |
Pos logit contributions | |
ier | +0.127 |
ge | +0.106 |
y | +0.089 |
beneath | +0.087 |
anymore | +0.085 |
Neg logit contributions | |
Everyone | -0.130 |
Here | -0.128 |
First | -0.126 |
Many | -0.124 |
Watch | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ier | +0.128 |
ge | +0.125 |
ud | +0.102 |
iness | +0.101 |
ited | +0.096 |
Neg logit contributions | |
This | -0.162 |
Here | -0.154 |
Everyone | -0.151 |
The | -0.147 |
Every | -0.144 |
Token | One |
Token ID | 1881 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
Here | +0.021 |
Majesty | +0.021 |
disl | +0.021 |
rac | +0.021 |
lder | +0.020 |
Neg logit contributions | |
again | -0.040 |
anymore | -0.040 |
ier | -0.037 |
. | -0.036 |
than | -0.035 |
Token | day |
Token ID | 1110 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
ier | +0.084 |
ge | +0.069 |
anymore | +0.063 |
again | +0.059 |
than | +0.057 |
Neg logit contributions | |
Here | -0.083 |
Many | -0.080 |
First | -0.078 |
The | -0.077 |
Watch | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ier | +0.043 |
ge | +0.034 |
than | +0.033 |
again | +0.032 |
anymore | +0.032 |
Neg logit contributions | |
Here | -0.055 |
First | -0.053 |
Many | -0.051 |
Everyone | -0.050 |
Watch | -0.050 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
Here | +0.002 |
First | +0.002 |
Many | +0.002 |
Watch | +0.002 |
Everyone | +0.002 |
Neg logit contributions | |
ier | -0.003 |
ge | -0.002 |
than | -0.002 |
again | -0.002 |
anymore | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
ier | +0.065 |
ge | +0.053 |
bul | +0.047 |
iness | +0.047 |
sooner | +0.044 |
Neg logit contributions | |
This | -0.066 |
Here | -0.065 |
The | -0.064 |
Everyone | -0.064 |
First | -0.063 |
Token | see |
Token ID | 766 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Here | +0.006 |
First | +0.006 |
Many | +0.005 |
Watch | +0.005 |
Everyone | +0.005 |
Neg logit contributions | |
ier | -0.009 |
again | -0.008 |
than | -0.008 |
ge | -0.008 |
anymore | -0.008 |
Token | what |
Token ID | 644 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ier | +0.044 |
ge | +0.036 |
y | +0.036 |
than | +0.035 |
anymore | +0.034 |
Neg logit contributions | |
Here | -0.032 |
First | -0.030 |
Everyone | -0.029 |
Many | -0.029 |
The | -0.028 |
Token | could |
Token ID | 714 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
ier | +0.033 |
ge | +0.029 |
anymore | +0.026 |
than | +0.025 |
y | +0.025 |
Neg logit contributions | |
Here | -0.028 |
Everyone | -0.026 |
First | -0.026 |
The | -0.026 |
Many | -0.026 |
Token | be |
Token ID | 307 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
ier | +0.013 |
ge | +0.010 |
than | +0.010 |
anymore | +0.010 |
again | +0.010 |
Neg logit contributions | |
Here | -0.011 |
First | -0.010 |
Many | -0.010 |
Watch | -0.009 |
Everyone | -0.009 |
Token | hidden |
Token ID | 7104 |
Feature activation | -7.98e+00 |
Pos logit contributions | |
ier | +0.051 |
ge | +0.044 |
iness | +0.042 |
y | +0.039 |
m | +0.039 |
Neg logit contributions | |
Here | -0.059 |
disl | -0.058 |
The | -0.057 |
Watch | -0.056 |
This | -0.056 |
Token | underneath |
Token ID | 14638 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
ier | +0.099 |
m | +0.093 |
ge | +0.084 |
bul | +0.082 |
y | +0.079 |
Neg logit contributions | |
The | -0.131 |
Harry | -0.129 |
This | -0.129 |
Fin | -0.126 |
Here | -0.125 |
Token | it |
Token ID | 340 |
Feature activation | -6.39e+00 |
Pos logit contributions | |
ier | +0.093 |
ge | +0.079 |
m | +0.072 |
y | +0.072 |
than | +0.070 |
Neg logit contributions | |
The | -0.066 |
Everyone | -0.061 |
This | -0.061 |
It | -0.060 |
Here | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
ier | +0.095 |
ge | +0.074 |
