Token | One |
Token ID | 3198 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
prise | +0.209 |
w | +0.206 |
uch | +0.200 |
e | +0.197 |
o | +0.197 |
Neg logit contributions | |
horizon | -0.073 |
der | -0.071 |
Everyone | -0.071 |
Afterwards | -0.068 |
rily | -0.065 |
Token | day |
Token ID | 1110 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
prise | +0.138 |
w | +0.129 |
asc | +0.126 |
seeker | +0.123 |
uch | +0.122 |
Neg logit contributions | |
Everyone | -0.110 |
horizon | -0.107 |
Afterwards | -0.103 |
Everybody | -0.102 |
After | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
prise | +0.136 |
asc | +0.129 |
seeker | +0.124 |
e | +0.123 |
uch | +0.117 |
Neg logit contributions | |
Everyone | -0.108 |
Then | -0.102 |
After | -0.102 |
Afterwards | -0.100 |
der | -0.100 |
Token | a |
Token ID | 257 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
prise | +0.121 |
uch | +0.111 |
w | +0.110 |
asc | +0.108 |
e | +0.107 |
Neg logit contributions | |
Everyone | -0.090 |
Then | -0.089 |
After | -0.088 |
Afterwards | -0.084 |
der | -0.084 |
Token | little |
Token ID | 1310 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
prise | +0.159 |
w | +0.153 |
asc | +0.148 |
e | +0.148 |
uch | +0.147 |
Neg logit contributions | |
Everyone | -0.080 |
Then | -0.075 |
horizon | -0.075 |
der | -0.073 |
' | -0.071 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
prise | +0.176 |
uch | +0.167 |
asc | +0.163 |
e | +0.163 |
w | +0.157 |
Neg logit contributions | |
Everyone | -0.077 |
horizon | -0.073 |
der | -0.069 |
Then | -0.067 |
rier | -0.066 |
Token | named |
Token ID | 3706 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
prise | +0.183 |
uch | +0.171 |
seeker | +0.169 |
ymes | +0.169 |
a | +0.165 |
Neg logit contributions | |
The | -0.265 |
Everyone | -0.260 |
Then | -0.258 |
But | -0.247 |
After | -0.239 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
prise | +0.106 |
w | +0.104 |
a | +0.102 |
uch | +0.100 |
e | +0.098 |
Neg logit contributions | |
Everyone | -0.074 |
Then | -0.070 |
After | -0.070 |
Afterwards | -0.069 |
Everybody | -0.067 |
Token | found |
Token ID | 1043 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
prise | +0.235 |
render | +0.206 |
uch | +0.206 |
a | +0.203 |
seeker | +0.202 |
Neg logit contributions | |
Then | -0.143 |
The | -0.139 |
Everyone | -0.137 |
After | -0.134 |
He | -0.133 |
Token | a |
Token ID | 257 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
w | +0.097 |
prise | +0.096 |
o | +0.093 |
e | +0.092 |
uch | +0.091 |
Neg logit contributions | |
horizon | -0.129 |
der | -0.124 |
rily | -0.122 |
Afterwards | -0.121 |
int | -0.121 |
Token | box |
Token ID | 3091 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
e | +0.103 |
w | +0.100 |
asc | +0.098 |
prise | +0.096 |
o | +0.093 |
Neg logit contributions | |
horizon | -0.051 |
' | -0.046 |
int | -0.046 |
� | -0.046 |
der | -0.043 |
Token | One |
Token ID | 3198 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
prise | +0.169 |
w | +0.167 |
uch | +0.162 |
e | +0.161 |
o | +0.161 |
Neg logit contributions | |
horizon | -0.064 |
der | -0.063 |
Everyone | -0.061 |
Afterwards | -0.060 |
rily | -0.058 |
Token | day |
Token ID | 1110 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
prise | +0.116 |
w | +0.112 |
asc | +0.107 |
uch | +0.105 |
seeker | +0.103 |
Neg logit contributions | |
Everyone | -0.096 |
horizon | -0.094 |
Afterwards | -0.091 |
Everybody | -0.090 |
After | -0.090 |
Token | , |
Token ID | 11 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
prise | +0.107 |
asc | +0.100 |
e | +0.099 |
w | +0.097 |
seeker | +0.096 |
Neg logit contributions | |
Everyone | -0.102 |
der | -0.100 |
Then | -0.099 |
Afterwards | -0.097 |
After | -0.097 |
Token | a |
Token ID | 257 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
prise | +0.112 |
uch | +0.102 |
w | +0.102 |
asc | +0.100 |
e | +0.098 |
Neg logit contributions | |
Everyone | -0.084 |
Then | -0.084 |
After | -0.082 |
der | -0.079 |
Afterwards | -0.078 |
Token | little |
Token ID | 1310 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
prise | +0.172 |
w | +0.167 |
e | +0.162 |
asc | +0.161 |
uch | +0.160 |
Neg logit contributions | |
Everyone | -0.084 |
horizon | -0.080 |
Then | -0.079 |
der | -0.076 |
' | -0.074 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
prise | +0.178 |
uch | +0.170 |
e | +0.165 |
asc | +0.164 |
w | +0.160 |
Neg logit contributions | |
Everyone | -0.090 |
horizon | -0.085 |
der | -0.079 |
Then | -0.078 |
Everybody | -0.077 |
Token | named |
Token ID | 3706 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
prise | +0.177 |
uch | +0.169 |
a | +0.167 |
ymes | +0.167 |
seeker | +0.165 |
Neg logit contributions | |
The | -0.260 |
Everyone | -0.256 |
Then | -0.254 |
But | -0.241 |
ment | -0.236 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.94e+00 |
Pos logit contributions | |
prise | +0.098 |
w | +0.096 |
a | +0.094 |
uch | +0.092 |
e | +0.091 |
Neg logit contributions | |
Everyone | -0.069 |
Then | -0.066 |
Afterwards | -0.065 |
After | -0.065 |
Everybody | -0.063 |
Token | went |
Token ID | 1816 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
prise | +0.231 |
render | +0.207 |
uch | +0.202 |
a | +0.201 |
ymes | +0.200 |
Neg logit contributions | |
Then | -0.132 |
The | -0.130 |
He | -0.126 |
Everyone | -0.125 |
After | -0.122 |
Token | to |
Token ID | 284 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
prise | +0.141 |
w | +0.140 |
uch | +0.136 |
a | +0.135 |
e | +0.133 |
Neg logit contributions | |
Everyone | -0.093 |
After | -0.091 |
Then | -0.088 |
der | -0.087 |
horizon | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
prise | +0.065 |
w | +0.065 |
uch | +0.062 |
a | +0.061 |
e | +0.060 |
Neg logit contributions | |
horizon | -0.059 |
Everyone | -0.058 |
der | -0.058 |
Afterwards | -0.057 |
Everybody | -0.056 |
Token | One |
Token ID | 3198 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
prise | +0.233 |
w | +0.230 |
uch | +0.223 |
e | +0.222 |
o | +0.221 |
Neg logit contributions | |
horizon | -0.087 |
der | -0.086 |
Everyone | -0.083 |
Afterwards | -0.081 |
rily | -0.079 |
Token | day |
Token ID | 1110 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
prise | +0.156 |
w | +0.146 |
asc | +0.143 |
tresp | +0.137 |
seeker | +0.137 |
Neg logit contributions | |
Everyone | -0.113 |
horizon | -0.105 |
After | -0.103 |
Everybody | -0.102 |
Afterwards | -0.102 |
Token | , |
Token ID | 11 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
prise | +0.162 |
asc | +0.152 |
e | +0.147 |
seeker | +0.146 |
a | +0.141 |
Neg logit contributions | |
Everyone | -0.119 |
Then | -0.115 |
After | -0.114 |
der | -0.112 |
Afterwards | -0.110 |
Token | a |
Token ID | 257 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
prise | +0.125 |
uch | +0.111 |
asc | +0.109 |
tresp | +0.108 |
e | +0.108 |
Neg logit contributions | |
Then | -0.099 |
Everyone | -0.097 |
After | -0.096 |
The | -0.089 |
Afterwards | -0.088 |
Token | little |
Token ID | 1310 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
prise | +0.155 |
w | +0.150 |
e | +0.146 |
uch | +0.144 |
asc | +0.143 |
Neg logit contributions | |
Everyone | -0.088 |
Then | -0.083 |
der | -0.081 |
horizon | -0.079 |
' | -0.079 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.76e+00 |
Pos logit contributions | |
prise | +0.178 |
uch | +0.168 |
asc | +0.164 |
e | +0.163 |
render | +0.159 |
Neg logit contributions | |
Everyone | -0.085 |
horizon | -0.075 |
The | -0.074 |
Then | -0.074 |
ment | -0.073 |
Token | named |
Token ID | 3706 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
prise | +0.186 |
uch | +0.174 |
ymes | +0.174 |
a | +0.171 |
ll | +0.171 |
Neg logit contributions | |
The | -0.252 |
Everyone | -0.242 |
Then | -0.241 |
But | -0.232 |
His | -0.223 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
prise | +0.101 |
w | +0.097 |
a | +0.096 |
uch | +0.095 |
asc | +0.092 |
Neg logit contributions | |
Everyone | -0.068 |
Then | -0.064 |
After | -0.063 |
Afterwards | -0.062 |
Everybody | -0.060 |
Token | went |
Token ID | 1816 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
prise | +0.255 |
render | +0.232 |
ymes | +0.225 |
a | +0.224 |
seeker | +0.223 |
Neg logit contributions | |
The | -0.130 |
Then | -0.123 |
Everyone | -0.118 |
He | -0.116 |
After | -0.110 |
Token | for |
Token ID | 329 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
prise | +0.144 |
w | +0.142 |
uch | +0.139 |
a | +0.137 |
e | +0.135 |
Neg logit contributions | |
Everyone | -0.092 |
After | -0.089 |
Then | -0.087 |
der | -0.085 |
int | -0.084 |
Token | a |
Token ID | 257 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
w | +0.079 |
prise | +0.078 |
uch | +0.076 |
a | +0.075 |
o | +0.073 |
Neg logit contributions | |
Everyone | -0.057 |
Then | -0.056 |
der | -0.055 |
Afterwards | -0.055 |
horizon | -0.055 |
Token | upon |
Token ID | 2402 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
prise | +0.125 |
w | +0.122 |
uch | +0.117 |
e | +0.116 |
o | +0.114 |
Neg logit contributions | |
horizon | -0.149 |
der | -0.148 |
Everyone | -0.146 |
Afterwards | -0.144 |
int | -0.142 |
Token | a |
Token ID | 257 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
prise | +0.156 |
w | +0.152 |
uch | +0.147 |
o | +0.143 |
asc | +0.142 |
Neg logit contributions | |
Everyone | -0.125 |
der | -0.123 |
horizon | -0.121 |
Then | -0.120 |
Afterwards | -0.119 |
Token | time |
Token ID | 640 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
prise | +0.183 |
asc | +0.174 |
w | +0.167 |
seeker | +0.158 |
tresp | +0.157 |
Neg logit contributions | |
int | -0.124 |
Then | -0.122 |
Everyone | -0.121 |
After | -0.121 |
horizon | -0.119 |
Token | , |
Token ID | 11 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
prise | +0.160 |
w | +0.151 |
asc | +0.147 |
uch | +0.142 |
e | +0.141 |
Neg logit contributions | |
Everyone | -0.110 |
Then | -0.106 |
After | -0.101 |
der | -0.100 |
Everybody | -0.099 |
Token | a |
Token ID | 257 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
prise | +0.100 |
w | +0.088 |
uch | +0.087 |
e | +0.085 |
asc | +0.083 |
Neg logit contributions | |
Then | -0.125 |
After | -0.122 |
Everyone | -0.121 |
Afterwards | -0.118 |
der | -0.118 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.74e+00 |
Pos logit contributions | |
prise | +0.146 |
w | +0.140 |
uch | +0.136 |
asc | +0.133 |
e | +0.132 |
Neg logit contributions | |
Everyone | -0.067 |
Then | -0.063 |
horizon | -0.061 |
' | -0.059 |
der | -0.059 |
Token | named |
Token ID | 3706 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
prise | +0.203 |
ymes | +0.187 |
seeker | +0.186 |
render | +0.186 |
ll | +0.183 |
Neg logit contributions | |
The | -0.232 |
Then | -0.215 |
Everyone | -0.211 |
But | -0.207 |
ment | -0.192 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.76e+00 |
Pos logit contributions | |
prise | +0.073 |
w | +0.070 |
a | +0.068 |
uch | +0.067 |
e | +0.066 |
Neg logit contributions | |
Everyone | -0.052 |
Then | -0.049 |
After | -0.049 |
Afterwards | -0.049 |
der | -0.047 |
Token | went |
Token ID | 1816 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
prise | +0.198 |
render | +0.173 |
uch | +0.165 |
seeker | +0.165 |
tresp | +0.163 |
Neg logit contributions | |
The | -0.156 |
Then | -0.154 |
He | -0.147 |
Everyone | -0.144 |
After | -0.144 |
Token | to |
Token ID | 284 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
prise | +0.114 |
w | +0.111 |
uch | +0.109 |
e | +0.106 |
a | +0.106 |
Neg logit contributions | |
Everyone | -0.087 |
After | -0.084 |
der | -0.084 |
Then | -0.083 |
horizon | -0.083 |
Token | visit |
Token ID | 3187 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
prise | +0.066 |
w | +0.065 |
uch | +0.062 |
e | +0.062 |
o | +0.062 |
Neg logit contributions | |
horizon | -0.045 |
der | -0.045 |
Everyone | -0.044 |
Afterwards | -0.043 |
rily | -0.042 |
Token | One |
Token ID | 3198 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
prise | +0.187 |
w | +0.186 |
o | +0.182 |
e | +0.181 |
uch | +0.180 |
Neg logit contributions | |
der | -0.082 |
horizon | -0.082 |
Afterwards | -0.077 |
rily | -0.076 |
Everyone | -0.075 |
Token | day |
Token ID | 1110 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
prise | +0.126 |
w | +0.121 |
asc | +0.115 |
uch | +0.113 |
seeker | +0.112 |
Neg logit contributions | |
Everyone | -0.101 |
horizon | -0.099 |
Afterwards | -0.096 |
After | -0.095 |
Everybody | -0.094 |
Token | , |
Token ID | 11 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
prise | +0.132 |
asc | +0.127 |
seeker | +0.122 |
e | +0.122 |
o | +0.118 |
Neg logit contributions | |
Everyone | -0.104 |
Then | -0.100 |
After | -0.099 |
Afterwards | -0.097 |
ment | -0.097 |
Token | a |
Token ID | 257 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
prise | +0.114 |
uch | +0.106 |
asc | +0.104 |
w | +0.104 |
seeker | +0.100 |
Neg logit contributions | |
Then | -0.077 |
After | -0.076 |
Everyone | -0.076 |
Afterwards | -0.070 |
As | -0.068 |
Token | little |
Token ID | 1310 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
prise | +0.163 |
w | +0.162 |
e | +0.156 |
asc | +0.155 |
uch | +0.155 |
Neg logit contributions | |
Everyone | -0.072 |
horizon | -0.068 |
Then | -0.068 |
der | -0.066 |
' | -0.064 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.70e+00 |
Pos logit contributions | |
prise | +0.182 |
uch | +0.176 |
asc | +0.171 |
e | +0.171 |
w | +0.167 |
Neg logit contributions | |
Everyone | -0.075 |
horizon | -0.072 |
der | -0.067 |
Then | -0.065 |
ment | -0.065 |
Token | named |
Token ID | 3706 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
prise | +0.173 |
uch | +0.168 |
ymes | +0.164 |
a | +0.163 |
seeker | +0.161 |
Neg logit contributions | |
The | -0.255 |
Everyone | -0.250 |
Then | -0.249 |
But | -0.237 |
ment | -0.234 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.86e+00 |
Pos logit contributions | |
prise | +0.082 |
w | +0.080 |
a | +0.078 |
uch | +0.077 |
e | +0.075 |
Neg logit contributions | |
Everyone | -0.060 |
Afterwards | -0.057 |
Then | -0.056 |
After | -0.056 |
Everybody | -0.055 |
Token | went |
Token ID | 1816 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
prise | +0.232 |
uch | +0.207 |
render | +0.207 |
seeker | +0.204 |
a | +0.203 |
Neg logit contributions | |
Then | -0.128 |
The | -0.127 |
Everyone | -0.121 |
He | -0.121 |
After | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
prise | +0.137 |
w | +0.136 |
uch | +0.133 |
a | +0.131 |
e | +0.130 |
Neg logit contributions | |
Everyone | -0.091 |
After | -0.088 |
der | -0.086 |
Then | -0.086 |
horizon | -0.085 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
prise | +0.061 |
w | +0.061 |
uch | +0.058 |
a | +0.057 |
o | +0.057 |
Neg logit contributions | |
horizon | -0.054 |
Everyone | -0.054 |
der | -0.053 |
Afterwards | -0.053 |
Everybody | -0.052 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
rily | +0.033 |
horizon | +0.032 |
rier | +0.031 |
der | +0.030 |
int | +0.029 |
Neg logit contributions | |
o | -0.048 |
w | -0.042 |
prise | -0.042 |
uch | -0.041 |
e | -0.041 |
Token | One |
Token ID | 3198 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
prise | +0.175 |
w | +0.172 |
uch | +0.168 |
a | +0.165 |
e | +0.164 |
Neg logit contributions | |
Everyone | -0.054 |
horizon | -0.053 |
der | -0.052 |
Afterwards | -0.051 |
Then | -0.049 |
Token | day |
Token ID | 1110 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
prise | +0.112 |
w | +0.107 |
asc | +0.103 |
uch | +0.100 |
e | +0.099 |
Neg logit contributions | |
Everyone | -0.090 |
horizon | -0.087 |
Afterwards | -0.085 |
Everybody | -0.084 |
After | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
prise | +0.101 |
asc | +0.096 |
e | +0.095 |
seeker | +0.092 |
uch | +0.091 |
Neg logit contributions | |
Everyone | -0.087 |
Then | -0.085 |
After | -0.082 |
der | -0.082 |
Afterwards | -0.081 |
Token | a |
Token ID | 257 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
prise | +0.104 |
uch | +0.098 |
asc | +0.096 |
w | +0.096 |
seeker | +0.094 |
Neg logit contributions | |
Then | -0.076 |
Everyone | -0.075 |
After | -0.074 |
Afterwards | -0.069 |
Everybody | -0.068 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.70e+00 |
Pos logit contributions | |
w | +0.153 |
prise | +0.151 |
e | +0.148 |
uch | +0.147 |
asc | +0.145 |
Neg logit contributions | |
Everyone | -0.080 |
Then | -0.075 |
horizon | -0.073 |
der | -0.072 |
' | -0.071 |
Token | named |
Token ID | 3706 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
uch | +0.175 |
prise | +0.174 |
a | +0.169 |
seeker | +0.167 |
ymes | +0.165 |
Neg logit contributions | |
The | -0.257 |
Everyone | -0.254 |
Then | -0.252 |
But | -0.243 |
His | -0.238 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
prise | +0.095 |
w | +0.094 |
a | +0.092 |
uch | +0.091 |
asc | +0.088 |
Neg logit contributions | |
Everyone | -0.068 |
Then | -0.064 |
After | -0.063 |
Afterwards | -0.063 |
Everybody | -0.062 |
Token | went |
Token ID | 1816 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
prise | +0.246 |
ymes | +0.224 |
render | +0.222 |
uch | +0.222 |
a | +0.221 |
Neg logit contributions | |
The | -0.125 |
Then | -0.122 |
He | -0.117 |
Everyone | -0.115 |
After | -0.112 |
Token | to |
Token ID | 284 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
prise | +0.141 |
w | +0.140 |
uch | +0.138 |
a | +0.136 |
e | +0.135 |
Neg logit contributions | |
Everyone | -0.084 |
After | -0.083 |
Then | -0.080 |
der | -0.078 |
int | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
prise | +0.061 |
w | +0.060 |
uch | +0.058 |
a | +0.057 |
e | +0.057 |
Neg logit contributions | |
horizon | -0.053 |
der | -0.053 |
Everyone | -0.052 |
Afterwards | -0.052 |
int | -0.050 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
horizon | +0.038 |
rily | +0.037 |
rier | +0.037 |
int | +0.036 |
der | +0.035 |
Neg logit contributions | |
o | -0.052 |
w | -0.045 |
uch | -0.043 |
e | -0.043 |
prise | -0.042 |
Token | One |
Token ID | 3198 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
prise | +0.183 |
w | +0.181 |
uch | +0.176 |
e | +0.174 |
o | +0.174 |
Neg logit contributions | |
horizon | -0.069 |
der | -0.068 |
Everyone | -0.066 |
Afterwards | -0.065 |
rily | -0.062 |
Token | day |
Token ID | 1110 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
prise | +0.117 |
w | +0.111 |
asc | +0.108 |
uch | +0.105 |
seeker | +0.105 |
Neg logit contributions | |
Everyone | -0.091 |
horizon | -0.088 |
Afterwards | -0.087 |
After | -0.087 |
Then | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
prise | +0.114 |
asc | +0.108 |
e | +0.104 |
seeker | +0.104 |
ymes | +0.101 |
Neg logit contributions | |
Everyone | -0.091 |
Then | -0.089 |
After | -0.087 |
Afterwards | -0.085 |
der | -0.084 |
Token | a |
Token ID | 257 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
prise | +0.110 |
uch | +0.100 |
asc | +0.099 |
w | +0.098 |
seeker | +0.097 |
Neg logit contributions | |
Then | -0.079 |
Everyone | -0.078 |
After | -0.077 |
Afterwards | -0.072 |
Everybody | -0.070 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.70e+00 |
Pos logit contributions | |
prise | +0.154 |
w | +0.153 |
e | +0.148 |
uch | +0.147 |
asc | +0.146 |
Neg logit contributions | |
Everyone | -0.079 |
Then | -0.074 |
horizon | -0.072 |
der | -0.071 |
' | -0.071 |
Token | named |
Token ID | 3706 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
prise | +0.174 |
uch | +0.173 |
seeker | +0.168 |
a | +0.165 |
ymes | +0.165 |
Neg logit contributions | |
The | -0.257 |
Everyone | -0.252 |
Then | -0.252 |
But | -0.241 |
After | -0.236 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
prise | +0.097 |
w | +0.095 |
a | +0.093 |
uch | +0.093 |
asc | +0.089 |
Neg logit contributions | |
Everyone | -0.069 |
Then | -0.064 |
After | -0.064 |
Afterwards | -0.064 |
Everybody | -0.062 |
Token | found |
Token ID | 1043 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
prise | +0.241 |
seeker | +0.218 |
render | +0.216 |
ymes | +0.216 |
uch | +0.216 |
Neg logit contributions | |
The | -0.128 |
Then | -0.127 |
Everyone | -0.120 |
He | -0.120 |
After | -0.119 |
Token | a |
Token ID | 257 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
w | +0.094 |
prise | +0.094 |
o | +0.091 |
e | +0.089 |
uch | +0.088 |
Neg logit contributions | |
horizon | -0.121 |
der | -0.118 |
rily | -0.115 |
Afterwards | -0.114 |
int | -0.114 |
Token | microphone |
Token ID | 21822 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
e | +0.104 |
w | +0.100 |
asc | +0.098 |
prise | +0.095 |
o | +0.093 |
Neg logit contributions | |
horizon | -0.048 |
� | -0.044 |
' | -0.043 |
int | -0.042 |
der | -0.041 |
Token | One |
Token ID | 3198 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
prise | +0.175 |
w | +0.173 |
o | +0.169 |
e | +0.168 |
uch | +0.168 |
Neg logit contributions | |
der | -0.073 |
horizon | -0.072 |
Afterwards | -0.068 |
Everyone | -0.067 |
rily | -0.067 |
Token | day |
Token ID | 1110 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
prise | +0.124 |
w | +0.118 |
asc | +0.115 |
seeker | +0.111 |
tresp | +0.110 |
Neg logit contributions | |
Everyone | -0.093 |
horizon | -0.088 |
Afterwards | -0.086 |
Everybody | -0.086 |
After | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
prise | +0.119 |
asc | +0.112 |
e | +0.108 |
seeker | +0.108 |
a | +0.105 |
Neg logit contributions | |
Everyone | -0.099 |
Then | -0.095 |
After | -0.094 |
der | -0.093 |
Afterwards | -0.092 |
Token | a |
Token ID | 257 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
prise | +0.110 |
uch | +0.100 |
asc | +0.099 |
w | +0.097 |
seeker | +0.097 |
Neg logit contributions | |
Then | -0.081 |
Everyone | -0.081 |
After | -0.079 |
Afterwards | -0.074 |
Everybody | -0.073 |
Token | little |
Token ID | 1310 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
prise | +0.149 |
w | +0.147 |
e | +0.142 |
uch | +0.141 |
asc | +0.140 |
Neg logit contributions | |
Everyone | -0.072 |
Then | -0.068 |
horizon | -0.066 |
der | -0.064 |
' | -0.064 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.68e+00 |
Pos logit contributions | |
prise | +0.170 |
uch | +0.163 |
e | +0.157 |
asc | +0.156 |
w | +0.155 |
Neg logit contributions | |
Everyone | -0.078 |
horizon | -0.073 |
der | -0.070 |
Then | -0.068 |
The | -0.067 |
Token | named |
Token ID | 3706 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
prise | +0.182 |
uch | +0.177 |
ymes | +0.176 |
seeker | +0.173 |
a | +0.173 |
Neg logit contributions | |
The | -0.249 |
Everyone | -0.242 |
Then | -0.241 |
But | -0.234 |
His | -0.230 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
prise | +0.106 |
w | +0.103 |
a | +0.102 |
uch | +0.100 |
asc | +0.096 |
Neg logit contributions | |
Everyone | -0.069 |
Then | -0.064 |
After | -0.064 |
Afterwards | -0.063 |
Everybody | -0.061 |
Token | went |
Token ID | 1816 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
prise | +0.254 |
render | +0.230 |
ymes | +0.230 |
a | +0.228 |
seeker | +0.224 |
Neg logit contributions | |
The | -0.123 |
Then | -0.118 |
He | -0.112 |
Everyone | -0.112 |
After | -0.108 |
Token | for |
Token ID | 329 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
prise | +0.142 |
w | +0.141 |
uch | +0.138 |
a | +0.136 |
e | +0.134 |
Neg logit contributions | |
Everyone | -0.090 |
After | -0.088 |
Then | -0.085 |
int | -0.083 |
der | -0.082 |
Token | a |
Token ID | 257 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
w | +0.071 |
prise | +0.070 |
uch | +0.068 |
a | +0.068 |
o | +0.066 |
Neg logit contributions | |
Everyone | -0.056 |
der | -0.055 |
horizon | -0.055 |
Then | -0.055 |
Afterwards | -0.054 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
rily | +0.019 |
rier | +0.019 |
horizon | +0.019 |
int | +0.018 |
der | +0.017 |
Neg logit contributions | |
o | -0.032 |
prise | -0.028 |
w | -0.028 |
asc | -0.028 |
e | -0.027 |
Token | One |
Token ID | 3198 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
prise | +0.208 |
w | +0.206 |
uch | +0.200 |
o | +0.199 |
e | +0.199 |
Neg logit contributions | |
horizon | -0.081 |
der | -0.081 |
Everyone | -0.077 |
Afterwards | -0.076 |
rily | -0.074 |
Token | day |
Token ID | 1110 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
prise | +0.146 |
w | +0.138 |
asc | +0.134 |
tresp | +0.131 |
uch | +0.129 |
Neg logit contributions | |
Everyone | -0.101 |
horizon | -0.094 |
After | -0.094 |
Everybody | -0.092 |
Afterwards | -0.092 |
Token | , |
Token ID | 11 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
prise | +0.160 |
asc | +0.152 |
seeker | +0.148 |
e | +0.144 |
ymes | +0.143 |
Neg logit contributions | |
Everyone | -0.108 |
Then | -0.104 |
After | -0.104 |
der | -0.100 |
ment | -0.099 |
Token | a |
Token ID | 257 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
prise | +0.113 |
uch | +0.104 |
asc | +0.103 |
w | +0.101 |
seeker | +0.101 |
Neg logit contributions | |
Then | -0.077 |
Everyone | -0.076 |
After | -0.075 |
Afterwards | -0.070 |
But | -0.068 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.67e+00 |
Pos logit contributions | |
prise | +0.158 |
w | +0.155 |
e | +0.151 |
uch | +0.149 |
asc | +0.149 |
Neg logit contributions | |
Everyone | -0.075 |
Then | -0.071 |
horizon | -0.068 |
der | -0.068 |
' | -0.066 |
Token | named |
Token ID | 3706 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
prise | +0.182 |
uch | +0.169 |
ll | +0.168 |
seeker | +0.168 |
a | +0.168 |
Neg logit contributions | |
The | -0.249 |
Everyone | -0.244 |
Then | -0.243 |
But | -0.234 |
After | -0.227 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.96e+00 |
Pos logit contributions | |
prise | +0.090 |
w | +0.086 |
a | +0.085 |
uch | +0.083 |
e | +0.081 |
Neg logit contributions | |
Everyone | -0.063 |
Then | -0.059 |
After | -0.058 |
Afterwards | -0.058 |
Everybody | -0.057 |
Token | found |
Token ID | 1043 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
prise | +0.246 |
render | +0.220 |
seeker | +0.215 |
a | +0.215 |
ymes | +0.212 |
Neg logit contributions | |
The | -0.122 |
Then | -0.121 |
Everyone | -0.116 |
After | -0.113 |
He | -0.111 |
Token | a |
Token ID | 257 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
w | +0.098 |
prise | +0.098 |
o | +0.093 |
uch | +0.092 |
e | +0.092 |
Neg logit contributions | |
horizon | -0.117 |
der | -0.114 |
Afterwards | -0.111 |
rily | -0.111 |
int | -0.110 |
Token | toy |
Token ID | 13373 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
e | +0.114 |
w | +0.109 |
asc | +0.106 |
prise | +0.105 |
o | +0.101 |
Neg logit contributions | |
horizon | -0.051 |
' | -0.047 |
� | -0.046 |
int | -0.045 |
" | -0.043 |
Token | One |
Token ID | 3198 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
prise | +0.156 |
w | +0.153 |
uch | +0.149 |
e | +0.147 |
o | +0.147 |
Neg logit contributions | |
horizon | -0.054 |
Everyone | -0.053 |
der | -0.053 |
Afterwards | -0.051 |
Everybody | -0.048 |
Token | day |
Token ID | 1110 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
prise | +0.117 |
w | +0.112 |
asc | +0.108 |
uch | +0.104 |
tresp | +0.104 |
Neg logit contributions | |
Everyone | -0.085 |
horizon | -0.080 |
Afterwards | -0.078 |
Everybody | -0.078 |
After | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
prise | +0.110 |
asc | +0.102 |
e | +0.101 |
seeker | +0.098 |
o | +0.096 |
Neg logit contributions | |
Everyone | -0.093 |
Then | -0.090 |
der | -0.088 |
After | -0.088 |
Afterwards | -0.087 |
Token | a |
Token ID | 257 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
prise | +0.109 |
uch | +0.099 |
w | +0.097 |
asc | +0.096 |
seeker | +0.094 |
Neg logit contributions | |
Then | -0.086 |
Everyone | -0.086 |
After | -0.084 |
Afterwards | -0.079 |
Everybody | -0.078 |
Token | little |
Token ID | 1310 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
prise | +0.153 |
w | +0.148 |
e | +0.143 |
uch | +0.143 |
asc | +0.142 |
Neg logit contributions | |
Everyone | -0.079 |
Then | -0.073 |
horizon | -0.073 |
der | -0.070 |
' | -0.069 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.64e+00 |
Pos logit contributions | |
prise | +0.175 |
uch | +0.167 |
asc | +0.162 |
e | +0.162 |
w | +0.158 |
Neg logit contributions | |
Everyone | -0.088 |
horizon | -0.084 |
Then | -0.076 |
der | -0.076 |
Everybody | -0.075 |
Token | named |
Token ID | 3706 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
prise | +0.179 |
uch | +0.170 |
ymes | +0.169 |
a | +0.167 |
seeker | +0.163 |
Neg logit contributions | |
The | -0.254 |
Then | -0.247 |
Everyone | -0.246 |
But | -0.236 |
His | -0.232 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.98e+00 |
Pos logit contributions | |
prise | +0.100 |
w | +0.097 |
a | +0.097 |
uch | +0.094 |
asc | +0.091 |
Neg logit contributions | |
Everyone | -0.066 |
Then | -0.062 |
After | -0.062 |
Afterwards | -0.061 |
Everybody | -0.059 |
Token | went |
Token ID | 1816 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
prise | +0.245 |
render | +0.220 |
ymes | +0.219 |
a | +0.215 |
uch | +0.215 |
Neg logit contributions | |
The | -0.126 |
Then | -0.124 |
He | -0.118 |
Everyone | -0.115 |
After | -0.111 |
Token | to |
Token ID | 284 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
prise | +0.136 |
w | +0.135 |
uch | +0.132 |
a | +0.130 |
e | +0.129 |
Neg logit contributions | |
Everyone | -0.089 |
After | -0.086 |
Then | -0.084 |
der | -0.083 |
horizon | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
prise | +0.064 |
w | +0.063 |
uch | +0.061 |
a | +0.060 |
o | +0.059 |
Neg logit contributions | |
horizon | -0.053 |
Everyone | -0.053 |
der | -0.052 |
Afterwards | -0.051 |
Everybody | -0.050 |
Token | upon |
Token ID | 2402 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
prise | +0.089 |
w | +0.088 |
o | +0.087 |
a | +0.084 |
uch | +0.082 |
Neg logit contributions | |
horizon | -0.151 |
der | -0.151 |
Afterwards | -0.146 |
rily | -0.146 |
Everyone | -0.145 |
Token | a |
Token ID | 257 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
prise | +0.134 |
w | +0.132 |
uch | +0.127 |
o | +0.124 |
a | +0.123 |
Neg logit contributions | |
der | -0.121 |
Everyone | -0.120 |
horizon | -0.119 |
Afterwards | -0.117 |
Then | -0.115 |
Token | time |
Token ID | 640 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
prise | +0.155 |
asc | +0.150 |
w | +0.149 |
seeker | +0.139 |
uch | +0.138 |
Neg logit contributions | |
int | -0.133 |
After | -0.129 |
der | -0.128 |
Afterwards | -0.128 |
Everyone | -0.127 |
Token | , |
Token ID | 11 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
prise | +0.129 |
w | +0.129 |
asc | +0.124 |
uch | +0.123 |
e | +0.119 |
Neg logit contributions | |
Everyone | -0.108 |
Then | -0.104 |
After | -0.103 |
der | -0.103 |
int | -0.101 |
Token | a |
Token ID | 257 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
prise | +0.086 |
w | +0.082 |
uch | +0.081 |
asc | +0.078 |
e | +0.076 |
Neg logit contributions | |
Then | -0.114 |
After | -0.112 |
Everyone | -0.112 |
Afterwards | -0.110 |
rily | -0.109 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
prise | +0.155 |
w | +0.150 |
uch | +0.146 |
asc | +0.144 |
e | +0.141 |
Neg logit contributions | |
Everyone | -0.058 |
Then | -0.053 |
horizon | -0.052 |
der | -0.051 |
int | -0.051 |
Token | named |
Token ID | 3706 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
ymes | +0.192 |
asc | +0.184 |
prise | +0.183 |
uch | +0.180 |
seeker | +0.179 |
Neg logit contributions | |
The | -0.232 |
Then | -0.221 |
Everyone | -0.219 |
But | -0.213 |
His | -0.208 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.26e+00 |
Pos logit contributions | |
prise | +0.067 |
w | +0.066 |
uch | +0.064 |
a | +0.063 |
e | +0.063 |
Neg logit contributions | |
Everyone | -0.053 |
Afterwards | -0.052 |
horizon | -0.052 |
der | -0.052 |
After | -0.051 |
Token | my |
Token ID | 1820 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
prise | +0.156 |
uch | +0.137 |
ymes | +0.134 |
render | +0.133 |
seeker | +0.132 |
Neg logit contributions | |
Then | -0.168 |
After | -0.164 |
Afterwards | -0.163 |
He | -0.163 |
The | -0.162 |
Token | went |
Token ID | 1816 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
prise | +0.242 |
seeker | +0.223 |
ymes | +0.220 |
asc | +0.220 |
render | +0.217 |
Neg logit contributions | |
Everyone | -0.137 |
Then | -0.133 |
The | -0.129 |
After | -0.126 |
Afterwards | -0.121 |
Token | outside |
Token ID | 2354 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
prise | +0.117 |
w | +0.115 |
uch | +0.113 |
e | +0.110 |
a | +0.110 |
Neg logit contributions | |
Everyone | -0.086 |
After | -0.084 |
der | -0.083 |
horizon | -0.083 |
Then | -0.082 |
Token | One |
Token ID | 3198 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
prise | +0.136 |
w | +0.131 |
uch | +0.129 |
a | +0.126 |
e | +0.123 |
Neg logit contributions | |
Everyone | -0.061 |
Then | -0.055 |
horizon | -0.054 |
Everybody | -0.054 |
der | -0.053 |
Token | day |
Token ID | 1110 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
prise | +0.101 |
w | +0.096 |
uch | +0.090 |
asc | +0.090 |
e | +0.089 |
Neg logit contributions | |
Everyone | -0.086 |
horizon | -0.086 |
Afterwards | -0.081 |
Everybody | -0.081 |
After | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
prise | +0.101 |
e | +0.098 |
asc | +0.097 |
uch | +0.095 |
w | +0.094 |
Neg logit contributions | |
Everyone | -0.091 |
Then | -0.088 |
der | -0.087 |
After | -0.085 |
ment | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
prise | +0.122 |
w | +0.115 |
uch | +0.113 |
asc | +0.113 |
e | +0.109 |
Neg logit contributions | |
Everyone | -0.102 |
Then | -0.102 |
After | -0.100 |
Afterwards | -0.097 |
horizon | -0.097 |
Token | little |
Token ID | 1310 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
prise | +0.159 |
w | +0.159 |
e | +0.155 |
asc | +0.153 |
uch | +0.153 |
Neg logit contributions | |
Everyone | -0.094 |
horizon | -0.091 |
Then | -0.089 |
der | -0.088 |
' | -0.084 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
prise | +0.176 |
uch | +0.174 |
e | +0.169 |
asc | +0.168 |
w | +0.164 |
Neg logit contributions | |
Everyone | -0.103 |
horizon | -0.103 |
der | -0.095 |
ment | -0.092 |
Everybody | -0.092 |
Token | named |
Token ID | 3706 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
uch | +0.199 |
prise | +0.196 |
a | +0.196 |
w | +0.187 |
ymes | +0.183 |
Neg logit contributions | |
Everyone | -0.229 |
Then | -0.225 |
The | -0.223 |
But | -0.213 |
ment | -0.213 |
Token | Tom |
Token ID | 4186 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
prise | +0.093 |
w | +0.092 |
a | +0.089 |
uch | +0.088 |
e | +0.087 |
Neg logit contributions | |
Everyone | -0.076 |
Afterwards | -0.073 |
horizon | -0.072 |
der | -0.072 |
Then | -0.072 |
Token | went |
Token ID | 1816 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
prise | +0.212 |
uch | +0.197 |
a | +0.195 |
w | +0.192 |
ymes | +0.190 |
Neg logit contributions | |
Then | -0.119 |
He | -0.117 |
Everyone | -0.116 |
The | -0.116 |
His | -0.110 |
Token | to |
Token ID | 284 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
w | +0.144 |
prise | +0.143 |
uch | +0.142 |
a | +0.139 |
e | +0.139 |
Neg logit contributions | |
Everyone | -0.097 |
After | -0.094 |
Then | -0.092 |
der | -0.090 |
horizon | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
prise | +0.067 |
w | +0.066 |
uch | +0.063 |
e | +0.062 |
o | +0.062 |
Neg logit contributions | |
horizon | -0.063 |
der | -0.062 |
Everyone | -0.061 |
Afterwards | -0.060 |
rily | -0.059 |
Token | One |
Token ID | 3198 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
prise | +0.208 |
w | +0.205 |
uch | +0.200 |
e | +0.197 |
o | +0.196 |
Neg logit contributions | |
horizon | -0.072 |
der | -0.070 |
Everyone | -0.070 |
Afterwards | -0.068 |
rily | -0.064 |
Token | day |
Token ID | 1110 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
prise | +0.140 |
w | +0.133 |
asc | +0.129 |
tresp | +0.129 |
seeker | +0.125 |
Neg logit contributions | |
Everyone | -0.093 |
horizon | -0.085 |
After | -0.084 |
Everybody | -0.083 |
Then | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
prise | +0.142 |
asc | +0.134 |
aky | +0.130 |
seeker | +0.130 |
e | +0.129 |
Neg logit contributions | |
Everyone | -0.094 |
Then | -0.092 |
After | -0.090 |
ment | -0.086 |
But | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
prise | +0.113 |
uch | +0.104 |
asc | +0.104 |
tresp | +0.102 |
seeker | +0.101 |
Neg logit contributions | |
Then | -0.070 |
After | -0.068 |
Everyone | -0.067 |
But | -0.062 |
The | -0.062 |
Token | little |
Token ID | 1310 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
prise | +0.147 |
w | +0.146 |
e | +0.143 |
uch | +0.141 |
asc | +0.139 |
Neg logit contributions | |
Everyone | -0.080 |
Then | -0.075 |
horizon | -0.072 |
der | -0.071 |
' | -0.071 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.61e+00 |
Pos logit contributions | |
prise | +0.186 |
uch | +0.181 |
e | +0.175 |
asc | +0.174 |
w | +0.171 |
Neg logit contributions | |
Everyone | -0.076 |
horizon | -0.070 |
Then | -0.065 |
ment | -0.065 |
The | -0.065 |
Token | named |
Token ID | 3706 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
prise | +0.183 |
uch | +0.176 |
ll | +0.176 |
seeker | +0.175 |
a | +0.174 |
Neg logit contributions | |
The | -0.244 |
Then | -0.235 |
Everyone | -0.232 |
But | -0.225 |
His | -0.217 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
prise | +0.086 |
w | +0.084 |
a | +0.083 |
uch | +0.082 |
e | +0.079 |
Neg logit contributions | |
Everyone | -0.060 |
Then | -0.056 |
After | -0.055 |
Afterwards | -0.055 |
Everybody | -0.054 |
Token | found |
Token ID | 1043 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
prise | +0.256 |
render | +0.233 |
seeker | +0.230 |
a | +0.227 |
ymes | +0.226 |
Neg logit contributions | |
The | -0.113 |
Then | -0.110 |
He | -0.103 |
Everyone | -0.101 |
After | -0.099 |
Token | a |
Token ID | 257 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
prise | +0.109 |
w | +0.108 |
uch | +0.103 |
o | +0.103 |
e | +0.102 |
Neg logit contributions | |
horizon | -0.116 |
der | -0.115 |
Everyone | -0.112 |
Afterwards | -0.111 |
rily | -0.110 |
Token | long |
Token ID | 890 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
e | +0.122 |
w | +0.116 |
asc | +0.113 |
prise | +0.112 |
o | +0.109 |
Neg logit contributions | |
horizon | -0.051 |
' | -0.049 |
� | -0.047 |
" | -0.045 |
int | -0.045 |
Token | One |
Token ID | 3198 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
prise | +0.167 |
w | +0.165 |