iness | +0.062 |
bul | +0.059 |
than | +0.059 |
Neg logit contributions | |
This | -0.132 |
The | -0.131 |
First | -0.130 |
Here | -0.128 |
Everyone | -0.126 |
Token | He |
Token ID | 679 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
disl | +0.055 |
Majesty | +0.054 |
majesty | +0.051 |
Deal | +0.049 |
lder | +0.048 |
Neg logit contributions | |
again | -0.087 |
ier | -0.080 |
. | -0.078 |
anymore | -0.078 |
than | -0.077 |
Token | carefully |
Token ID | 7773 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
ier | +0.027 |
anymore | +0.022 |
ge | +0.021 |
than | +0.021 |
again | +0.020 |
Neg logit contributions | |
Here | -0.025 |
First | -0.024 |
Many | -0.022 |
Watch | -0.022 |
Everyone | -0.022 |
Token | ither |
Token ID | 1555 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
Here | +0.009 |
First | +0.009 |
Many | +0.008 |
Watch | +0.008 |
disl | +0.007 |
Neg logit contributions | |
ier | -0.012 |
anymore | -0.010 |
ge | -0.010 |
than | -0.009 |
again | -0.009 |
Token | y |
Token ID | 88 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
ier | +0.062 |
ge | +0.049 |
anymore | +0.048 |
sooner | +0.047 |
than | +0.047 |
Neg logit contributions | |
Everyone | -0.078 |
Fin | -0.077 |
First | -0.077 |
The | -0.077 |
Here | -0.076 |
Token | gl |
Token ID | 1278 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
ier | +0.074 |
ge | +0.062 |
anymore | +0.055 |
than | +0.052 |
sooner | +0.052 |
Neg logit contributions | |
Here | -0.071 |
First | -0.071 |
Everyone | -0.070 |
Many | -0.069 |
Watch | -0.069 |
Token | ided |
Token ID | 1384 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
ier | +0.051 |
again | +0.044 |
anymore | +0.044 |
than | +0.043 |
ge | +0.042 |
Neg logit contributions | |
Here | -0.057 |
First | -0.054 |
Watch | -0.051 |
Many | -0.051 |
Everyone | -0.050 |
Token | across |
Token ID | 1973 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
ier | +0.050 |
ge | +0.038 |
anymore | +0.036 |
than | +0.034 |
again | +0.032 |
Neg logit contributions | |
First | -0.080 |
Here | -0.079 |
Everyone | -0.075 |
The | -0.075 |
Watch | -0.074 |
Token | them |
Token ID | 606 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
ier | +0.018 |
ge | +0.016 |
than | +0.015 |
anymore | +0.015 |
iness | +0.015 |
Neg logit contributions | |
The | -0.008 |
First | -0.007 |
Here | -0.007 |
Many | -0.007 |
Everyone | -0.007 |
Token | until |
Token ID | 1566 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
ier | +0.087 |
ge | +0.065 |
iest | +0.056 |
iness | +0.056 |
bul | +0.055 |
Neg logit contributions | |
The | -0.121 |
This | -0.117 |
Here | -0.115 |
Everyone | -0.114 |
First | -0.114 |
Token | he |
Token ID | 339 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Here | +0.017 |
First | +0.016 |
Many | +0.015 |
Watch | +0.015 |
Everyone | +0.015 |
Neg logit contributions | |
ier | -0.020 |
ge | -0.016 |
than | -0.016 |
anymore | -0.016 |
again | -0.016 |
Token | reached |
Token ID | 4251 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ier | +0.020 |
ge | +0.016 |
than | +0.016 |
anymore | +0.016 |
again | +0.015 |
Neg logit contributions | |
Here | -0.019 |
First | -0.018 |
Many | -0.017 |
Watch | -0.017 |
Everyone | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
ier | +0.041 |
ge | +0.034 |
than | +0.034 |
anymore | +0.033 |
y | +0.032 |
Neg logit contributions | |
Here | -0.030 |
First | -0.030 |
The | -0.027 |
Watch | -0.026 |
Everyone | -0.026 |
Token | other |
Token ID | 584 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Here | +0.003 |
First | +0.003 |
Everyone | +0.003 |
Watch | +0.003 |
Many | +0.003 |
Neg logit contributions | |
ier | -0.007 |
ge | -0.006 |
than | -0.006 |
anymore | -0.006 |
y | -0.006 |