uch | +0.161 |
e | +0.160 |
o | +0.160 |
Neg logit contributions | |
horizon | -0.063 |
der | -0.063 |
Everyone | -0.060 |
Afterwards | -0.059 |
rily | -0.057 |
Token | day |
Token ID | 1110 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
prise | +0.118 |
w | +0.111 |
asc | +0.108 |
seeker | +0.106 |
uch | +0.105 |
Neg logit contributions | |
Everyone | -0.085 |
After | -0.079 |
Afterwards | -0.079 |
horizon | -0.079 |
Everybody | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
prise | +0.108 |
asc | +0.102 |
seeker | +0.098 |
e | +0.097 |
ymes | +0.097 |
Neg logit contributions | |
Everyone | -0.084 |
Then | -0.081 |
After | -0.079 |
der | -0.077 |
Afterwards | -0.077 |
Token | a |
Token ID | 257 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
prise | +0.101 |
uch | +0.094 |
asc | +0.092 |
w | +0.091 |
seeker | +0.090 |
Neg logit contributions | |
Then | -0.064 |
Everyone | -0.064 |
After | -0.062 |
Afterwards | -0.057 |
Everybody | -0.057 |
Token | little |
Token ID | 1310 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
prise | +0.144 |
w | +0.142 |
e | +0.138 |
uch | +0.137 |
asc | +0.136 |
Neg logit contributions | |
Everyone | -0.074 |
Then | -0.069 |
horizon | -0.067 |
der | -0.067 |
' | -0.065 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.60e+00 |
Pos logit contributions | |
prise | +0.159 |
uch | +0.156 |
asc | +0.149 |
e | +0.149 |
w | +0.148 |
Neg logit contributions | |
Everyone | -0.072 |
horizon | -0.067 |
der | -0.063 |
Then | -0.062 |
Everybody | -0.062 |
Token | named |
Token ID | 3706 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
prise | +0.173 |
uch | +0.172 |
ymes | +0.167 |
seeker | +0.166 |
a | +0.165 |
Neg logit contributions | |
The | -0.252 |
Everyone | -0.248 |
Then | -0.247 |
But | -0.236 |
His | -0.233 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
prise | +0.090 |
w | +0.089 |
a | +0.087 |
uch | +0.087 |
e | +0.083 |
Neg logit contributions | |
Everyone | -0.062 |
Then | -0.058 |
After | -0.058 |
Afterwards | -0.058 |
Everybody | -0.056 |
Token | found |
Token ID | 1043 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
prise | +0.247 |
uch | +0.223 |
seeker | +0.223 |
render | +0.222 |
ymes | +0.222 |
Neg logit contributions | |
Then | -0.122 |
The | -0.122 |
He | -0.115 |
Everyone | -0.115 |
After | -0.113 |
Token | a |
Token ID | 257 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
prise | +0.099 |
w | +0.099 |
o | +0.095 |
e | +0.094 |
uch | +0.093 |
Neg logit contributions | |
horizon | -0.122 |
der | -0.119 |
rily | -0.116 |
Afterwards | -0.116 |
int | -0.115 |
Token | sc |
Token ID | 629 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
e | +0.109 |
w | +0.105 |
asc | +0.102 |
prise | +0.100 |
o | +0.097 |
Neg logit contributions | |
horizon | -0.051 |
� | -0.048 |
' | -0.047 |
int | -0.045 |
der | -0.044 |
Token | One |
Token ID | 3198 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
prise | +0.145 |
w | +0.143 |
uch | +0.139 |
e | +0.138 |
o | +0.138 |
Neg logit contributions | |
horizon | -0.055 |
der | -0.054 |
Everyone | -0.052 |
Afterwards | -0.051 |
rily | -0.050 |
Token | day |
Token ID | 1110 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
prise | +0.098 |
w | +0.094 |
asc | +0.091 |
uch | +0.089 |
seeker | +0.088 |
Neg logit contributions | |
Everyone | -0.078 |
horizon | -0.073 |
Everybody | -0.072 |
Afterwards | -0.072 |
After | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
prise | +0.092 |
asc | +0.085 |
e | +0.083 |
seeker | +0.081 |
uch | +0.081 |
Neg logit contributions | |
Everyone | -0.082 |
Then | -0.078 |
der | -0.077 |
After | -0.077 |
Afterwards | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
prise | +0.097 |
uch | +0.089 |
w | +0.087 |
asc | +0.086 |
e | +0.085 |
Neg logit contributions | |
Everyone | -0.072 |
Then | -0.071 |
After | -0.069 |
Afterwards | -0.066 |
Everybody | -0.065 |
Token | little |
Token ID | 1310 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
prise | +0.145 |
w | +0.142 |
uch | +0.136 |
asc | +0.136 |
e | +0.135 |
Neg logit contributions | |
Everyone | -0.071 |
Then | -0.065 |
horizon | -0.064 |
der | -0.063 |
' | -0.062 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.60e+00 |
Pos logit contributions | |
prise | +0.156 |
uch | +0.151 |
e | +0.145 |
asc | +0.145 |
w | +0.142 |
Neg logit contributions | |
Everyone | -0.069 |
horizon | -0.063 |
der | -0.060 |
Everybody | -0.059 |
Then | -0.059 |
Token | named |
Token ID | 3706 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
prise | +0.176 |
uch | +0.172 |
ymes | +0.168 |
seeker | +0.168 |
a | +0.164 |
Neg logit contributions | |
The | -0.252 |
Everyone | -0.247 |
Then | -0.246 |
But | -0.235 |
His | -0.232 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
prise | +0.095 |
w | +0.092 |
a | +0.090 |
uch | +0.089 |
asc | +0.086 |
Neg logit contributions | |
Everyone | -0.066 |
Then | -0.062 |
After | -0.061 |
Afterwards | -0.061 |
Everybody | -0.059 |
Token | found |
Token ID | 1043 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
prise | +0.243 |
render | +0.218 |
seeker | +0.218 |
uch | +0.218 |
ymes | +0.217 |
Neg logit contributions | |
Then | -0.124 |
The | -0.123 |
Everyone | -0.117 |
He | -0.116 |
After | -0.114 |
Token | a |
Token ID | 257 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
w | +0.096 |
prise | +0.096 |
o | +0.093 |
e | +0.092 |
uch | +0.091 |
Neg logit contributions | |
horizon | -0.120 |
der | -0.117 |
rily | -0.114 |
Afterwards | -0.114 |
int | -0.113 |
Token | magic |
Token ID | 5536 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
e | +0.099 |
w | +0.095 |
asc | +0.094 |
prise | +0.092 |
o | +0.089 |
Neg logit contributions | |
horizon | -0.051 |
� | -0.047 |
' | -0.046 |
int | -0.046 |
der | -0.044 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
rier | +0.007 |
rily | +0.007 |
horizon | +0.007 |
int | +0.006 |
der | +0.006 |
Neg logit contributions | |
o | -0.008 |
prise | -0.007 |
w | -0.007 |
asc | -0.007 |
e | -0.007 |
Token | One |
Token ID | 3198 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
prise | +0.189 |
w | +0.188 |
o | +0.183 |
e | +0.183 |
uch | +0.182 |
Neg logit contributions | |
der | -0.081 |
horizon | -0.081 |
Afterwards | -0.075 |
Everyone | -0.075 |
rily | -0.074 |
Token | day |
Token ID | 1110 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
prise | +0.117 |
w | +0.110 |
asc | +0.108 |
tresp | +0.105 |
seeker | +0.105 |
Neg logit contributions | |
Everyone | -0.084 |
horizon | -0.078 |
After | -0.077 |
Afterwards | -0.077 |
Everybody | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
prise | +0.129 |
asc | +0.123 |
seeker | +0.119 |
e | +0.118 |
ymes | +0.115 |
Neg logit contributions | |
Everyone | -0.095 |
After | -0.090 |
Then | -0.090 |
Afterwards | -0.087 |
der | -0.087 |
Token | a |
Token ID | 257 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
prise | +0.102 |
asc | +0.094 |
uch | +0.093 |
tresp | +0.091 |
seeker | +0.090 |
Neg logit contributions | |
Then | -0.067 |
After | -0.066 |
Everyone | -0.066 |
But | -0.060 |
As | -0.059 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.56e+00 |
Pos logit contributions | |
prise | +0.150 |
w | +0.149 |
e | +0.145 |
uch | +0.143 |
asc | +0.142 |
Neg logit contributions | |
Everyone | -0.067 |
Then | -0.063 |
horizon | -0.060 |
der | -0.060 |
' | -0.059 |
Token | named |
Token ID | 3706 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
prise | +0.174 |
uch | +0.170 |
seeker | +0.166 |
ll | +0.165 |
a | +0.165 |
Neg logit contributions | |
The | -0.245 |
Everyone | -0.242 |
Then | -0.240 |
But | -0.230 |
After | -0.225 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
prise | +0.089 |
w | +0.086 |
a | +0.084 |
uch | +0.084 |
e | +0.080 |
Neg logit contributions | |
Everyone | -0.061 |
Then | -0.057 |
After | -0.057 |
Afterwards | -0.056 |
Everybody | -0.055 |
Token | found |
Token ID | 1043 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
prise | +0.246 |
render | +0.224 |
seeker | +0.221 |
a | +0.219 |
ymes | +0.219 |
Neg logit contributions | |
The | -0.121 |
Then | -0.120 |
Everyone | -0.113 |
After | -0.112 |
He | -0.111 |
Token | a |
Token ID | 257 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
w | +0.094 |
prise | +0.094 |
o | +0.090 |
e | +0.089 |
uch | +0.089 |
Neg logit contributions | |
horizon | -0.116 |
der | -0.112 |
Afterwards | -0.110 |
rily | -0.110 |
int | -0.109 |
Token | big |
Token ID | 1263 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
e | +0.103 |
w | +0.099 |
asc | +0.097 |
prise | +0.095 |
o | +0.092 |
Neg logit contributions | |
horizon | -0.048 |
' | -0.044 |
� | -0.044 |
int | -0.044 |
der | -0.042 |
Token | One |
Token ID | 3198 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
prise | +0.161 |
w | +0.159 |
uch | +0.155 |
o | +0.154 |
e | +0.154 |
Neg logit contributions | |
horizon | -0.063 |
der | -0.063 |
Everyone | -0.060 |
Afterwards | -0.059 |
rily | -0.058 |
Token | day |
Token ID | 1110 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
prise | +0.106 |
w | +0.101 |
asc | +0.097 |
uch | +0.095 |
seeker | +0.094 |
Neg logit contributions | |
Everyone | -0.083 |
horizon | -0.079 |
Everybody | -0.077 |
Afterwards | -0.077 |
After | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
prise | +0.119 |
asc | +0.113 |
seeker | +0.109 |
e | +0.107 |
uch | +0.103 |
Neg logit contributions | |
Everyone | -0.087 |
Then | -0.083 |
After | -0.082 |
Afterwards | -0.080 |
der | -0.080 |
Token | a |
Token ID | 257 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
prise | +0.106 |
uch | +0.095 |
asc | +0.094 |
w | +0.094 |
seeker | +0.091 |
Neg logit contributions | |
Everyone | -0.077 |
Then | -0.077 |
After | -0.075 |
Afterwards | -0.071 |
Everybody | -0.070 |
Token | little |
Token ID | 1310 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
prise | +0.148 |
w | +0.144 |
uch | +0.138 |
asc | +0.138 |
e | +0.138 |
Neg logit contributions | |
Everyone | -0.072 |
horizon | -0.067 |
der | -0.066 |
Then | -0.066 |
Everybody | -0.063 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.55e+00 |
Pos logit contributions | |
prise | +0.167 |
uch | +0.162 |
asc | +0.156 |
e | +0.154 |
w | +0.154 |
Neg logit contributions | |
Everyone | -0.074 |
horizon | -0.070 |
der | -0.064 |
Everybody | -0.064 |
Then | -0.063 |
Token | named |
Token ID | 3706 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
prise | +0.176 |
uch | +0.173 |
ymes | +0.169 |
seeker | +0.166 |
a | +0.163 |
Neg logit contributions | |
The | -0.248 |
Everyone | -0.245 |
Then | -0.241 |
But | -0.230 |
After | -0.223 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.91e+00 |
Pos logit contributions | |
prise | +0.099 |
w | +0.097 |
a | +0.096 |
uch | +0.093 |
e | +0.091 |
Neg logit contributions | |
Everyone | -0.066 |
Then | -0.062 |
After | -0.062 |
Afterwards | -0.061 |
Everybody | -0.059 |
Token | found |
Token ID | 1043 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
prise | +0.235 |
uch | +0.210 |
render | +0.209 |
ymes | +0.208 |
a | +0.207 |
Neg logit contributions | |
Then | -0.129 |
The | -0.128 |
Everyone | -0.124 |
He | -0.121 |
After | -0.120 |
Token | a |
Token ID | 257 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
w | +0.097 |
prise | +0.097 |
o | +0.093 |
e | +0.093 |
uch | +0.091 |
Neg logit contributions | |
horizon | -0.124 |
der | -0.120 |
rily | -0.117 |
Afterwards | -0.117 |
int | -0.116 |
Token | filthy |
Token ID | 35677 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
e | +0.108 |
w | +0.105 |
asc | +0.102 |
prise | +0.100 |
o | +0.097 |
Neg logit contributions | |
horizon | -0.055 |
� | -0.050 |
' | -0.050 |
int | -0.049 |
der | -0.047 |
Token | sunny |
Token ID | 27737 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
prise | +0.111 |
w | +0.107 |
asc | +0.102 |
uch | +0.100 |
seeker | +0.099 |
Neg logit contributions | |
Everyone | -0.095 |
horizon | -0.092 |
Afterwards | -0.091 |
After | -0.090 |
Everybody | -0.089 |
Token | day |
Token ID | 1110 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
prise | +0.090 |
a | +0.080 |
uch | +0.080 |
e | +0.079 |
w | +0.079 |
Neg logit contributions | |
Everyone | -0.078 |
horizon | -0.077 |
Afterwards | -0.075 |
After | -0.074 |
Everybody | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
prise | +0.105 |
asc | +0.098 |
e | +0.096 |
w | +0.095 |
uch | +0.095 |
Neg logit contributions | |
Everyone | -0.103 |
der | -0.098 |
Afterwards | -0.098 |
After | -0.098 |
Then | -0.097 |
Token | a |
Token ID | 257 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
prise | +0.098 |
w | +0.094 |
uch | +0.093 |
e | +0.090 |
asc | +0.089 |
Neg logit contributions | |
Everyone | -0.082 |
der | -0.079 |
Then | -0.079 |
After | -0.079 |
Afterwards | -0.079 |
Token | little |
Token ID | 1310 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
prise | +0.158 |
w | +0.158 |
e | +0.152 |
uch | +0.151 |
asc | +0.150 |
Neg logit contributions | |
Everyone | -0.074 |
horizon | -0.071 |
der | -0.069 |
Then | -0.069 |
Everybody | -0.066 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.53e+00 |
Pos logit contributions | |
prise | +0.165 |
uch | +0.158 |
e | +0.153 |
asc | +0.153 |
w | +0.150 |
Neg logit contributions | |
Everyone | -0.079 |
horizon | -0.075 |
der | -0.073 |
Everybody | -0.070 |
Then | -0.069 |
Token | named |
Token ID | 3706 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
prise | +0.164 |
uch | +0.159 |
seeker | +0.154 |
a | +0.153 |
asc | +0.152 |
Neg logit contributions | |
Everyone | -0.260 |
Then | -0.258 |
The | -0.252 |
After | -0.246 |
ment | -0.243 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
prise | +0.089 |
w | +0.088 |
uch | +0.084 |
a | +0.084 |
e | +0.083 |
Neg logit contributions | |
Everyone | -0.071 |
Afterwards | -0.069 |
horizon | -0.068 |
der | -0.068 |
After | -0.068 |
Token | went |
Token ID | 1816 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
prise | +0.215 |
uch | +0.192 |
seeker | +0.190 |
a | +0.189 |
render | +0.186 |
Neg logit contributions | |
Then | -0.140 |
After | -0.136 |
Everyone | -0.134 |
Afterwards | -0.132 |
The | -0.130 |
Token | to |
Token ID | 284 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
prise | +0.138 |
w | +0.138 |
uch | +0.135 |
a | +0.133 |
e | +0.131 |
Neg logit contributions | |
Everyone | -0.096 |
After | -0.093 |
Then | -0.090 |
der | -0.090 |
int | -0.089 |
Token | the |
Token ID | 262 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
prise | +0.056 |
w | +0.055 |
uch | +0.053 |
e | +0.052 |
o | +0.052 |
Neg logit contributions | |
horizon | -0.058 |
der | -0.057 |
Everyone | -0.056 |
Afterwards | -0.056 |
rily | -0.055 |
Token | One |
Token ID | 3198 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
prise | +0.148 |
w | +0.147 |
o | +0.143 |
e | +0.143 |
uch | +0.143 |
Neg logit contributions | |
horizon | -0.064 |
der | -0.063 |
Afterwards | -0.059 |
Everyone | -0.059 |
rily | -0.059 |
Token | day |
Token ID | 1110 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
prise | +0.097 |
w | +0.094 |
asc | +0.091 |
uch | +0.088 |
seeker | +0.086 |
Neg logit contributions | |
Everyone | -0.077 |
horizon | -0.077 |
Afterwards | -0.074 |
After | -0.072 |
Everybody | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
prise | +0.089 |
asc | +0.083 |
e | +0.082 |
o | +0.080 |
seeker | +0.079 |
Neg logit contributions | |
Everyone | -0.087 |
der | -0.085 |
Afterwards | -0.083 |
Then | -0.083 |
After | -0.082 |
Token | a |
Token ID | 257 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
prise | +0.087 |
uch | +0.081 |
w | +0.080 |
asc | +0.078 |
e | +0.078 |
Neg logit contributions | |
Everyone | -0.068 |
Then | -0.067 |
After | -0.066 |
der | -0.066 |
Afterwards | -0.065 |
Token | little |
Token ID | 1310 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
prise | +0.149 |
w | +0.145 |
e | +0.141 |
asc | +0.141 |
uch | +0.139 |
Neg logit contributions | |
Everyone | -0.069 |
horizon | -0.066 |
Then | -0.065 |
der | -0.064 |
Everybody | -0.061 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.53e+00 |
Pos logit contributions | |
prise | +0.156 |
uch | +0.148 |
asc | +0.144 |
e | +0.144 |
w | +0.141 |
Neg logit contributions | |
Everyone | -0.076 |
horizon | -0.076 |
der | -0.070 |
Then | -0.067 |
Everybody | -0.067 |
Token | named |
Token ID | 3706 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
uch | +0.168 |
prise | +0.167 |
ymes | +0.164 |
a | +0.160 |
seeker | +0.160 |
Neg logit contributions | |
The | -0.250 |
Then | -0.249 |
Everyone | -0.245 |
His | -0.236 |
ment | -0.235 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
prise | +0.085 |
w | +0.082 |
a | +0.081 |
uch | +0.079 |
e | +0.078 |
Neg logit contributions | |
Everyone | -0.061 |
Afterwards | -0.058 |
Then | -0.058 |
After | -0.058 |
Everybody | -0.056 |
Token | had |
Token ID | 550 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
prise | +0.216 |
uch | +0.193 |
render | +0.191 |
ymes | +0.189 |
a | +0.189 |
Neg logit contributions | |
Then | -0.133 |
The | -0.130 |
He | -0.126 |
After | -0.125 |
Everyone | -0.125 |
Token | a |
Token ID | 257 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
prise | +0.116 |
w | +0.107 |
a | +0.104 |
uch | +0.104 |
asc | +0.103 |
Neg logit contributions | |
Then | -0.078 |
Everyone | -0.078 |
After | -0.076 |
Afterwards | -0.074 |
der | -0.074 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
w | +0.074 |
asc | +0.072 |
e | +0.070 |
prise | +0.070 |
as | +0.067 |
Neg logit contributions | |
int | -0.044 |
� | -0.044 |
' | -0.043 |
But | -0.042 |
attent | -0.042 |
Token | One |
Token ID | 3198 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
prise | +0.196 |
w | +0.194 |
uch | +0.188 |
e | +0.186 |
o | +0.186 |
Neg logit contributions | |
horizon | -0.072 |
der | -0.071 |
Everyone | -0.069 |
Afterwards | -0.068 |
rily | -0.065 |
Token | day |
Token ID | 1110 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
prise | +0.131 |
w | +0.123 |
asc | +0.120 |
tresp | +0.115 |
uch | +0.115 |
Neg logit contributions | |
Everyone | -0.097 |
horizon | -0.094 |
Afterwards | -0.090 |
Everybody | -0.089 |
After | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
prise | +0.127 |
asc | +0.118 |
e | +0.116 |
seeker | +0.113 |
ymes | +0.110 |
Neg logit contributions | |
Everyone | -0.095 |
Then | -0.093 |
After | -0.090 |
der | -0.090 |
Afterwards | -0.088 |
Token | a |
Token ID | 257 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
prise | +0.123 |
asc | +0.111 |
uch | +0.110 |
seeker | +0.108 |
w | +0.107 |
Neg logit contributions | |
Then | -0.086 |
After | -0.084 |
Everyone | -0.083 |
Afterwards | -0.077 |
But | -0.076 |
Token | little |
Token ID | 1310 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
prise | +0.163 |
w | +0.161 |
e | +0.159 |
asc | +0.156 |
uch | +0.154 |
Neg logit contributions | |
Everyone | -0.078 |
Then | -0.073 |
horizon | -0.073 |
der | -0.072 |
' | -0.070 |
Token | boy |
Token ID | 2933 |
Feature activation | +9.53e+00 |
Pos logit contributions | |
prise | +0.174 |
uch | +0.168 |
asc | +0.166 |
e | +0.166 |
w | +0.158 |
Neg logit contributions | |
Everyone | -0.082 |
horizon | -0.079 |
der | -0.075 |
ment | -0.074 |
rier | -0.072 |
Token | named |
Token ID | 3706 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
prise | +0.177 |
uch | +0.169 |
ymes | +0.168 |
a | +0.167 |
seeker | +0.166 |
Neg logit contributions | |
The | -0.248 |
Everyone | -0.238 |
Then | -0.238 |
But | -0.229 |
His | -0.226 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.10e+00 |
Pos logit contributions | |
prise | +0.104 |
w | +0.103 |
a | +0.100 |
uch | +0.099 |
e | +0.097 |
Neg logit contributions | |
Everyone | -0.075 |
Then | -0.071 |
After | -0.070 |
Afterwards | -0.070 |
Everybody | -0.068 |
Token | found |
Token ID | 1043 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
prise | +0.246 |
render | +0.223 |
ymes | +0.219 |
a | +0.218 |
seeker | +0.215 |
Neg logit contributions | |
The | -0.128 |
Then | -0.123 |
He | -0.119 |
Everyone | -0.114 |
After | -0.111 |
Token | some |
Token ID | 617 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
w | +0.104 |
prise | +0.103 |
o | +0.100 |
e | +0.098 |
uch | +0.097 |
Neg logit contributions | |
horizon | -0.128 |
der | -0.124 |
rily | -0.121 |
Afterwards | -0.121 |
int | -0.121 |
Token | clay |
Token ID | 21558 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Everyone | +0.003 |
der | +0.003 |
horizon | +0.003 |
rier | +0.003 |
Everybody | +0.003 |
Neg logit contributions | |
prise | -0.005 |
o | -0.005 |
e | -0.005 |
uch | -0.005 |
w | -0.005 |
Token | using |
Token ID | 1262 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
rily | +0.066 |
der | +0.066 |
horizon | +0.066 |
Afterwards | +0.065 |
Everyone | +0.064 |
Neg logit contributions | |
prise | -0.045 |
w | -0.045 |
uch | -0.043 |
e | -0.042 |
a | -0.040 |
Token | them |
Token ID | 606 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
horizon | +0.063 |
der | +0.063 |
Afterwards | +0.062 |
rily | +0.061 |
Everyone | +0.060 |
Neg logit contributions | |
prise | -0.073 |
w | -0.072 |
e | -0.070 |
a | -0.068 |
uch | -0.067 |
Token | ,' |
Token ID | 4032 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
horizon | +0.098 |
der | +0.096 |
Afterwards | +0.095 |
rily | +0.095 |
Everyone | +0.094 |
Neg logit contributions | |
prise | -0.085 |
w | -0.084 |
a | -0.081 |
e | -0.080 |
uch | -0.080 |
Token | Jack |
Token ID | 3619 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
horizon | +0.118 |
der | +0.112 |
rily | +0.108 |
Afterwards | +0.107 |
lights | +0.102 |
Neg logit contributions | |
a | -0.130 |
w | -0.129 |
e | -0.129 |
prise | -0.126 |
o | -0.126 |
Token | said |
Token ID | 531 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
horizon | +0.020 |
der | +0.020 |
Everyone | +0.020 |
Afterwards | +0.020 |
rily | +0.019 |
Neg logit contributions | |
prise | -0.020 |
w | -0.020 |
uch | -0.019 |
o | -0.019 |
e | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
horizon | +0.087 |
Afterwards | +0.079 |
growth | +0.077 |
der | +0.075 |
lights | +0.075 |
Neg logit contributions | |
a | -0.052 |
e | -0.049 |
prise | -0.045 |
o | -0.044 |
w | -0.042 |
Token | ' |
Token ID | 705 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
horizon | +0.133 |
rier | +0.131 |
rily | +0.129 |
ment | +0.129 |
der | +0.128 |
Neg logit contributions | |
o | -0.208 |
e | -0.185 |
a | -0.183 |
prise | -0.180 |
w | -0.170 |
Token | And |
Token ID | 1870 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
der | +0.008 |
horizon | +0.008 |
Everyone | +0.008 |
Afterwards | +0.008 |
rily | +0.008 |
Neg logit contributions | |
prise | -0.009 |
w | -0.009 |
e | -0.008 |
uch | -0.008 |
a | -0.008 |
Token | don |
Token ID | 836 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
horizon | +0.076 |
der | +0.075 |
rily | +0.074 |
Afterwards | +0.072 |
ment | +0.070 |
Neg logit contributions | |
prise | -0.061 |
w | -0.057 |
a | -0.057 |
e | -0.057 |
uch | -0.055 |
Token | 't |
Token ID | 470 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
uch | +0.024 |
w | +0.024 |
prise | +0.023 |
e | +0.023 |
a | +0.022 |
Neg logit contributions | |
ment | -0.047 |
horizon | -0.047 |
rily | -0.046 |
der | -0.046 |
Afterwards | -0.045 |
Token | forget |
Token ID | 6044 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
prise | +0.011 |
w | +0.011 |
uch | +0.010 |
e | +0.010 |
o | +0.010 |
Neg logit contributions | |
horizon | -0.012 |
der | -0.012 |
Everyone | -0.012 |
Afterwards | -0.012 |
rily | -0.012 |
Token | r |
Token ID | 81 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
horizon | +0.113 |
der | +0.109 |
Afterwards | +0.108 |
Everyone | +0.106 |
rily | +0.106 |
Neg logit contributions | |
w | -0.102 |
a | -0.099 |
o | -0.098 |
prise | -0.098 |
e | -0.098 |
Token | ut |
Token ID | 315 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
horizon | +0.087 |
der | +0.085 |
Afterwards | +0.084 |
Everyone | +0.083 |
int | +0.081 |
Neg logit contributions | |
w | -0.071 |
prise | -0.070 |
e | -0.068 |
a | -0.067 |
o | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
horizon | +0.066 |
der | +0.065 |
Afterwards | +0.063 |
rily | +0.062 |
Everyone | +0.062 |
Neg logit contributions | |
w | -0.067 |
e | -0.063 |
prise | -0.063 |
o | -0.063 |
a | -0.063 |
Token | pand |
Token ID | 19798 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
horizon | +0.152 |
der | +0.148 |
Afterwards | +0.146 |
rily | +0.146 |
Everyone | +0.146 |
Neg logit contributions | |
w | -0.148 |
prise | -0.146 |
e | -0.144 |
a | -0.141 |
o | -0.138 |
Token | an |
Token ID | 272 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
prise | +0.003 |
seeker | +0.003 |
w | +0.003 |
uch | +0.003 |
e | +0.002 |
Neg logit contributions | |
der | -0.010 |
Everyone | -0.009 |
horizon | -0.009 |
ment | -0.009 |
Everybody | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
horizon | +0.097 |
der | +0.096 |
Everyone | +0.094 |
Afterwards | +0.093 |
rily | +0.092 |
Neg logit contributions | |
prise | -0.092 |
w | -0.091 |
uch | -0.087 |
e | -0.087 |
o | -0.087 |
Token | curry |
Token ID | 34611 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
horizon | +0.167 |
der | +0.163 |
Afterwards | +0.162 |
rily | +0.161 |
Everyone | +0.161 |
Neg logit contributions | |
w | -0.169 |
prise | -0.167 |
e | -0.165 |
a | -0.161 |
o | -0.158 |
Token | leaf |
Token ID | 12835 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
horizon | +0.067 |
der | +0.066 |
Everyone | +0.065 |
Afterwards | +0.065 |
rily | +0.064 |
Neg logit contributions | |
prise | -0.061 |
w | -0.061 |
uch | -0.058 |
e | -0.057 |
a | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
horizon | +0.089 |
der | +0.088 |
Everyone | +0.086 |
Afterwards | +0.086 |
rily | +0.084 |
Neg logit contributions | |
prise | -0.085 |
w | -0.084 |
uch | -0.080 |
o | -0.079 |
e | -0.079 |
Token | ne |
Token ID | 497 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
horizon | +0.152 |
Afterwards | +0.147 |
Everyone | +0.147 |
der | +0.147 |
rily | +0.146 |
Neg logit contributions | |
w | -0.160 |
prise | -0.158 |
e | -0.156 |
a | -0.152 |
o | -0.151 |
Token | em |
Token ID | 368 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
prise | +0.030 |
w | +0.028 |
uch | +0.028 |
seeker | +0.027 |
o | +0.026 |
Neg logit contributions | |
der | -0.043 |
rily | -0.043 |
horizon | -0.043 |
int | -0.043 |
Afterwards | -0.042 |
Token | moan |
Token ID | 44567 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
horizon | +0.029 |
der | +0.029 |
Everyone | +0.028 |
Afterwards | +0.027 |
int | +0.027 |
Neg logit contributions | |
prise | -0.037 |
w | -0.036 |
uch | -0.035 |
o | -0.034 |
e | -0.034 |
Token | came |
Token ID | 1625 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
der | +0.004 |
horizon | +0.004 |
Everyone | +0.004 |
Afterwards | +0.004 |
int | +0.004 |
Neg logit contributions | |
prise | -0.004 |
w | -0.003 |
uch | -0.003 |
e | -0.003 |
o | -0.003 |
Token | from |
Token ID | 422 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
prise | +0.012 |
w | +0.012 |
uch | +0.011 |
e | +0.011 |
seeker | +0.011 |
Neg logit contributions | |
horizon | -0.009 |
der | -0.009 |
int | -0.008 |
rily | -0.008 |
Everyone | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
der | +0.025 |
horizon | +0.024 |
Everyone | +0.024 |
Afterwards | +0.024 |
rily | +0.023 |
Neg logit contributions | |
prise | -0.029 |
w | -0.029 |
e | -0.028 |
o | -0.028 |
uch | -0.027 |
Token | corner |
Token ID | 5228 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
horizon | +0.034 |
der | +0.032 |
Everyone | +0.032 |
Afterwards | +0.031 |
int | +0.031 |
Neg logit contributions | |
prise | -0.039 |
w | -0.039 |
uch | -0.037 |
o | -0.037 |
e | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
horizon | +0.055 |
der | +0.055 |
Everyone | +0.054 |
Afterwards | +0.053 |
int | +0.052 |
Neg logit contributions | |
prise | -0.062 |
w | -0.061 |
uch | -0.059 |
e | -0.058 |
o | -0.058 |
Token | It |
Token ID | 632 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
horizon | +0.119 |
der | +0.114 |
rily | +0.111 |
rier | +0.108 |
lights | +0.107 |
Neg logit contributions | |
o | -0.207 |
e | -0.199 |
prise | -0.198 |
a | -0.198 |
w | -0.185 |
Token | was |
Token ID | 373 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
horizon | +0.045 |
der | +0.045 |
Everyone | +0.044 |
Afterwards | +0.044 |
rily | +0.043 |
Neg logit contributions | |
prise | -0.041 |
w | -0.040 |
uch | -0.038 |
o | -0.038 |
e | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
prise | +0.019 |
w | +0.019 |
uch | +0.018 |
e | +0.018 |
o | +0.018 |
Neg logit contributions | |
horizon | -0.020 |
der | -0.019 |
Everyone | -0.019 |
Afterwards | -0.019 |
int | -0.019 |
Token | lady |
Token ID | 10846 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
horizon | +0.065 |
der | +0.061 |
Everyone | +0.059 |
rier | +0.058 |
int | +0.058 |
Neg logit contributions | |
prise | -0.070 |
w | -0.069 |
o | -0.067 |
uch | -0.066 |
e | -0.066 |
Token | 's |
Token ID | 338 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
int | +0.016 |
horizon | +0.016 |
rily | +0.016 |
der | +0.016 |
Everyone | +0.015 |
Neg logit contributions | |
w | -0.017 |
prise | -0.016 |
seeker | -0.016 |
uch | -0.016 |
asc | -0.016 |
Token | store |
Token ID | 3650 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
der | +0.081 |
horizon | +0.079 |
Afterwards | +0.077 |
int | +0.075 |
Then | +0.075 |
Neg logit contributions | |
w | -0.076 |
prise | -0.075 |
a | -0.074 |
e | -0.073 |
uch | -0.071 |
Token | ', |
Token ID | 3256 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
der | +0.080 |
horizon | +0.077 |
Afterwards | +0.076 |
Then | +0.073 |
Everyone | +0.073 |
Neg logit contributions | |
prise | -0.070 |
a | -0.068 |
w | -0.068 |
e | -0.065 |
o | -0.065 |
Token | his |
Token ID | 465 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
horizon | +0.142 |
der | +0.138 |
Afterwards | +0.130 |
rily | +0.126 |
int | +0.125 |
Neg logit contributions | |
e | -0.150 |
a | -0.147 |
w | -0.146 |
prise | -0.144 |
o | -0.141 |
Token | dad |
Token ID | 9955 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
der | +0.086 |
horizon | +0.085 |
Afterwards | +0.083 |
Everyone | +0.082 |
rily | +0.080 |
Neg logit contributions | |
prise | -0.129 |
w | -0.124 |
a | -0.123 |
e | -0.121 |
uch | -0.121 |
Token | said |
Token ID | 531 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
horizon | +0.036 |
der | +0.036 |
Everyone | +0.035 |
Afterwards | +0.035 |
rily | +0.034 |
Neg logit contributions | |
prise | -0.032 |
w | -0.031 |
o | -0.030 |
e | -0.030 |
a | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
horizon | +0.079 |
Afterwards | +0.072 |
lights | +0.071 |
der | +0.070 |
growth | +0.067 |
Neg logit contributions | |
a | -0.071 |
e | -0.070 |
prise | -0.067 |
w | -0.064 |
o | -0.062 |
Token | |
Token ID | 220 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
horizon | +0.116 |
lights | +0.115 |
der | +0.113 |
ment | +0.112 |
rier | +0.103 |
Neg logit contributions | |
o | -0.213 |
a | -0.199 |
e | -0.196 |
prise | -0.185 |
ee | -0.176 |
Token |
|
Token ID | 198 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
horizon | +0.086 |
der | +0.080 |
lights | +0.075 |
rier | +0.073 |
ment | +0.073 |
Neg logit contributions | |
o | -0.093 |
a | -0.089 |
prise | -0.078 |
e | -0.077 |
as | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
der | +0.066 |
horizon | +0.064 |
rier | +0.060 |
ment | +0.059 |
rily | +0.059 |
Neg logit contributions | |
a | -0.088 |
o | -0.088 |
prise | -0.086 |
e | -0.085 |
w | -0.082 |
Token | John |
Token ID | 7554 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
der | +0.048 |
horizon | +0.048 |
rily | +0.045 |
Afterwards | +0.045 |
ment | +0.044 |
Neg logit contributions | |
prise | -0.059 |
w | -0.057 |
a | -0.057 |
e | -0.056 |
o | -0.056 |
Token | was |
Token ID | 373 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
horizon | +0.020 |
der | +0.020 |
Everyone | +0.020 |
Afterwards | +0.020 |
int | +0.019 |
Neg logit contributions | |
prise | -0.020 |
w | -0.020 |
uch | -0.019 |
o | -0.018 |
e | -0.018 |
Token | words |
Token ID | 2456 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
horizon | +0.086 |
der | +0.085 |
Everyone | +0.083 |
Afterwards | +0.083 |
rily | +0.081 |
Neg logit contributions | |
prise | -0.093 |
w | -0.092 |
uch | -0.088 |
e | -0.087 |
o | -0.087 |
Token | very |
Token ID | 845 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
der | +0.035 |
horizon | +0.035 |
Everyone | +0.034 |
Afterwards | +0.033 |
rily | +0.033 |
Neg logit contributions | |
prise | -0.036 |
w | -0.035 |
uch | -0.034 |
o | -0.033 |
e | -0.033 |
Token | clearly |
Token ID | 4084 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
horizon | +0.079 |
Afterwards | +0.077 |
der | +0.076 |
Everyone | +0.075 |
rily | +0.074 |
Neg logit contributions | |
prise | -0.060 |
w | -0.060 |
a | -0.058 |
uch | -0.057 |
o | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
horizon | +0.076 |
Everyone | +0.074 |
der | +0.074 |
Afterwards | +0.074 |
rily | +0.072 |
Neg logit contributions | |
w | -0.065 |
prise | -0.065 |
e | -0.062 |
o | -0.062 |
a | -0.061 |
Token | slowly |
Token ID | 6364 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
horizon | +0.132 |
rily | +0.125 |
Everyone | +0.124 |
der | +0.124 |
Afterwards | +0.123 |
Neg logit contributions | |
prise | -0.117 |
w | -0.115 |
o | -0.113 |
a | -0.113 |
e | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
horizon | +0.094 |
Everyone | +0.092 |
der | +0.091 |
Afterwards | +0.091 |
Everybody | +0.090 |
Neg logit contributions | |
prise | -0.077 |
w | -0.076 |
e | -0.074 |
a | -0.074 |
o | -0.074 |
Token | She |
Token ID | 1375 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
horizon | +0.156 |
ment | +0.153 |
rily | +0.152 |
rier | +0.151 |
lights | +0.149 |
Neg logit contributions | |
o | -0.172 |
a | -0.153 |
seeker | -0.142 |
prise | -0.140 |
asc | -0.136 |
Token | first |
Token ID | 717 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
horizon | +0.069 |
der | +0.069 |
Everyone | +0.068 |
Afterwards | +0.067 |
rily | +0.066 |
Neg logit contributions | |
prise | -0.064 |
w | -0.063 |
uch | -0.060 |
e | -0.060 |
o | -0.059 |
Token | explained |
Token ID | 4893 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
der | +0.071 |
horizon | +0.071 |
Everyone | +0.071 |
Afterwards | +0.069 |
int | +0.068 |
Neg logit contributions | |
prise | -0.069 |
w | -0.067 |
uch | -0.065 |
o | -0.063 |
e | -0.062 |
Token | about |
Token ID | 546 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
horizon | +0.112 |
Afterwards | +0.108 |
rily | +0.103 |
Everyone | +0.102 |
Everybody | +0.101 |
Neg logit contributions | |
prise | -0.096 |
a | -0.094 |
w | -0.093 |
o | -0.090 |
e | -0.089 |
Token | shapes |
Token ID | 15268 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
horizon | +0.068 |
Afterwards | +0.066 |
der | +0.066 |
Everyone | +0.065 |
rily | +0.064 |
Neg logit contributions | |
prise | -0.083 |
w | -0.081 |
e | -0.079 |
o | -0.079 |
a | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
der | +0.038 |
horizon | +0.038 |
Everyone | +0.038 |
Afterwards | +0.037 |
rily | +0.036 |
Neg logit contributions | |
prise | -0.042 |
w | -0.041 |
e | -0.039 |
uch | -0.039 |
o | -0.039 |
Token | stairs |
Token ID | 16046 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
horizon | +0.043 |
der | +0.042 |
Everyone | +0.041 |
Afterwards | +0.041 |
int | +0.040 |
Neg logit contributions | |
prise | -0.056 |
w | -0.055 |
uch | -0.053 |
o | -0.053 |
e | -0.053 |
Token | ,' |
Token ID | 4032 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
horizon | +0.056 |
der | +0.056 |
Everyone | +0.055 |
Afterwards | +0.055 |
rily | +0.054 |
Neg logit contributions | |
prise | -0.047 |
w | -0.046 |
uch | -0.044 |
e | -0.044 |
o | -0.044 |
Token | he |
Token ID | 339 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
der | +0.131 |
horizon | +0.130 |
rily | +0.126 |
lights | +0.125 |
Afterwards | +0.121 |
Neg logit contributions | |
w | -0.137 |
o | -0.137 |
a | -0.136 |
e | -0.135 |
prise | -0.128 |
Token | replied |
Token ID | 8712 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
horizon | +0.062 |
der | +0.061 |
Afterwards | +0.059 |
Everyone | +0.058 |
rily | +0.058 |
Neg logit contributions | |
prise | -0.049 |
w | -0.049 |
a | -0.048 |
o | -0.047 |
e | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
horizon | +0.113 |
Afterwards | +0.107 |
der | +0.105 |
lights | +0.103 |
Everyone | +0.100 |
Neg logit contributions | |
e | -0.071 |
a | -0.070 |
prise | -0.062 |
o | -0.062 |
w | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
lights | +0.145 |
rily | +0.135 |
der | +0.134 |
horizon | +0.130 |
rier | +0.130 |
Neg logit contributions | |
o | -0.197 |
a | -0.180 |
e | -0.175 |
w | -0.170 |
prise | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
der | +0.068 |
horizon | +0.065 |
rily | +0.065 |
rier | +0.064 |
lights | +0.062 |
Neg logit contributions | |
o | -0.091 |
a | -0.089 |
prise | -0.088 |
w | -0.088 |
e | -0.086 |
Token | His |
Token ID | 6653 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
der | +0.066 |
rily | +0.065 |
horizon | +0.065 |
lights | +0.062 |
rier | +0.062 |
Neg logit contributions | |
prise | -0.058 |
w | -0.057 |
o | -0.056 |
a | -0.056 |
e | -0.055 |
Token | uncle |
Token ID | 7711 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
der | +0.087 |
rily | +0.085 |
horizon | +0.085 |
Everyone | +0.084 |
Afterwards | +0.084 |
Neg logit contributions | |
prise | -0.107 |
w | -0.106 |
a | -0.103 |
o | -0.102 |
uch | -0.102 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
der | +0.049 |
Everyone | +0.049 |
horizon | +0.048 |
Then | +0.047 |
Afterwards | +0.047 |
Neg logit contributions | |
prise | -0.058 |
w | -0.057 |
uch | -0.055 |
asc | -0.053 |
e | -0.052 |
Token | so |
Token ID | 523 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
prise | +0.050 |
w | +0.049 |
uch | +0.047 |
o | +0.045 |
e | +0.044 |
Neg logit contributions | |
horizon | -0.057 |
der | -0.057 |
Everyone | -0.056 |
int | -0.056 |
rily | -0.054 |
Token | interested |
Token ID | 4609 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
horizon | +0.009 |
der | +0.009 |
Everyone | +0.009 |
int | +0.009 |
Afterwards | +0.009 |
Neg logit contributions | |
prise | -0.007 |
w | -0.007 |
uch | -0.007 |
e | -0.006 |
o | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
der | +0.050 |
horizon | +0.049 |
Everyone | +0.048 |
rily | +0.048 |
int | +0.048 |
Neg logit contributions | |
prise | -0.043 |
w | -0.041 |
uch | -0.040 |
e | -0.038 |
o | -0.038 |
Token | their |
Token ID | 511 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
horizon | +0.052 |
der | +0.052 |
Afterwards | +0.051 |
Everyone | +0.050 |
rily | +0.050 |
Neg logit contributions | |
prise | -0.077 |
w | -0.076 |
e | -0.074 |
uch | -0.073 |
o | -0.073 |
Token | language |
Token ID | 3303 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
horizon | +0.115 |
der | +0.114 |
Everyone | +0.112 |
Afterwards | +0.111 |
int | +0.109 |
Neg logit contributions | |
prise | -0.124 |
w | -0.122 |
uch | -0.117 |
o | -0.116 |
e | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
horizon | +0.125 |
Afterwards | +0.122 |
der | +0.122 |
rily | +0.120 |
Everyone | +0.120 |
Neg logit contributions | |
prise | -0.110 |
w | -0.107 |
o | -0.104 |
e | -0.104 |
a | -0.103 |
Token | J |
Token ID | 449 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
rily | +0.163 |
rier | +0.162 |
lights | +0.160 |
der | +0.156 |
ment | +0.155 |
Neg logit contributions | |
o | -0.165 |
a | -0.142 |
e | -0.139 |
prise | -0.134 |
seeker | -0.134 |
Token | ax |
Token ID | 897 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
horizon | +0.059 |
der | +0.058 |
Afterwards | +0.058 |
Everyone | +0.057 |
rily | +0.056 |
Neg logit contributions | |
w | -0.041 |
prise | -0.040 |
o | -0.039 |
uch | -0.039 |
e | -0.038 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
der | +0.010 |
horizon | +0.010 |
Everyone | +0.009 |
Afterwards | +0.009 |
int | +0.009 |
Neg logit contributions | |
prise | -0.010 |
w | -0.010 |
uch | -0.010 |
e | -0.009 |
asc | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
Afterwards | +0.043 |
horizon | +0.043 |
Everyone | +0.042 |
growth | +0.041 |
Everybody | +0.041 |
Neg logit contributions | |
a | -0.024 |
o | -0.024 |
e | -0.022 |
mean | -0.020 |
prise | -0.020 |
Token | replied |
Token ID | 8712 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
horizon | +0.104 |
lights | +0.098 |
rily | +0.098 |
rier | +0.097 |
der | +0.095 |
Neg logit contributions | |
a | -0.058 |
o | -0.056 |
w | -0.055 |
e | -0.052 |
prise | -0.051 |
Token | that |
Token ID | 326 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
horizon | +0.014 |
der | +0.014 |
rily | +0.014 |
Afterwards | +0.014 |
ment | +0.013 |
Neg logit contributions | |
e | -0.014 |
prise | -0.014 |
o | -0.013 |
w | -0.013 |
a | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
horizon | +0.101 |
der | +0.099 |
rily | +0.098 |
Afterwards | +0.097 |
Everyone | +0.096 |
Neg logit contributions | |
w | -0.110 |
prise | -0.109 |
uch | -0.104 |
o | -0.104 |
e | -0.103 |
Token | " |
Token ID | 366 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
horizon | +0.078 |
der | +0.075 |
Afterwards | +0.074 |
Everyone | +0.073 |
rily | +0.072 |
Neg logit contributions | |
prise | -0.078 |
w | -0.076 |
e | -0.074 |
o | -0.073 |
a | -0.073 |
Token | Free |
Token ID | 11146 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
w | +0.002 |
prise | +0.002 |
e | +0.002 |
o | +0.002 |
a | +0.002 |
Neg logit contributions | |
der | -0.002 |
horizon | -0.002 |
Afterwards | -0.002 |
rily | -0.002 |
Everyone | -0.002 |
Token | Candy |
Token ID | 24680 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
Everyone | +0.011 |
der | +0.011 |
Everybody | +0.011 |
Afterwards | +0.010 |
horizon | +0.010 |
Neg logit contributions | |
prise | -0.010 |
w | -0.010 |
uch | -0.009 |
o | -0.009 |
seeker | -0.009 |
Token | ". |
Token ID | 1911 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
der | +0.019 |
Everyone | +0.019 |
horizon | +0.018 |
Afterwards | +0.018 |
rily | +0.018 |
Neg logit contributions | |
prise | -0.020 |
w | -0.020 |
uch | -0.019 |
e | -0.018 |
o | -0.018 |
Token | A |
Token ID | 317 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
horizon | +0.136 |
lights | +0.135 |
der | +0.132 |
rily | +0.122 |
rier | +0.121 |
Neg logit contributions | |
o | -0.195 |
e | -0.191 |
a | -0.188 |
prise | -0.179 |
w | -0.178 |
Token | man |
Token ID | 582 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
horizon | +0.026 |
Everyone | +0.026 |
der | +0.026 |
Afterwards | +0.025 |
int | +0.025 |
Neg logit contributions | |
w | -0.034 |
prise | -0.033 |
uch | -0.033 |
asc | -0.032 |
e | -0.032 |
Token | with |
Token ID | 351 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
w | +0.021 |
uch | +0.020 |
prise | +0.020 |
seeker | +0.020 |
asc | +0.019 |
Neg logit contributions | |
int | -0.019 |
der | -0.019 |
Everyone | -0.018 |
Then | -0.018 |
horizon | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
horizon | +0.018 |
der | +0.018 |
Afterwards | +0.018 |
rily | +0.018 |
Everyone | +0.017 |
Neg logit contributions | |
prise | -0.015 |
w | -0.014 |
e | -0.014 |
a | -0.014 |
o | -0.014 |
Token | beard |
Token ID | 21213 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
horizon | +0.051 |
Everyone | +0.050 |
der | +0.050 |
Afterwards | +0.048 |
int | +0.048 |
Neg logit contributions | |
prise | -0.049 |
w | -0.049 |
uch | -0.047 |
e | -0.046 |
o | -0.046 |
Token | discover |
Token ID | 7073 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
horizon | +0.076 |
rily | +0.076 |
Afterwards | +0.075 |
der | +0.075 |
Everyone | +0.074 |
Neg logit contributions | |
prise | -0.072 |
w | -0.071 |
e | -0.069 |
o | -0.068 |
a | -0.067 |
Token | " |
Token ID | 1 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
horizon | +0.082 |
Afterwards | +0.080 |
der | +0.077 |
rily | +0.074 |
After | +0.074 |
Neg logit contributions | |
a | -0.077 |
prise | -0.076 |
e | -0.073 |
w | -0.073 |
o | -0.068 |
Token | written |
Token ID | 3194 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
horizon | +0.109 |
der | +0.107 |
Afterwards | +0.105 |
rily | +0.103 |
int | +0.102 |
Neg logit contributions | |
w | -0.096 |
o | -0.095 |
a | -0.094 |
prise | -0.093 |
e | -0.090 |
Token | on |
Token ID | 319 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
horizon | +0.069 |
Afterwards | +0.066 |
der | +0.065 |
rily | +0.062 |
Everyone | +0.062 |
Neg logit contributions | |
a | -0.080 |
w | -0.079 |
prise | -0.077 |
e | -0.077 |
o | -0.077 |
Token | it |
Token ID | 340 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
horizon | +0.114 |
Afterwards | +0.112 |
der | +0.107 |
rily | +0.104 |
lights | +0.104 |
Neg logit contributions | |
e | -0.130 |
w | -0.125 |
a | -0.125 |
prise | -0.119 |
o | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | -7.03e+00 |
Pos logit contributions | |
horizon | +0.126 |
Afterwards | +0.120 |
der | +0.119 |
rily | +0.116 |
ment | +0.116 |
Neg logit contributions | |
e | -0.098 |
a | -0.098 |
w | -0.098 |
prise | -0.098 |
o | -0.096 |
Token |
|
Token ID | 198 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
horizon | +0.128 |
der | +0.123 |
ment | +0.119 |
rier | +0.117 |
rily | +0.116 |
Neg logit contributions | |
o | -0.200 |
a | -0.185 |
e | -0.184 |
prise | -0.183 |
itty | -0.171 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
der | +0.053 |
horizon | +0.052 |
rily | +0.048 |
Afterwards | +0.047 |
rier | +0.047 |
Neg logit contributions | |
prise | -0.092 |
o | -0.090 |
a | -0.090 |
w | -0.089 |
e | -0.088 |
Token | Lu |
Token ID | 25596 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
horizon | +0.037 |
der | +0.037 |
Everyone | +0.036 |
Afterwards | +0.036 |
int | +0.035 |
Neg logit contributions | |
prise | -0.049 |
w | -0.049 |
uch | -0.047 |
o | -0.046 |
e | -0.046 |
Token | cy |
Token ID | 948 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
prise | +0.005 |
w | +0.004 |
uch | +0.004 |
e | +0.004 |
o | +0.004 |
Neg logit contributions | |
horizon | -0.013 |
der | -0.012 |
Everyone | -0.012 |
Afterwards | -0.012 |
rily | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
der | +0.019 |
horizon | +0.019 |
Everyone | +0.019 |
Afterwards | +0.019 |
int | +0.018 |
Neg logit contributions | |
prise | -0.020 |
w | -0.019 |
uch | -0.019 |
asc | -0.018 |
o | -0.018 |
Token | out |
Token ID | 503 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
prise | +0.044 |
w | +0.043 |
uch | +0.042 |
o | +0.041 |
e | +0.040 |
Neg logit contributions | |
horizon | -0.038 |
der | -0.037 |
rily | -0.036 |
int | -0.036 |
Everyone | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Afterwards | +0.026 |
horizon | +0.026 |
Everyone | +0.026 |
Everybody | +0.025 |
der | +0.025 |
Neg logit contributions | |
prise | -0.019 |
e | -0.019 |
a | -0.018 |
o | -0.018 |
w | -0.017 |
Token | began |
Token ID | 2540 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
der | +0.071 |
horizon | +0.071 |
Everyone | +0.071 |
Afterwards | +0.070 |
Everybody | +0.069 |
Neg logit contributions | |
w | -0.049 |
prise | -0.048 |
a | -0.047 |
o | -0.047 |
e | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
horizon | +0.016 |
der | +0.016 |
Everyone | +0.015 |
Afterwards | +0.015 |
rily | +0.015 |
Neg logit contributions | |
prise | -0.015 |
w | -0.014 |
o | -0.014 |
e | -0.014 |
a | -0.014 |
Token | speak |
Token ID | 2740 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
w | +0.009 |
prise | +0.009 |
uch | +0.009 |
o | +0.009 |
a | +0.009 |
Neg logit contributions | |
horizon | -0.010 |
der | -0.009 |
Everyone | -0.009 |
int | -0.009 |
Afterwards | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -7.01e+00 |
Pos logit contributions | |
horizon | +0.086 |
Afterwards | +0.085 |
der | +0.083 |
Everyone | +0.081 |
Everybody | +0.079 |
Neg logit contributions | |
a | -0.074 |
prise | -0.074 |
w | -0.072 |
o | -0.071 |
e | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
lights | +0.163 |
der | +0.137 |
horizon | +0.132 |
ment | +0.126 |
rily | +0.116 |
Neg logit contributions | |
o | -0.173 |
e | -0.170 |
a | -0.168 |
ow | -0.149 |
named | -0.144 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
der | +0.049 |
horizon | +0.048 |
lights | +0.047 |
rier | +0.046 |
rily | +0.045 |
Neg logit contributions | |
a | -0.049 |
o | -0.049 |
e | -0.047 |
prise | -0.046 |
w | -0.045 |
Token | The |
Token ID | 464 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
horizon | +0.026 |
der | +0.026 |
lights | +0.025 |
rily | +0.025 |
ment | +0.025 |
Neg logit contributions | |
a | -0.034 |
prise | -0.034 |
e | -0.033 |
w | -0.033 |
uch | -0.032 |
Token | fle |
Token ID | 5104 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
horizon | +0.071 |
der | +0.070 |
Everyone | +0.070 |
Then | +0.067 |
Afterwards | +0.067 |
Neg logit contributions | |
prise | -0.058 |
w | -0.056 |
o | -0.054 |
uch | -0.053 |
asc | -0.053 |
Token | a |
Token ID | 64 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
prise | +0.007 |
seeker | +0.005 |
uch | +0.005 |
w | +0.005 |
asc | +0.004 |
Neg logit contributions | |
der | -0.032 |
Everyone | -0.030 |
ment | -0.030 |
rily | -0.029 |
Everybody | -0.029 |
Token | aces |
Token ID | 2114 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
horizon | +0.091 |
Afterwards | +0.091 |
Everyone | +0.090 |
Everybody | +0.088 |
rily | +0.086 |
Neg logit contributions | |
w | -0.080 |
e | -0.077 |
o | -0.075 |
uch | -0.074 |
a | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
horizon | +0.050 |
Afterwards | +0.049 |
Everyone | +0.049 |
der | +0.049 |
Everybody | +0.048 |
Neg logit contributions | |
w | -0.044 |
o | -0.042 |
a | -0.042 |
prise | -0.042 |
uch | -0.042 |
Token | grape |
Token ID | 30777 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
Everyone | +0.135 |
Afterwards | +0.135 |
horizon | +0.134 |
der | +0.134 |
Everybody | +0.132 |
Neg logit contributions | |
w | -0.124 |
e | -0.124 |
o | -0.123 |
prise | -0.119 |
a | -0.118 |
Token | brace |
Token ID | 22581 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
der | +0.072 |
horizon | +0.071 |
Everyone | +0.070 |
Afterwards | +0.068 |
int | +0.067 |
Neg logit contributions | |
prise | -0.066 |
w | -0.063 |
uch | -0.062 |
e | -0.060 |
o | -0.060 |
Token | lets |
Token ID | 5289 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
w | +0.019 |
prise | +0.019 |
e | +0.018 |
a | +0.018 |
o | +0.018 |
Neg logit contributions | |
horizon | -0.020 |
der | -0.019 |
Everyone | -0.019 |
Afterwards | -0.019 |
Everybody | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -7.01e+00 |
Pos logit contributions | |
horizon | +0.037 |
der | +0.036 |
Everyone | +0.036 |
Afterwards | +0.036 |
Everybody | +0.035 |
Neg logit contributions | |
w | -0.032 |
prise | -0.032 |
e | -0.030 |
o | -0.030 |
a | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
Afterwards | +0.177 |
Everyone | +0.173 |
der | +0.171 |
horizon | +0.170 |
Everybody | +0.170 |
Neg logit contributions | |
e | -0.144 |
w | -0.143 |
a | -0.138 |
prise | -0.136 |
o | -0.135 |
Token | grape |
Token ID | 30777 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
horizon | +0.167 |
der | +0.159 |
rily | +0.158 |
Afterwards | +0.156 |
int | +0.153 |
Neg logit contributions | |
e | -0.134 |
prise | -0.133 |
w | -0.133 |
a | -0.131 |
o | -0.130 |
Token | crown |
Token ID | 12389 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
der | +0.069 |
horizon | +0.069 |
Everyone | +0.067 |
Afterwards | +0.066 |
rily | +0.065 |
Neg logit contributions | |
prise | -0.070 |
w | -0.069 |
uch | -0.066 |
o | -0.065 |
e | -0.065 |
Token | s |
Token ID | 82 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
horizon | +0.044 |
der | +0.043 |
Afterwards | +0.043 |
Everyone | +0.042 |
int | +0.041 |
Neg logit contributions | |
w | -0.046 |
prise | -0.045 |
o | -0.043 |
a | -0.043 |
uch | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
horizon | +0.071 |
der | +0.071 |
Everyone | +0.069 |
Afterwards | +0.069 |
rily | +0.068 |
Neg logit contributions | |
prise | -0.067 |
w | -0.066 |
uch | -0.063 |
e | -0.062 |
o | -0.062 |
Token | ' |
Token ID | 705 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
lights | +0.108 |
horizon | +0.096 |
rily | +0.095 |
rier | +0.094 |
bread | +0.093 |
Neg logit contributions | |
o | -0.162 |
a | -0.146 |
e | -0.130 |
ee | -0.130 |
ow | -0.125 |
Token | Wow |
Token ID | 22017 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
prise | +0.023 |
w | +0.023 |
e | +0.022 |
o | +0.022 |
a | +0.022 |
Neg logit contributions | |
der | -0.021 |
horizon | -0.021 |
rily | -0.020 |
Everyone | -0.020 |
Afterwards | -0.020 |
Token | !' |
Token ID | 13679 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
prise | +0.008 |
w | +0.008 |
uch | +0.008 |
o | +0.007 |
e | +0.007 |
Neg logit contributions | |
der | -0.011 |
Everyone | -0.011 |
horizon | -0.010 |
Afterwards | -0.010 |
rily | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
lights | +0.114 |
horizon | +0.114 |
der | +0.106 |
Afterwards | +0.104 |
rily | +0.102 |
Neg logit contributions | |
a | -0.118 |
e | -0.115 |
w | -0.112 |
o | -0.110 |
prise | -0.105 |
Token | said |
Token ID | 531 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
horizon | +0.043 |
der | +0.042 |
rily | +0.041 |
Afterwards | +0.040 |
rier | +0.040 |
Neg logit contributions | |
w | -0.032 |
prise | -0.032 |
a | -0.032 |
o | -0.031 |
e | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
horizon | +0.094 |
Afterwards | +0.089 |
lights | +0.088 |
der | +0.087 |
After | +0.082 |
Neg logit contributions | |
e | -0.057 |
a | -0.057 |
prise | -0.052 |
w | -0.050 |
o | -0.048 |
Token | ' |
Token ID | 705 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
lights | +0.132 |
horizon | +0.115 |
der | +0.108 |
ment | +0.102 |
rily | +0.096 |
Neg logit contributions | |
o | -0.191 |
a | -0.189 |
e | -0.181 |
prise | -0.168 |
ee | -0.165 |
Token | That |
Token ID | 2504 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
prise | +0.011 |
w | +0.011 |
e | +0.010 |
o | +0.010 |
a | +0.010 |
Neg logit contributions | |
der | -0.010 |
horizon | -0.009 |
rily | -0.009 |
Afterwards | -0.009 |
Everyone | -0.009 |
Token | 's |
Token ID | 338 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
der | +0.055 |
rily | +0.054 |
horizon | +0.054 |
Afterwards | +0.054 |
Everyone | +0.053 |
Neg logit contributions | |
w | -0.036 |
prise | -0.035 |
a | -0.034 |
uch | -0.034 |
o | -0.033 |
Token | so |
Token ID | 523 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
prise | +0.015 |
w | +0.015 |
e | +0.014 |
a | +0.014 |
uch | +0.014 |
Neg logit contributions | |
der | -0.017 |
horizon | -0.017 |
Everyone | -0.017 |
rily | -0.016 |
Afterwards | -0.016 |
Token | cool |
Token ID | 3608 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
der | +0.039 |
horizon | +0.039 |
rily | +0.038 |
Afterwards | +0.037 |
ment | +0.037 |
Neg logit contributions | |
prise | -0.027 |
w | -0.026 |
a | -0.025 |
o | -0.025 |
e | -0.025 |
Token | one |
Token ID | 530 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
prise | +0.171 |
w | +0.162 |
uch | +0.161 |
seeker | +0.157 |
asc | +0.154 |
Neg logit contributions | |
der | -0.096 |
Everyone | -0.095 |
Then | -0.093 |
int | -0.090 |
horizon | -0.090 |
Token | of |
Token ID | 286 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
horizon | +0.112 |
der | +0.111 |
Everyone | +0.109 |
Afterwards | +0.109 |
rily | +0.107 |
Neg logit contributions | |
prise | -0.106 |
w | -0.105 |
uch | -0.099 |
o | -0.099 |
a | -0.099 |
Token | them |
Token ID | 606 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
horizon | +0.075 |
der | +0.074 |
Afterwards | +0.072 |
Everyone | +0.071 |
rily | +0.070 |
Neg logit contributions | |
prise | -0.097 |
w | -0.096 |
e | -0.093 |
a | -0.092 |
o | -0.091 |
Token | and |
Token ID | 290 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
horizon | +0.091 |
der | +0.091 |
Everyone | +0.089 |
Afterwards | +0.088 |
int | +0.086 |
Neg logit contributions | |
prise | -0.079 |
w | -0.078 |
uch | -0.074 |
e | -0.073 |
o | -0.073 |
Token | grinned |
Token ID | 36268 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
horizon | +0.114 |
der | +0.112 |
Afterwards | +0.110 |
Everyone | +0.109 |
rily | +0.108 |
Neg logit contributions | |
prise | -0.123 |
w | -0.121 |
e | -0.118 |
a | -0.117 |
o | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
horizon | +0.058 |
Afterwards | +0.057 |
der | +0.056 |
Everyone | +0.055 |
After | +0.054 |
Neg logit contributions | |
a | -0.042 |
e | -0.041 |
o | -0.041 |
prise | -0.039 |
w | -0.037 |
Token | It |
Token ID | 632 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
horizon | +0.120 |
rier | +0.116 |
der | +0.115 |
rily | +0.110 |
ment | +0.108 |
Neg logit contributions | |
o | -0.211 |
a | -0.194 |
e | -0.189 |
prise | -0.189 |
w | -0.178 |
Token | tasted |
Token ID | 29187 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
horizon | +0.074 |
der | +0.073 |
Everyone | +0.072 |
Afterwards | +0.072 |
rily | +0.071 |
Neg logit contributions | |
prise | -0.059 |
w | -0.058 |
a | -0.056 |
o | -0.056 |
e | -0.056 |
Token | so |
Token ID | 523 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
horizon | +0.034 |
der | +0.033 |
Afterwards | +0.033 |
Everyone | +0.033 |
Everybody | +0.032 |
Neg logit contributions | |
prise | -0.026 |
w | -0.026 |
a | -0.025 |
e | -0.025 |
uch | -0.024 |
Token | good |
Token ID | 922 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
horizon | +0.084 |
der | +0.080 |
Afterwards | +0.080 |
rily | +0.079 |
Everyone | +0.078 |
Neg logit contributions | |
prise | -0.051 |
w | -0.050 |
a | -0.048 |
uch | -0.046 |
e | -0.045 |
Token | ! |
Token ID | 0 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
horizon | +0.042 |
der | +0.041 |
Everyone | +0.041 |
Afterwards | +0.041 |
rily | +0.040 |
Neg logit contributions | |
prise | -0.031 |
w | -0.030 |
o | -0.028 |
e | -0.028 |
uch | -0.028 |
Token | " |
Token ID | 1 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
horizon | +0.058 |
der | +0.058 |
Afterwards | +0.057 |
Everyone | +0.056 |
int | +0.055 |
Neg logit contributions | |
prise | -0.069 |
w | -0.069 |
uch | -0.066 |
a | -0.066 |
o | -0.066 |
Token | sign |
Token ID | 1051 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
der | +0.106 |
horizon | +0.105 |
rily | +0.105 |
Afterwards | +0.104 |
Everyone | +0.100 |
Neg logit contributions | |
o | -0.086 |
w | -0.084 |
a | -0.081 |
prise | -0.077 |
uch | -0.077 |
Token | on |
Token ID | 319 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
horizon | +0.116 |
Afterwards | +0.114 |
der | +0.112 |
rily | +0.112 |
Everyone | +0.108 |
Neg logit contributions | |
w | -0.105 |
prise | -0.104 |
a | -0.104 |
o | -0.103 |
e | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
horizon | +0.091 |
der | +0.090 |
Afterwards | +0.090 |
rily | +0.085 |
Everyone | +0.085 |
Neg logit contributions | |
e | -0.123 |
w | -0.122 |
a | -0.119 |
prise | -0.119 |
o | -0.118 |
Token | wall |
Token ID | 3355 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
horizon | +0.124 |
der | +0.123 |
Everyone | +0.121 |
Afterwards | +0.119 |
rily | +0.117 |
Neg logit contributions | |
prise | -0.129 |
w | -0.126 |
uch | -0.121 |
o | -0.120 |
e | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
horizon | +0.116 |
Afterwards | +0.114 |
der | +0.113 |
Everyone | +0.112 |
rily | +0.111 |
Neg logit contributions | |
prise | -0.094 |
a | -0.091 |
e | -0.091 |
w | -0.091 |
o | -0.091 |
Token | He |
Token ID | 679 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
rily | +0.136 |
rier | +0.135 |
horizon | +0.134 |
der | +0.131 |
lights | +0.123 |
Neg logit contributions | |
o | -0.202 |
e | -0.170 |
prise | -0.166 |
a | -0.165 |
itty | -0.157 |
Token | looked |
Token ID | 3114 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
horizon | +0.079 |
der | +0.078 |
Everyone | +0.077 |
Afterwards | +0.076 |
rily | +0.075 |
Neg logit contributions | |
prise | -0.067 |
w | -0.066 |
uch | -0.063 |
o | -0.062 |
e | -0.062 |
Token | around |
Token ID | 1088 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
horizon | +0.002 |
der | +0.002 |
Afterwards | +0.002 |
Everyone | +0.002 |
ment | +0.002 |
Neg logit contributions | |
prise | -0.001 |
a | -0.001 |
w | -0.001 |
o | -0.001 |
e | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Afterwards | +0.093 |
der | +0.092 |
Everyone | +0.091 |
horizon | +0.091 |
Everybody | +0.090 |
Neg logit contributions | |
prise | -0.062 |
e | -0.061 |
w | -0.059 |
a | -0.058 |
o | -0.058 |
Token | store |
Token ID | 3650 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
horizon | +0.052 |
Everyone | +0.050 |
der | +0.048 |
Everybody | +0.048 |
Afterwards | +0.047 |
Neg logit contributions | |
prise | -0.051 |
w | -0.051 |
o | -0.049 |
uch | -0.049 |
a | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
horizon | +0.052 |
der | +0.052 |
Afterwards | +0.052 |
Everyone | +0.051 |
rily | +0.050 |
Neg logit contributions | |
prise | -0.040 |
w | -0.039 |
o | -0.037 |
a | -0.037 |
e | -0.037 |
Token | cl |
Token ID | 537 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
der | +0.085 |
horizon | +0.082 |
rily | +0.080 |
Afterwards | +0.079 |
ment | +0.078 |
Neg logit contributions | |
prise | -0.071 |
a | -0.069 |
o | -0.068 |
w | -0.067 |
e | -0.066 |
Token | apped |
Token ID | 6320 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
prise | +0.007 |
w | +0.007 |
uch | +0.007 |
e | +0.007 |
o | +0.007 |
Neg logit contributions | |
horizon | -0.008 |
der | -0.008 |
Everyone | -0.008 |
Afterwards | -0.008 |
rily | -0.008 |
Token | even |
Token ID | 772 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
horizon | +0.087 |
der | +0.085 |
Afterwards | +0.085 |
Everyone | +0.082 |
After | +0.080 |
Neg logit contributions | |
prise | -0.074 |
a | -0.074 |
e | -0.073 |
w | -0.073 |
o | -0.071 |
Token | louder |
Token ID | 27089 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
der | +0.031 |
Everyone | +0.031 |
horizon | +0.030 |
Afterwards | +0.030 |
Everybody | +0.029 |
Neg logit contributions | |
a | -0.035 |
prise | -0.034 |
e | -0.032 |
w | -0.032 |
o | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
Afterwards | +0.094 |
horizon | +0.091 |
Everyone | +0.091 |
Everybody | +0.089 |
rily | +0.088 |
Neg logit contributions | |
e | -0.065 |
a | -0.064 |
w | -0.063 |
prise | -0.061 |
o | -0.060 |
Token | Now |
Token ID | 2735 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
rily | +0.102 |
rier | +0.101 |
der | +0.100 |
ment | +0.097 |
horizon | +0.096 |
Neg logit contributions | |
o | -0.220 |
e | -0.208 |
a | -0.205 |
prise | -0.203 |
w | -0.192 |
Token | it |
Token ID | 340 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
horizon | +0.058 |
der | +0.056 |
Afterwards | +0.055 |
rily | +0.054 |
Everyone | +0.052 |
Neg logit contributions | |
prise | -0.077 |
w | -0.076 |
a | -0.075 |
e | -0.075 |
o | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
horizon | +0.044 |
der | +0.043 |
Everyone | +0.043 |
Afterwards | +0.042 |
rily | +0.042 |
Neg logit contributions | |
prise | -0.039 |
w | -0.038 |
uch | -0.036 |
e | -0.036 |
o | -0.036 |
Token | time |
Token ID | 640 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
prise | +0.008 |
w | +0.008 |
e | +0.008 |
o | +0.008 |
a | +0.008 |
Neg logit contributions | |
der | -0.009 |
horizon | -0.009 |
Everyone | -0.009 |
rily | -0.009 |
Afterwards | -0.009 |
Token | for |
Token ID | 329 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
prise | +0.002 |
w | +0.002 |
o | +0.002 |
a | +0.002 |
uch | +0.002 |
Neg logit contributions | |
horizon | -0.002 |
der | -0.002 |
Everyone | -0.002 |
Afterwards | -0.002 |
rily | -0.002 |
Token | en |
Token ID | 268 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
der | +0.010 |
horizon | +0.010 |
Everyone | +0.010 |
Afterwards | +0.010 |
rily | +0.010 |
Neg logit contributions | |
prise | -0.009 |
w | -0.009 |
uch | -0.008 |
e | -0.008 |
o | -0.008 |
Token | ug |
Token ID | 1018 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
horizon | +0.117 |
der | +0.116 |
Everyone | +0.113 |
Afterwards | +0.113 |
rily | +0.110 |
Neg logit contributions | |
prise | -0.118 |
w | -0.117 |
e | -0.112 |
uch | -0.111 |
o | -0.111 |
Token | reek |
Token ID | 10316 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
horizon | +0.048 |
der | +0.047 |
Afterwards | +0.046 |
Everyone | +0.046 |
rily | +0.045 |
Neg logit contributions | |
w | -0.045 |
prise | -0.044 |
e | -0.044 |
a | -0.043 |
o | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
horizon | +0.093 |
der | +0.093 |
Afterwards | +0.091 |
Everyone | +0.091 |
rily | +0.089 |
Neg logit contributions | |
prise | -0.090 |
w | -0.089 |
e | -0.085 |
uch | -0.085 |
o | -0.085 |
Token | mustard |
Token ID | 33694 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
horizon | +0.149 |
der | +0.148 |
Everyone | +0.145 |
Afterwards | +0.145 |
rily | +0.144 |
Neg logit contributions | |
prise | -0.148 |
w | -0.148 |
e | -0.143 |
a | -0.140 |
o | -0.140 |
Token | and |
Token ID | 290 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
horizon | +0.044 |
der | +0.044 |
Everyone | +0.043 |
Afterwards | +0.043 |
rily | +0.042 |
Neg logit contributions | |
prise | -0.037 |
w | -0.036 |
uch | -0.034 |
o | -0.034 |
e | -0.034 |
Token | hors |
Token ID | 45334 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
horizon | +0.157 |
der | +0.154 |
Everyone | +0.152 |
Afterwards | +0.152 |
rily | +0.151 |
Neg logit contributions | |
w | -0.164 |
prise | -0.163 |
e | -0.159 |
a | -0.155 |
o | -0.155 |
Token | er |
Token ID | 263 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
horizon | +0.035 |
der | +0.033 |
Afterwards | +0.033 |
Everyone | +0.032 |
Then | +0.031 |
Neg logit contributions | |
w | -0.034 |
a | -0.034 |
o | -0.034 |
e | -0.033 |
uch | -0.031 |
Token | adish |
Token ID | 48563 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
horizon | +0.091 |
der | +0.089 |
Afterwards | +0.088 |
Everyone | +0.087 |
rily | +0.086 |
Neg logit contributions | |
w | -0.081 |
prise | -0.080 |
o | -0.078 |
e | -0.078 |
a | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
horizon | +0.116 |
der | +0.114 |
Afterwards | +0.112 |
Everyone | +0.112 |
rily | +0.111 |
Neg logit contributions | |
w | -0.104 |
prise | -0.104 |
e | -0.099 |
o | -0.099 |
uch | -0.099 |
Token | was |
Token ID | 373 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
horizon | +0.153 |
der | +0.149 |
Afterwards | +0.148 |
Everyone | +0.148 |
rily | +0.147 |
Neg logit contributions | |
w | -0.155 |
prise | -0.155 |
e | -0.151 |
a | -0.148 |
o | -0.146 |
Token | pouring |
Token ID | 23147 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
horizon | +0.047 |
der | +0.047 |
Everyone | +0.046 |
Afterwards | +0.045 |
rily | +0.044 |
Neg logit contributions | |
prise | -0.050 |
w | -0.049 |
uch | -0.047 |
e | -0.046 |
o | -0.046 |
Token | out |
Token ID | 503 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
Everyone | +0.057 |
der | +0.057 |
Afterwards | +0.056 |
horizon | +0.056 |
Everybody | +0.055 |
Neg logit contributions | |
w | -0.064 |
prise | -0.063 |
o | -0.062 |
e | -0.061 |
a | -0.060 |
Token | of |
Token ID | 286 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
horizon | +0.091 |
der | +0.089 |
Afterwards | +0.089 |
Everyone | +0.088 |
Everybody | +0.085 |
Neg logit contributions | |
prise | -0.094 |
w | -0.091 |
e | -0.089 |
a | -0.088 |
o | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
der | +0.059 |
Everyone | +0.057 |
Afterwards | +0.056 |
Everybody | +0.056 |
horizon | +0.055 |
Neg logit contributions | |
prise | -0.072 |
e | -0.069 |
w | -0.069 |
o | -0.065 |
hiding | -0.064 |
Token | cane |
Token ID | 33009 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
horizon | +0.075 |
der | +0.070 |
Everyone | +0.069 |
rily | +0.067 |
Afterwards | +0.067 |
Neg logit contributions | |
prise | -0.081 |
w | -0.081 |
o | -0.078 |
uch | -0.077 |
e | -0.076 |
Token | ! |
Token ID | 0 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
horizon | +0.058 |
der | +0.058 |
Everyone | +0.056 |
Afterwards | +0.056 |
rily | +0.055 |
Neg logit contributions | |
prise | -0.061 |
w | -0.060 |
uch | -0.057 |
e | -0.057 |
o | -0.056 |
Token | The |
Token ID | 383 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
horizon | +0.120 |
der | +0.119 |
rier | +0.114 |
rily | +0.113 |
ment | +0.111 |
Neg logit contributions | |
o | -0.209 |
e | -0.193 |
a | -0.188 |
prise | -0.187 |
w | -0.181 |
Token | little |
Token ID | 1310 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
horizon | +0.103 |
der | +0.102 |
Everyone | +0.099 |
Afterwards | +0.097 |
int | +0.096 |
Neg logit contributions | |
prise | -0.121 |
w | -0.119 |
uch | -0.115 |
o | -0.114 |
e | -0.113 |
Token | boy |
Token ID | 2933 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
horizon | +0.106 |
der | +0.104 |
Everyone | +0.101 |
rily | +0.099 |
Afterwards | +0.098 |
Neg logit contributions | |
prise | -0.136 |
w | -0.133 |
uch | -0.130 |
o | -0.126 |
e | -0.126 |
Token | was |
Token ID | 373 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
der | +0.019 |
horizon | +0.019 |
Everyone | +0.019 |
Afterwards | +0.019 |
int | +0.019 |
Neg logit contributions | |
prise | -0.021 |
w | -0.020 |
uch | -0.019 |
asc | -0.019 |
seeker | -0.019 |
Token | so |
Token ID | 523 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
w | +0.067 |
prise | +0.066 |
uch | +0.063 |
o | +0.060 |
asc | +0.059 |
Neg logit contributions | |
horizon | -0.061 |
der | -0.060 |
Everyone | -0.060 |
Afterwards | -0.060 |
int | -0.059 |
Token | feel |
Token ID | 1254 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
horizon | +0.018 |
der | +0.018 |
Everyone | +0.017 |
Afterwards | +0.017 |
rily | +0.017 |
Neg logit contributions | |
prise | -0.016 |
w | -0.015 |
uch | -0.015 |
e | -0.014 |
o | -0.014 |
Token | very |
Token ID | 845 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
horizon | +0.028 |
der | +0.027 |
rily | +0.027 |
Afterwards | +0.027 |
Everyone | +0.027 |
Neg logit contributions | |
prise | -0.022 |
w | -0.022 |
e | -0.021 |
a | -0.021 |
uch | -0.020 |
Token | puzzled |
Token ID | 36907 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
horizon | +0.007 |
der | +0.007 |
Afterwards | +0.007 |
Everyone | +0.007 |
rily | +0.007 |
Neg logit contributions | |
prise | -0.004 |
w | -0.004 |
a | -0.004 |
uch | -0.004 |
e | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
horizon | +0.076 |
Afterwards | +0.075 |
Everyone | +0.074 |
der | +0.073 |
Everybody | +0.072 |
Neg logit contributions | |
prise | -0.059 |
w | -0.058 |
e | -0.057 |
a | -0.056 |
o | -0.056 |
Token | confused |
Token ID | 10416 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
horizon | +0.090 |
der | +0.089 |
rily | +0.089 |
Everyone | +0.086 |
rier | +0.086 |
Neg logit contributions | |
prise | -0.072 |
w | -0.070 |
a | -0.070 |
o | -0.069 |
e | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
horizon | +0.095 |
Afterwards | +0.093 |
Everyone | +0.089 |
rily | +0.089 |
Everybody | +0.088 |
Neg logit contributions | |
prise | -0.065 |
w | -0.065 |
a | -0.064 |
e | -0.064 |
o | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
rier | +0.115 |
rily | +0.114 |
horizon | +0.112 |
der | +0.109 |
ment | +0.107 |
Neg logit contributions | |
o | -0.204 |
a | -0.188 |
e | -0.188 |
prise | -0.187 |
w | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
der | +0.055 |
horizon | +0.055 |
rily | +0.053 |
rier | +0.053 |
ment | +0.048 |
Neg logit contributions | |
prise | -0.088 |
o | -0.087 |
a | -0.086 |
e | -0.084 |
w | -0.084 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
horizon | +0.042 |
der | +0.042 |
rily | +0.040 |
Everyone | +0.040 |
Afterwards | +0.040 |
Neg logit contributions | |
prise | -0.056 |
w | -0.055 |
e | -0.053 |
o | -0.053 |
a | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
horizon | +0.099 |
der | +0.099 |
Everyone | +0.097 |
Afterwards | +0.096 |
rily | +0.095 |
Neg logit contributions | |
prise | -0.076 |
w | -0.074 |
uch | -0.070 |
e | -0.070 |
o | -0.070 |
Token | from |
Token ID | 422 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
horizon | +0.084 |
der | +0.083 |
Afterwards | +0.080 |
rily | +0.079 |
Everyone | +0.079 |
Neg logit contributions | |
prise | -0.110 |
w | -0.108 |
a | -0.104 |
e | -0.103 |
o | -0.103 |
Token | 4 |
Token ID | 604 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
horizon | +0.087 |
der | +0.087 |
Afterwards | +0.083 |
Everyone | +0.083 |
rily | +0.083 |
Neg logit contributions | |
prise | -0.094 |
w | -0.092 |
o | -0.090 |
a | -0.090 |
e | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
der | +0.066 |
horizon | +0.066 |
Everyone | +0.065 |
Afterwards | +0.064 |
int | +0.063 |
Neg logit contributions | |
prise | -0.048 |
w | -0.047 |
uch | -0.044 |
o | -0.044 |
e | -0.043 |
Token | 5 |
Token ID | 642 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
horizon | +0.104 |
der | +0.104 |
Afterwards | +0.100 |
rily | +0.100 |
Everyone | +0.099 |
Neg logit contributions | |
prise | -0.113 |
w | -0.110 |
e | -0.107 |
a | -0.107 |
o | -0.107 |
Token | , |
Token ID | 11 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
horizon | +0.087 |
der | +0.087 |
Everyone | +0.085 |
Afterwards | +0.084 |
rily | +0.083 |
Neg logit contributions | |
prise | -0.072 |
w | -0.071 |
uch | -0.068 |
e | -0.067 |
o | -0.067 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
horizon | +0.124 |
der | +0.123 |
Afterwards | +0.120 |
rily | +0.119 |
Everyone | +0.118 |
Neg logit contributions | |
prise | -0.125 |
w | -0.122 |
e | -0.119 |
a | -0.119 |
o | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
horizon | +0.107 |
der | +0.104 |
Afterwards | +0.103 |
rily | +0.103 |
Everyone | +0.102 |
Neg logit contributions | |
prise | -0.070 |
w | -0.069 |
e | -0.068 |
a | -0.067 |
o | -0.065 |
Token | Mia |
Token ID | 32189 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
rily | +0.109 |
der | +0.109 |
horizon | +0.108 |
rier | +0.106 |
ment | +0.104 |
Neg logit contributions | |
o | -0.214 |
e | -0.207 |
a | -0.203 |
prise | -0.200 |
w | -0.188 |
Token | picked |
Token ID | 6497 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
der | +0.040 |
horizon | +0.040 |
Everyone | +0.040 |
Afterwards | +0.039 |
int | +0.039 |
Neg logit contributions | |
prise | -0.039 |
w | -0.037 |
uch | -0.036 |
o | -0.035 |
asc | -0.034 |
Token | out |
Token ID | 503 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
horizon | +0.060 |
der | +0.059 |
Afterwards | +0.057 |
lights | +0.055 |
ment | +0.054 |
Neg logit contributions | |
w | -0.059 |
a | -0.059 |
prise | -0.058 |
e | -0.058 |
o | -0.056 |
Token | her |
Token ID | 607 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
horizon | +0.104 |
der | +0.099 |
Afterwards | +0.098 |
rily | +0.095 |
Everyone | +0.092 |
Neg logit contributions | |
prise | -0.085 |
a | -0.085 |
e | -0.083 |
w | -0.083 |
o | -0.079 |
Token | favorite |
Token ID | 4004 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
der | +0.114 |
horizon | +0.114 |
Afterwards | +0.111 |
Everyone | +0.111 |
rily | +0.108 |
Neg logit contributions | |
prise | -0.123 |
w | -0.120 |
a | -0.117 |
e | -0.116 |
uch | -0.115 |
Token | for |
Token ID | 329 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
horizon | +0.053 |
der | +0.052 |
Everyone | +0.051 |
Afterwards | +0.051 |
int | +0.051 |
Neg logit contributions | |
prise | -0.042 |
w | -0.041 |
uch | -0.040 |
o | -0.039 |
e | -0.039 |
Token | what |
Token ID | 644 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
horizon | +0.047 |
der | +0.047 |
Everyone | +0.045 |
Afterwards | +0.045 |
rily | +0.045 |
Neg logit contributions | |
prise | -0.056 |
w | -0.055 |
e | -0.053 |
uch | -0.053 |
o | -0.052 |
Token | they |
Token ID | 484 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
horizon | +0.079 |
der | +0.079 |
Everyone | +0.077 |
Afterwards | +0.076 |
rily | +0.074 |
Neg logit contributions | |
prise | -0.111 |
w | -0.109 |
uch | -0.106 |
e | -0.104 |
o | -0.104 |
Token | believe |
Token ID | 1975 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
horizon | +0.021 |
der | +0.021 |
Everyone | +0.021 |
Afterwards | +0.020 |
Everybody | +0.020 |
Neg logit contributions | |
prise | -0.018 |
w | -0.018 |
uch | -0.017 |
a | -0.017 |
asc | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
horizon | +0.045 |
Afterwards | +0.044 |
der | +0.044 |
Everyone | +0.043 |
int | +0.042 |
Neg logit contributions | |
prise | -0.036 |
w | -0.035 |
a | -0.033 |
e | -0.033 |
o | -0.033 |
Token | - |
Token ID | 532 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
horizon | +0.045 |
der | +0.045 |
Afterwards | +0.043 |
rily | +0.043 |
Everyone | +0.042 |
Neg logit contributions | |
prise | -0.051 |
w | -0.049 |
e | -0.049 |
a | -0.047 |
uch | -0.046 |
Token | something |
Token ID | 1223 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
horizon | +0.141 |
rily | +0.139 |
der | +0.136 |
Afterwards | +0.134 |
rier | +0.127 |
Neg logit contributions | |
prise | -0.176 |
a | -0.174 |
e | -0.171 |
w | -0.170 |
o | -0.170 |
Token | that |
Token ID | 326 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
horizon | +0.066 |
der | +0.066 |
Everyone | +0.065 |
Afterwards | +0.064 |
rily | +0.063 |
Neg logit contributions | |
prise | -0.064 |
w | -0.063 |
uch | -0.060 |
e | -0.060 |
o | -0.060 |
Token | Gina |
Token ID | 43002 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
horizon | +0.094 |
der | +0.094 |
Afterwards | +0.092 |
rily | +0.091 |
Everyone | +0.091 |
Neg logit contributions | |
prise | -0.086 |
w | -0.085 |
o | -0.081 |
uch | -0.081 |
a | -0.081 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
horizon | +0.042 |
der | +0.042 |
Everyone | +0.041 |
Afterwards | +0.040 |
int | +0.040 |
Neg logit contributions | |
prise | -0.039 |
w | -0.037 |
uch | -0.036 |
o | -0.035 |
asc | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
horizon | +0.048 |
der | +0.048 |
Afterwards | +0.047 |
Everyone | +0.047 |
rily | +0.046 |
Neg logit contributions | |
prise | -0.047 |
w | -0.047 |
e | -0.044 |
uch | -0.044 |
o | -0.044 |
Token | meal |
Token ID | 9799 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
prise | +0.010 |
w | +0.010 |
o | +0.009 |
e | +0.009 |
uch | +0.009 |
Neg logit contributions | |
horizon | -0.012 |
der | -0.012 |
Afterwards | -0.011 |
Everyone | -0.011 |
rily | -0.011 |
Token | together |
Token ID | 1978 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
w | +0.008 |
prise | +0.007 |
uch | +0.007 |
asc | +0.007 |
e | +0.007 |
Neg logit contributions | |
der | -0.007 |
Everyone | -0.006 |
horizon | -0.006 |
ment | -0.006 |
rily | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
prise | +0.019 |
w | +0.019 |
uch | +0.018 |
a | +0.017 |
o | +0.017 |
Neg logit contributions | |
der | -0.016 |
horizon | -0.015 |
Everyone | -0.015 |
Afterwards | -0.015 |
int | -0.015 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
rier | +0.014 |
horizon | +0.013 |
rily | +0.012 |
ment | +0.012 |
current | +0.012 |
Neg logit contributions | |
o | -0.010 |
named | -0.008 |
a | -0.008 |
itty | -0.008 |
uffy | -0.007 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
prise | +0.143 |
w | +0.142 |
o | +0.139 |
e | +0.138 |
uch | +0.137 |
Neg logit contributions | |
der | -0.063 |
horizon | -0.063 |
Afterwards | -0.059 |
rily | -0.058 |
int | -0.058 |
Token | upon |
Token ID | 2402 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
prise | +0.086 |
w | +0.085 |
o | +0.083 |
a | +0.081 |
uch | +0.079 |
Neg logit contributions | |
horizon | -0.140 |
der | -0.140 |
Afterwards | -0.135 |
Everyone | -0.134 |
rily | -0.134 |
Token | a |
Token ID | 257 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
prise | +0.128 |
w | +0.127 |
uch | +0.122 |
o | +0.119 |
a | +0.117 |
Neg logit contributions | |
der | -0.112 |
Everyone | -0.112 |
horizon | -0.111 |
Afterwards | -0.108 |
Then | -0.107 |
Token | time |
Token ID | 640 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
prise | +0.157 |
asc | +0.150 |
w | +0.148 |
uch | +0.138 |
seeker | +0.138 |
Neg logit contributions | |
int | -0.130 |
After | -0.126 |
Afterwards | -0.125 |
Then | -0.124 |
Everyone | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
prise | +0.128 |
w | +0.126 |
asc | +0.121 |
uch | +0.121 |
e | +0.118 |
Neg logit contributions | |
Everyone | -0.109 |
der | -0.105 |
Then | -0.105 |
After | -0.104 |
int | -0.103 |
Token | there |
Token ID | 612 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
prise | +0.079 |
w | +0.074 |
uch | +0.073 |
asc | +0.069 |
e | +0.069 |
Neg logit contributions | |
Then | -0.105 |
After | -0.104 |
Everyone | -0.104 |
Afterwards | -0.101 |
rily | -0.101 |
Token | was |
Token ID | 373 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
prise | +0.139 |
w | +0.133 |
uch | +0.127 |
asc | +0.125 |
a | +0.123 |
Neg logit contributions | |
Everyone | -0.107 |
horizon | -0.103 |
Afterwards | -0.103 |
der | -0.102 |
Then | -0.101 |
Token | until |
Token ID | 1566 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
prise | +0.021 |
w | +0.021 |
e | +0.021 |
o | +0.020 |
uch | +0.020 |
Neg logit contributions | |
horizon | -0.021 |
der | -0.021 |
Afterwards | -0.021 |
Everyone | -0.021 |
rily | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
rily | +0.003 |
der | +0.003 |
rier | +0.003 |
int | +0.003 |
Everybody | +0.003 |
Neg logit contributions | |
w | -0.003 |
prise | -0.003 |
uch | -0.003 |
seeker | -0.002 |
o | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
w | +0.011 |
uch | +0.010 |
o | +0.010 |
a | +0.010 |
prise | +0.010 |
Neg logit contributions | |
der | -0.015 |
horizon | -0.015 |
rily | -0.014 |
Everyone | -0.014 |
Afterwards | -0.014 |
Token | over |
Token ID | 625 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
prise | +0.094 |
w | +0.092 |
uch | +0.088 |
e | +0.087 |
o | +0.086 |
Neg logit contributions | |
horizon | -0.126 |
der | -0.124 |
Afterwards | -0.122 |
Everyone | -0.122 |
int | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
prise | +0.037 |
w | +0.037 |
o | +0.036 |
e | +0.035 |
uch | +0.034 |
Neg logit contributions | |
der | -0.051 |
Everyone | -0.051 |
rily | -0.051 |
Everybody | -0.050 |
Afterwards | -0.050 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
rier | +0.026 |
rily | +0.024 |
horizon | +0.024 |
int | +0.022 |
der | +0.022 |
Neg logit contributions | |
o | -0.029 |
w | -0.023 |
uch | -0.023 |
asc | -0.023 |
named | -0.022 |
Token | Once |
Token ID | 7454 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
prise | +0.215 |
w | +0.212 |
uch | +0.206 |
e | +0.203 |
a | +0.202 |
Neg logit contributions | |
horizon | -0.074 |
der | -0.072 |
Everyone | -0.072 |
Afterwards | -0.069 |
rily | -0.066 |
Token | upon |
Token ID | 2402 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
prise | +0.119 |
w | +0.118 |
uch | +0.112 |
o | +0.111 |
e | +0.110 |
Neg logit contributions | |
horizon | -0.153 |
der | -0.152 |
Everyone | -0.149 |
Afterwards | -0.148 |
rily | -0.146 |
Token | a |
Token ID | 257 |
Feature activation | +6.76e+00 |
Pos logit contributions | |
prise | +0.153 |
w | +0.150 |
uch | +0.145 |
o | +0.140 |
a | +0.140 |
Neg logit contributions | |
Everyone | -0.129 |
der | -0.128 |
horizon | -0.126 |
Then | -0.123 |
Afterwards | -0.123 |
Token | time |
Token ID | 640 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
prise | +0.171 |
asc | +0.163 |
w | +0.159 |
seeker | +0.152 |
uch | +0.150 |
Neg logit contributions | |
int | -0.135 |
After | -0.132 |
Then | -0.131 |
Everyone | -0.130 |
der | -0.129 |
Token | , |
Token ID | 11 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
prise | +0.145 |
w | +0.140 |
asc | +0.134 |
uch | +0.133 |
e | +0.131 |
Neg logit contributions | |
Everyone | -0.113 |
Then | -0.110 |
der | -0.108 |
After | -0.106 |
int | -0.103 |
Token | way |
Token ID | 835 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
horizon | +0.040 |
der | +0.039 |
Everyone | +0.038 |
Afterwards | +0.038 |
rily | +0.037 |
Neg logit contributions | |
prise | -0.048 |
w | -0.047 |
uch | -0.045 |
o | -0.045 |
e | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
der | +0.002 |
horizon | +0.002 |
Afterwards | +0.002 |
Everyone | +0.002 |
rily | +0.002 |
Neg logit contributions | |
prise | -0.002 |
w | -0.002 |
o | -0.001 |
a | -0.001 |
e | -0.001 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
rier | +0.010 |
horizon | +0.009 |
rily | +0.009 |
int | +0.008 |
der | +0.008 |
Neg logit contributions | |
o | -0.010 |
prise | -0.008 |
w | -0.008 |
a | -0.008 |
uffy | -0.008 |
Token | Once |
Token ID | 7454 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
prise | +0.206 |
w | +0.204 |
uch | +0.198 |
o | +0.198 |
e | +0.198 |
Neg logit contributions | |
horizon | -0.083 |
der | -0.082 |
Everyone | -0.078 |
Afterwards | -0.077 |
rily | -0.076 |
Token | upon |
Token ID | 2402 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
prise | +0.106 |
w | +0.105 |
o | +0.101 |
uch | +0.099 |
a | +0.099 |
Neg logit contributions | |
horizon | -0.152 |
der | -0.151 |
Afterwards | -0.147 |
Everyone | -0.146 |
rily | -0.145 |
Token | a |
Token ID | 257 |
Feature activation | +6.71e+00 |
Pos logit contributions | |
prise | +0.156 |
w | +0.153 |
uch | +0.147 |
o | +0.143 |
a | +0.142 |
Neg logit contributions | |
Everyone | -0.133 |
der | -0.132 |
horizon | -0.130 |
Then | -0.127 |
Afterwards | -0.127 |
Token | time |
Token ID | 640 |
Feature activation | +6.03e+00 |
Pos logit contributions | |
prise | +0.174 |
asc | +0.169 |
w | +0.162 |
seeker | +0.154 |
o | +0.152 |
Neg logit contributions | |
int | -0.127 |
Then | -0.126 |
After | -0.125 |
But | -0.125 |
Everyone | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
prise | +0.156 |
w | +0.151 |
asc | +0.149 |
a | +0.143 |
uch | +0.142 |
Neg logit contributions | |
Everyone | -0.117 |
Then | -0.114 |
After | -0.111 |
der | -0.111 |
int | -0.107 |
Token | in |
Token ID | 287 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
prise | +0.099 |
w | +0.090 |
uch | +0.089 |
asc | +0.088 |
e | +0.087 |
Neg logit contributions | |
Then | -0.128 |
After | -0.126 |
Everyone | -0.123 |
der | -0.122 |
Afterwards | -0.122 |
Token | a |
Token ID | 257 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
prise | +0.073 |
w | +0.072 |
uch | +0.069 |
o | +0.068 |
e | +0.067 |
Neg logit contributions | |
horizon | -0.068 |
der | -0.068 |
Everyone | -0.067 |
Afterwards | -0.066 |
rily | -0.065 |
Token | small |
Token ID | 1402 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
prise | +0.166 |
w | +0.165 |
uch | +0.160 |
asc | +0.160 |
o | +0.150 |
Neg logit contributions | |
horizon | -0.103 |
Then | -0.103 |
Everyone | -0.102 |
After | -0.101 |
Afterwards | -0.098 |
Token | mail |
Token ID | 6920 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
der | +0.030 |
rily | +0.029 |
Afterwards | +0.029 |
Everyone | +0.028 |
horizon | +0.028 |
Neg logit contributions | |
prise | -0.022 |
w | -0.022 |
uch | -0.021 |
e | -0.021 |
a | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
horizon | +0.002 |
der | +0.002 |
Everyone | +0.002 |
Afterwards | +0.002 |
int | +0.002 |
Neg logit contributions | |
prise | -0.002 |
w | -0.002 |
uch | -0.002 |
o | -0.002 |
e | -0.002 |
Token | but |
Token ID | 475 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
horizon | +0.043 |
der | +0.042 |
Afterwards | +0.042 |
Everyone | +0.041 |
rily | +0.040 |
Neg logit contributions | |
prise | -0.049 |
w | -0.047 |
a | -0.046 |
o | -0.046 |
e | -0.046 |
Token | I |
Token ID | 314 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
prise | +0.012 |
w | +0.011 |
uch | +0.011 |
a | +0.011 |
o | +0.011 |
Neg logit contributions | |
horizon | -0.010 |
der | -0.010 |
Everyone | -0.010 |
Afterwards | -0.010 |
rily | -0.009 |
Token | don |
Token ID | 836 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
prise | +0.086 |
asc | +0.084 |
w | +0.082 |
ymes | +0.079 |
uch | +0.077 |
Neg logit contributions | |
der | -0.091 |
After | -0.090 |
Everyone | -0.089 |
Then | -0.088 |
But | -0.087 |
Token | 't |
Token ID | 470 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
w | +0.099 |
prise | +0.098 |
uch | +0.095 |
e | +0.093 |
o | +0.091 |
Neg logit contributions | |
horizon | -0.142 |
der | -0.141 |
Afterwards | -0.138 |
rily | -0.136 |
Everyone | -0.136 |
Token | know |
Token ID | 760 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
w | +0.140 |
prise | +0.139 |
uch | +0.134 |
o | +0.132 |
asc | +0.129 |
Neg logit contributions | |
Everyone | -0.104 |
horizon | -0.100 |
Everybody | -0.098 |
der | -0.097 |
Afterwards | -0.094 |
Token | who |
Token ID | 508 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
prise | +0.015 |
w | +0.015 |
uch | +0.014 |
e | +0.014 |
a | +0.014 |
Neg logit contributions | |
horizon | -0.013 |
der | -0.013 |
Afterwards | -0.013 |
Everyone | -0.013 |
int | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
Everyone | +0.008 |
der | +0.007 |
horizon | +0.007 |
Afterwards | +0.007 |
Everybody | +0.007 |
Neg logit contributions | |
prise | -0.007 |
w | -0.007 |
uch | -0.007 |
o | -0.007 |
asc | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
prise | +0.021 |
seeker | +0.019 |
w | +0.019 |
asc | +0.019 |
e | +0.018 |
Neg logit contributions | |
der | -0.018 |
Everyone | -0.017 |
Then | -0.017 |
horizon | -0.017 |
int | -0.016 |
Token | from |
Token ID | 422 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
prise | +0.007 |
w | +0.007 |
uch | +0.007 |
o | +0.007 |
e | +0.007 |
Neg logit contributions | |
horizon | -0.008 |
der | -0.008 |
Everyone | -0.008 |
rily | -0.008 |
Afterwards | -0.008 |
Token | boy |
Token ID | 2933 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
uch | +0.082 |
prise | +0.079 |
w | +0.079 |
e | +0.078 |
asc | +0.076 |
Neg logit contributions | |
horizon | -0.025 |
Everyone | -0.023 |
rier | -0.023 |
der | -0.022 |
Then | -0.020 |
Token | named |
Token ID | 3706 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
uch | +0.158 |
prise | +0.156 |
w | +0.149 |
seeker | +0.145 |
ymes | +0.140 |
Neg logit contributions | |
Then | -0.165 |
The | -0.164 |
But | -0.162 |
Everyone | -0.158 |
His | -0.154 |
Token | Alec |
Token ID | 38285 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
prise | +0.040 |
w | +0.040 |
uch | +0.038 |
a | +0.038 |
e | +0.037 |
Neg logit contributions | |
Everyone | -0.029 |
Afterwards | -0.028 |
Then | -0.028 |
horizon | -0.028 |
der | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
prise | +0.148 |
w | +0.142 |
uch | +0.141 |
seeker | +0.138 |
asc | +0.134 |
Neg logit contributions | |
der | -0.099 |
Everyone | -0.096 |
ment | -0.094 |
horizon | -0.093 |
rily | -0.093 |
Token | Alec |
Token ID | 38285 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
der | +0.017 |
rily | +0.017 |
horizon | +0.016 |
rier | +0.016 |
ment | +0.015 |
Neg logit contributions | |
o | -0.032 |
w | -0.031 |
seeker | -0.031 |
e | -0.029 |
uch | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
prise | +0.128 |
seeker | +0.119 |
w | +0.114 |
asc | +0.113 |
uch | +0.112 |
Neg logit contributions | |
Everyone | -0.084 |
Then | -0.084 |
His | -0.077 |
The | -0.076 |
He | -0.074 |
Token | an |
Token ID | 281 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
w | +0.132 |
prise | +0.130 |
uch | +0.120 |
ymes | +0.113 |
a | +0.108 |
Neg logit contributions | |
Then | -0.117 |
Everyone | -0.115 |
After | -0.111 |
The | -0.108 |
int | -0.105 |
Token | eager |
Token ID | 11069 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
w | +0.087 |
prise | +0.087 |
uch | +0.082 |
a | +0.081 |
o | +0.080 |
Neg logit contributions | |
horizon | -0.072 |
Everyone | -0.070 |
der | -0.069 |
int | -0.069 |
rily | -0.067 |
Token | little |
Token ID | 1310 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
prise | +0.005 |
w | +0.004 |
uch | +0.004 |
e | +0.004 |
o | +0.004 |
Neg logit contributions | |
horizon | -0.005 |
der | -0.005 |
Everyone | -0.005 |
Afterwards | -0.004 |
int | -0.004 |
Token | boy |
Token ID | 2933 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
prise | +0.014 |
w | +0.014 |
uch | +0.014 |
e | +0.013 |
asc | +0.013 |
Neg logit contributions | |
der | -0.010 |
horizon | -0.009 |
Everyone | -0.009 |
Then | -0.009 |
int | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
prise | +0.092 |
uch | +0.091 |
w | +0.090 |
asc | +0.078 |
seeker | +0.077 |
Neg logit contributions | |
Then | -0.115 |
Everyone | -0.111 |
But | -0.110 |
After | -0.108 |
der | -0.107 |
Token | box |
Token ID | 3091 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Everyone | +0.010 |
horizon | +0.010 |
der | +0.010 |
Everybody | +0.010 |
Afterwards | +0.009 |
Neg logit contributions | |
prise | -0.011 |
w | -0.011 |
uch | -0.010 |
asc | -0.010 |
e | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
prise | +0.004 |
w | +0.004 |
uch | +0.004 |
seeker | +0.004 |
e | +0.004 |
Neg logit contributions | |
Everyone | -0.005 |
der | -0.005 |
horizon | -0.005 |
Everybody | -0.005 |
rily | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
w | +0.020 |
prise | +0.020 |
uch | +0.019 |
e | +0.018 |
o | +0.018 |
Neg logit contributions | |
horizon | -0.022 |
Everyone | -0.022 |
Afterwards | -0.021 |
der | -0.021 |
Then | -0.021 |
Token | useful |
Token ID | 4465 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Everyone | +0.012 |
horizon | +0.011 |
Afterwards | +0.011 |
int | +0.011 |
Then | +0.011 |
Neg logit contributions | |
w | -0.012 |
e | -0.012 |
uch | -0.012 |
prise | -0.012 |
o | -0.011 |
Token | for |
Token ID | 329 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
der | +0.005 |
Everyone | +0.005 |
horizon | +0.005 |
rily | +0.005 |
Then | +0.005 |
Neg logit contributions | |
prise | -0.007 |
w | -0.007 |
uch | -0.006 |
e | -0.006 |
o | -0.006 |
Token | you |
Token ID | 345 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
horizon | +0.014 |
der | +0.014 |
Everyone | +0.014 |
Afterwards | +0.014 |
rily | +0.014 |
Neg logit contributions | |
prise | -0.008 |
w | -0.008 |
uch | -0.007 |
o | -0.007 |
a | -0.007 |
Token | ." |
Token ID | 526 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
w | +0.018 |
prise | +0.017 |
uch | +0.017 |
asc | +0.016 |
e | +0.016 |
Neg logit contributions | |
der | -0.013 |
horizon | -0.013 |
Everyone | -0.013 |
Afterwards | -0.012 |
int | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
horizon | +0.102 |
rily | +0.101 |
rier | +0.099 |
int | +0.096 |
der | +0.095 |
Neg logit contributions | |
o | -0.108 |
e | -0.092 |
a | -0.086 |
prise | -0.085 |
itty | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
der | +0.017 |
horizon | +0.017 |
rily | +0.016 |
rier | +0.016 |
int | +0.015 |
Neg logit contributions | |
o | -0.021 |
prise | -0.020 |
a | -0.020 |
e | -0.020 |
w | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
horizon | +0.007 |
der | +0.007 |
rily | +0.007 |
Afterwards | +0.007 |
int | +0.007 |
Neg logit contributions | |
prise | -0.011 |
w | -0.011 |
a | -0.011 |
e | -0.011 |
o | -0.011 |
Token | man |
Token ID | 582 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
horizon | +0.051 |
der | +0.051 |
Everyone | +0.050 |
Afterwards | +0.048 |
int | +0.048 |
Neg logit contributions | |
prise | -0.071 |
w | -0.070 |
uch | -0.068 |
o | -0.068 |
e | -0.067 |
Token | 't |
Token ID | 470 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
uch | +0.018 |
e | +0.018 |
w | +0.017 |
prise | +0.017 |
o | +0.017 |
Neg logit contributions | |
horizon | -0.038 |
der | -0.038 |
rily | -0.037 |
ment | -0.037 |
Afterwards | -0.037 |
Token | believe |
Token ID | 1975 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
e | +0.048 |
prise | +0.047 |
a | +0.044 |
uch | +0.043 |
w | +0.042 |
Neg logit contributions | |
Afterwards | -0.073 |
der | -0.071 |
rily | -0.070 |
After | -0.070 |
horizon | -0.069 |
Token | how |
Token ID | 703 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
prise | +0.007 |
w | +0.007 |
e | +0.007 |
a | +0.007 |
o | +0.007 |
Neg logit contributions | |
horizon | -0.008 |
Afterwards | -0.008 |
Everyone | -0.007 |
der | -0.007 |
After | -0.007 |
Token | big |
Token ID | 1263 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
horizon | +0.008 |
der | +0.008 |
Everyone | +0.008 |
Afterwards | +0.008 |
int | +0.008 |
Neg logit contributions | |
prise | -0.007 |
w | -0.007 |
uch | -0.007 |
e | -0.007 |
o | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
der | +0.090 |
horizon | +0.090 |
Afterwards | +0.088 |
Everyone | +0.088 |
rily | +0.085 |
Neg logit contributions | |
prise | -0.133 |
w | -0.132 |
e | -0.127 |
uch | -0.127 |
a | -0.125 |
Token | was |
Token ID | 373 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
horizon | +0.022 |
der | +0.021 |
Everyone | +0.021 |
Afterwards | +0.021 |
int | +0.020 |
Neg logit contributions | |
prise | -0.022 |
w | -0.021 |
uch | -0.020 |
o | -0.020 |
e | -0.020 |
Token | ! |
Token ID | 0 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
prise | +0.020 |
w | +0.020 |
uch | +0.019 |
e | +0.019 |
o | +0.019 |
Neg logit contributions | |
horizon | -0.021 |
der | -0.021 |
Everyone | -0.020 |
Afterwards | -0.020 |
rily | -0.020 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
rier | +0.096 |
der | +0.095 |
horizon | +0.095 |
rily | +0.095 |
lights | +0.091 |
Neg logit contributions | |
o | -0.108 |
prise | -0.101 |
a | -0.100 |
itty | -0.094 |
e | -0.093 |
Token | she |
Token ID | 673 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
horizon | +0.026 |
der | +0.026 |
Everyone | +0.025 |
Afterwards | +0.025 |
rily | +0.025 |
Neg logit contributions | |
prise | -0.042 |
w | -0.042 |
e | -0.040 |
uch | -0.040 |
a | -0.040 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
horizon | +0.001 |
der | +0.001 |
Everyone | +0.001 |
Afterwards | +0.001 |
rily | +0.001 |
Neg logit contributions | |
prise | -0.001 |
w | -0.001 |
uch | -0.001 |
e | -0.001 |
o | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
prise | +0.004 |
w | +0.004 |
uch | +0.004 |
o | +0.004 |
e | +0.004 |
Neg logit contributions | |
horizon | -0.004 |
der | -0.004 |
Everyone | -0.004 |
Afterwards | -0.004 |
int | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
prise | +0.027 |
w | +0.026 |
o | +0.025 |
e | +0.025 |
uch | +0.025 |
Neg logit contributions | |
horizon | -0.028 |
der | -0.028 |
Everyone | -0.027 |
Afterwards | -0.027 |
rily | -0.026 |
Token | At |
Token ID | 1629 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
rier | +0.057 |
der | +0.053 |
rily | +0.052 |
lights | +0.050 |
horizon | +0.048 |
Neg logit contributions | |
o | -0.071 |
e | -0.061 |
a | -0.061 |
seeker | -0.061 |
ow | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
prise | +0.063 |
w | +0.063 |
o | +0.062 |
uch | +0.060 |
seeker | +0.060 |
Neg logit contributions | |
der | -0.052 |
rily | -0.050 |
Everyone | -0.049 |
rier | -0.048 |
ment | -0.048 |
Token | top |
Token ID | 1353 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
prise | +0.007 |
w | +0.007 |
uch | +0.007 |
o | +0.007 |
a | +0.007 |
Neg logit contributions | |
der | -0.008 |
rily | -0.008 |
ment | -0.008 |
Afterwards | -0.008 |
horizon | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
der | +0.008 |
rily | +0.008 |
horizon | +0.008 |
Afterwards | +0.007 |
int | +0.007 |
Neg logit contributions | |
w | -0.006 |
prise | -0.006 |
a | -0.006 |
o | -0.006 |
uch | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
horizon | +0.044 |
der | +0.044 |
Afterwards | +0.043 |
Everyone | +0.042 |
rily | +0.042 |
Neg logit contributions | |
prise | -0.045 |
w | -0.045 |
a | -0.042 |
o | -0.042 |
uch | -0.042 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
prise | +0.006 |
w | +0.005 |
uch | +0.005 |
e | +0.005 |
asc | +0.005 |
Neg logit contributions | |
horizon | -0.007 |
Everyone | -0.007 |
der | -0.007 |
Afterwards | -0.007 |
Then | -0.007 |
Token | around |
Token ID | 1088 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
prise | +0.074 |
w | +0.073 |
uch | +0.070 |
o | +0.070 |
e | +0.069 |
Neg logit contributions | |
horizon | -0.065 |
der | -0.065 |
Everyone | -0.064 |
Afterwards | -0.063 |
rily | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Afterwards | +0.016 |
Everyone | +0.016 |
horizon | +0.016 |
der | +0.016 |
rily | +0.016 |
Neg logit contributions | |
prise | -0.013 |
e | -0.012 |
w | -0.012 |
o | -0.012 |
a | -0.012 |
Token | smiled |
Token ID | 13541 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
der | +0.032 |
rily | +0.031 |
horizon | +0.031 |
rier | +0.031 |
Everyone | +0.030 |
Neg logit contributions | |
w | -0.013 |
prise | -0.013 |
o | -0.013 |
e | -0.012 |
a | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
horizon | +0.003 |
Afterwards | +0.003 |
Everyone | +0.003 |
Everybody | +0.003 |
der | +0.003 |
Neg logit contributions | |
a | -0.002 |
o | -0.002 |
prise | -0.002 |
seeker | -0.002 |
e | -0.002 |
Token | even |
Token ID | 772 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
horizon | +0.039 |
der | +0.038 |
Everyone | +0.038 |
Afterwards | +0.037 |
Everybody | +0.036 |
Neg logit contributions | |
w | -0.051 |
prise | -0.050 |
e | -0.049 |
a | -0.048 |
uch | -0.048 |
Token | when |
Token ID | 618 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
horizon | +0.016 |
der | +0.015 |
Everyone | +0.015 |
Afterwards | +0.015 |
rily | +0.015 |
Neg logit contributions | |
prise | -0.020 |
w | -0.020 |
uch | -0.019 |
e | -0.019 |
o | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
der | +0.030 |
horizon | +0.029 |
rily | +0.029 |
Everyone | +0.028 |
int | +0.027 |
Neg logit contributions | |
prise | -0.043 |
w | -0.043 |
uch | -0.041 |
e | -0.041 |
o | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
prise | +0.044 |
asc | +0.044 |
w | +0.044 |
seeker | +0.043 |
uch | +0.041 |
Neg logit contributions | |
der | -0.043 |
Afterwards | -0.042 |
Then | -0.042 |
horizon | -0.042 |
int | -0.041 |
Token | deaf |
Token ID | 21815 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
w | +0.086 |
prise | +0.084 |
uch | +0.078 |
o | +0.075 |
asc | +0.074 |
Neg logit contributions | |
der | -0.089 |
int | -0.087 |
horizon | -0.087 |
Afterwards | -0.084 |
Then | -0.084 |
Token | to |
Token ID | 284 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
der | +0.025 |
horizon | +0.024 |
Everyone | +0.023 |
int | +0.023 |
rily | +0.023 |
Neg logit contributions | |
prise | -0.023 |
w | -0.022 |
uch | -0.022 |
asc | -0.021 |
o | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
e | +0.011 |
prise | +0.011 |
w | +0.011 |
uch | +0.011 |
a | +0.010 |
Neg logit contributions | |
der | -0.011 |
rily | -0.011 |
horizon | -0.011 |
Afterwards | -0.011 |
rier | -0.010 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
horizon | +0.038 |
der | +0.037 |
int | +0.036 |
Everyone | +0.036 |
Then | +0.035 |
Neg logit contributions | |
w | -0.065 |
prise | -0.064 |
uch | -0.062 |
asc | -0.061 |
o | -0.060 |
Token | my |
Token ID | 1820 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
horizon | +0.007 |
der | +0.007 |
Afterwards | +0.006 |
Everyone | +0.006 |
int | +0.006 |
Neg logit contributions | |
prise | -0.003 |
w | -0.003 |
uch | -0.002 |
asc | -0.002 |
a | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
horizon | +0.011 |
der | +0.011 |
Everyone | +0.011 |
Afterwards | +0.011 |
int | +0.011 |
Neg logit contributions | |
prise | -0.010 |
w | -0.009 |
uch | -0.009 |
asc | -0.009 |
o | -0.009 |
Token | reminders |
Token ID | 40687 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
horizon | +0.014 |
der | +0.014 |
Everyone | +0.013 |
int | +0.013 |
Afterwards | +0.013 |
Neg logit contributions | |
w | -0.017 |
prise | -0.017 |
uch | -0.017 |
o | -0.016 |
asc | -0.016 |
Token | But |
Token ID | 1537 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
prise | +0.031 |
w | +0.031 |
uch | +0.030 |
e | +0.030 |
o | +0.030 |
Neg logit contributions | |
horizon | -0.017 |
der | -0.016 |
Afterwards | -0.016 |
Everyone | -0.016 |
rily | -0.015 |
Token | then |
Token ID | 788 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
horizon | +0.026 |
der | +0.026 |
Everyone | +0.025 |
rily | +0.025 |
Afterwards | +0.025 |
Neg logit contributions | |
prise | -0.037 |
w | -0.037 |
e | -0.036 |
o | -0.036 |
uch | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
prise | +0.001 |
w | +0.001 |
uch | +0.001 |
o | +0.001 |
a | +0.001 |
Neg logit contributions | |
Everyone | -0.002 |
der | -0.002 |
horizon | -0.002 |
Afterwards | -0.002 |
Then | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
horizon | +0.039 |
der | +0.037 |
rily | +0.037 |
Afterwards | +0.036 |
int | +0.036 |
Neg logit contributions | |
prise | -0.034 |
w | -0.034 |
e | -0.033 |
o | -0.033 |
uch | -0.032 |
Token | little |
Token ID | 1310 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
w | +0.055 |
prise | +0.053 |
uch | +0.052 |
e | +0.052 |
asc | +0.051 |
Neg logit contributions | |
horizon | -0.046 |
Everyone | -0.045 |
der | -0.043 |
Everybody | -0.043 |
int | -0.042 |
Token | boy |
Token ID | 2933 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
w | +0.067 |
uch | +0.067 |
prise | +0.066 |
e | +0.063 |
asc | +0.062 |
Neg logit contributions | |
horizon | -0.045 |
der | -0.043 |
Everyone | -0.042 |
rier | -0.041 |
int | -0.041 |
Token | of |
Token ID | 286 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
uch | +0.118 |
seeker | +0.117 |
asc | +0.114 |
prise | +0.114 |
w | +0.113 |
Neg logit contributions | |
Then | -0.074 |
Everyone | -0.067 |
ment | -0.065 |
Immediately | -0.062 |
After | -0.061 |
Token | three |
Token ID | 1115 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
prise | +0.005 |
w | +0.005 |
uch | +0.005 |
o | +0.005 |
a | +0.005 |
Neg logit contributions | |
horizon | -0.003 |
der | -0.003 |
Everyone | -0.003 |
Afterwards | -0.003 |
Then | -0.003 |
Token | years |
Token ID | 812 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
prise | +0.017 |
uch | +0.016 |
w | +0.016 |
seeker | +0.016 |
asc | +0.015 |
Neg logit contributions | |
Everyone | -0.024 |
der | -0.024 |
ment | -0.023 |
Everybody | -0.023 |
int | -0.023 |
Token | old |
Token ID | 1468 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
prise | +0.026 |
w | +0.026 |
uch | +0.025 |
o | +0.025 |
e | +0.025 |
Neg logit contributions | |
horizon | -0.015 |
der | -0.014 |
Everyone | -0.014 |
Afterwards | -0.014 |
rily | -0.014 |
Token | came |
Token ID | 1625 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
der | +0.001 |
Everyone | +0.001 |
horizon | +0.001 |
Then | +0.001 |
ment | +0.001 |
Neg logit contributions | |
prise | -0.002 |
w | -0.002 |
uch | -0.002 |
asc | -0.001 |
e | -0.001 |
Token | problems |
Token ID | 2761 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
horizon | +0.003 |
der | +0.003 |
Everyone | +0.003 |
Afterwards | +0.003 |
int | +0.003 |
Neg logit contributions | |
prise | -0.005 |
w | -0.005 |
uch | -0.005 |
o | -0.005 |
e | -0.005 |
Token | won |
Token ID | 1839 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
prise | +0.002 |
w | +0.002 |
uch | +0.002 |
asc | +0.002 |
seeker | +0.002 |
Neg logit contributions | |
der | -0.002 |
Everyone | -0.002 |
horizon | -0.001 |
Then | -0.001 |
Everybody | -0.001 |
Token | 't |
Token ID | 470 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
prise | +0.040 |
w | +0.040 |
uch | +0.039 |
e | +0.039 |
o | +0.038 |
Neg logit contributions | |
horizon | -0.042 |
der | -0.042 |
Afterwards | -0.041 |
Everyone | -0.041 |
rily | -0.041 |
Token | solve |
Token ID | 8494 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
prise | +0.082 |
w | +0.080 |
uch | +0.076 |
e | +0.076 |
o | +0.075 |
Neg logit contributions | |
der | -0.081 |
horizon | -0.080 |
Everyone | -0.080 |
Afterwards | -0.077 |
int | -0.076 |
Token | them |
Token ID | 606 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
prise | +0.016 |
w | +0.015 |
uch | +0.015 |
o | +0.015 |
asc | +0.015 |
Neg logit contributions | |
der | -0.013 |
horizon | -0.012 |
rily | -0.012 |
Everyone | -0.012 |
ment | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
der | +0.009 |
horizon | +0.009 |
Everyone | +0.008 |
int | +0.008 |
Afterwards | +0.008 |
Neg logit contributions | |
prise | -0.011 |
w | -0.011 |
uch | -0.010 |
o | -0.010 |
e | -0.010 |
Token | So |
Token ID | 1406 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
horizon | +0.056 |
ment | +0.054 |
rier | +0.054 |
rily | +0.054 |
lights | +0.051 |
Neg logit contributions | |
o | -0.056 |
a | -0.050 |
prise | -0.049 |
uffy | -0.047 |
itty | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
prise | +0.007 |
w | +0.007 |
a | +0.006 |
e | +0.006 |
uch | +0.006 |
Neg logit contributions | |
horizon | -0.015 |
der | -0.015 |
rily | -0.015 |
Everyone | -0.014 |
int | -0.014 |
Token | she |
Token ID | 673 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
horizon | +0.031 |
rily | +0.028 |
der | +0.028 |
rier | +0.028 |
ment | +0.027 |
Neg logit contributions | |
prise | -0.020 |
w | -0.020 |
e | -0.019 |
a | -0.018 |
hiding | -0.018 |
Token | decided |
Token ID | 3066 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
prise | +0.033 |
w | +0.032 |
uch | +0.031 |
e | +0.030 |
asc | +0.029 |
Neg logit contributions | |
der | -0.025 |
Then | -0.024 |
Everyone | -0.023 |
After | -0.022 |
Afterwards | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
horizon | +0.006 |
Afterwards | +0.006 |
rily | +0.006 |
Everyone | +0.006 |
der | +0.006 |
Neg logit contributions | |
prise | -0.004 |
w | -0.004 |
o | -0.004 |
a | -0.004 |
uch | -0.004 |
Token | use |
Token ID | 779 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
prise | +0.002 |
w | +0.002 |
e | +0.002 |
uch | +0.002 |
o | +0.002 |
Neg logit contributions | |
der | -0.002 |
horizon | -0.002 |
Afterwards | -0.002 |
Everyone | -0.002 |
rily | -0.002 |
Token | these |
Token ID | 777 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
horizon | +0.025 |
der | +0.024 |
Afterwards | +0.024 |
Everyone | +0.024 |
Everybody | +0.024 |
Neg logit contributions | |
prise | -0.028 |
w | -0.027 |
e | -0.027 |
o | -0.026 |
a | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
horizon | +0.063 |
Afterwards | +0.063 |
der | +0.062 |
Everyone | +0.062 |
int | +0.061 |
Neg logit contributions | |
w | -0.066 |
prise | -0.065 |
a | -0.062 |
uch | -0.062 |
o | -0.062 |
Token | They |
Token ID | 1119 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
horizon | +0.006 |
ment | +0.006 |
der | +0.006 |
int | +0.005 |
rily | +0.005 |
Neg logit contributions | |
prise | -0.009 |
o | -0.009 |
e | -0.009 |
seeker | -0.009 |
a | -0.008 |
Token | are |
Token ID | 389 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
prise | +0.001 |
w | +0.001 |
uch | +0.001 |
o | +0.001 |
asc | +0.001 |
Neg logit contributions | |
horizon | -0.002 |
der | -0.002 |
Everyone | -0.002 |
Afterwards | -0.002 |
rily | -0.002 |
Token | prick |
Token ID | 41409 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
prise | +0.021 |
w | +0.020 |
uch | +0.019 |
o | +0.019 |
e | +0.019 |
Neg logit contributions | |
horizon | -0.026 |
der | -0.026 |
Everyone | -0.025 |
Afterwards | -0.025 |
rily | -0.024 |
Token | ly |
Token ID | 306 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
w | +0.001 |
prise | +0.001 |
uch | +0.001 |
o | +0.001 |
e | +0.001 |
Neg logit contributions | |
horizon | -0.001 |
der | -0.001 |
Everyone | -0.001 |
Afterwards | -0.001 |
int | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
horizon | +0.020 |
der | +0.020 |
Everyone | +0.020 |
Afterwards | +0.020 |
rily | +0.020 |
Neg logit contributions | |
prise | -0.019 |
w | -0.019 |
uch | -0.018 |
e | -0.018 |
o | -0.018 |
Token | fun |
Token ID | 1257 |
Feature activation | +4.70e-03 |
Pos logit contributions | |
horizon | +0.034 |
der | +0.034 |
Everyone | +0.033 |
Afterwards | +0.033 |
rily | +0.032 |
Neg logit contributions | |
prise | -0.025 |
w | -0.025 |
uch | -0.024 |
e | -0.023 |
o | -0.023 |
Token | ." |
Token ID | 526 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
prise | +0.000 |
w | +0.000 |
uch | +0.000 |
e | +0.000 |
o | +0.000 |
Neg logit contributions | |
der | -0.000 |
horizon | -0.000 |
Everyone | -0.000 |
rily | -0.000 |
Afterwards | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
horizon | +0.054 |
lights | +0.053 |
rier | +0.052 |
rily | +0.051 |
der | +0.049 |
Neg logit contributions | |
o | -0.049 |
w | -0.047 |
a | -0.046 |
prise | -0.043 |
e | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
o | +0.038 |
prise | +0.038 |
w | +0.037 |
e | +0.037 |
a | +0.037 |
Neg logit contributions | |
der | -0.025 |
horizon | -0.025 |
rier | -0.025 |
rily | -0.024 |
ment | -0.022 |
Token | Lu |
Token ID | 25596 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
prise | +0.049 |
w | +0.048 |
uch | +0.047 |
o | +0.047 |
e | +0.046 |
Neg logit contributions | |
Everyone | -0.028 |
Afterwards | -0.028 |
der | -0.028 |
horizon | -0.028 |
Everybody | -0.027 |
Token | cy |
Token ID | 948 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
seeker | +0.030 |
prise | +0.030 |
tresp | +0.029 |
uch | +0.028 |
mean | +0.027 |
Neg logit contributions | |
After | -0.038 |
Afterwards | -0.038 |
ment | -0.038 |
horizon | -0.038 |
Then | -0.038 |
Token | 's |
Token ID | 338 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
der | +0.005 |
Then | +0.005 |
Everyone | +0.005 |
horizon | +0.005 |
Afterwards | +0.005 |
Neg logit contributions | |
prise | -0.006 |
w | -0.006 |
uch | -0.005 |
asc | -0.005 |
seeker | -0.005 |
Token | friend |
Token ID | 1545 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
horizon | +0.030 |
der | +0.030 |
Everyone | +0.029 |
Afterwards | +0.029 |
int | +0.029 |
Neg logit contributions | |
prise | -0.049 |
w | -0.049 |
uch | -0.047 |
asc | -0.046 |
o | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Everyone | +0.014 |
der | +0.013 |
Everybody | +0.013 |
Then | +0.013 |
Afterwards | +0.013 |
Neg logit contributions | |
w | -0.014 |
prise | -0.014 |
uch | -0.014 |
asc | -0.013 |
seeker | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Everyone | +0.028 |
Everybody | +0.026 |
Then | +0.026 |
der | +0.026 |
After | +0.025 |
Neg logit contributions | |
uch | -0.043 |
w | -0.042 |
prise | -0.042 |
e | -0.039 |
asc | -0.038 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
horizon | +0.005 |
Everyone | +0.005 |
der | +0.005 |
Everybody | +0.005 |
Then | +0.005 |
Neg logit contributions | |
w | -0.007 |
uch | -0.007 |
prise | -0.007 |
e | -0.006 |
asc | -0.006 |
Token | named |
Token ID | 3706 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
w | +0.040 |
uch | +0.040 |
prise | +0.038 |
asc | +0.035 |
seeker | +0.034 |
Neg logit contributions | |
Everyone | -0.038 |
� | -0.037 |
Then | -0.036 |
' | -0.036 |
der | -0.035 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Everyone | +0.062 |
der | +0.061 |
horizon | +0.061 |
Afterwards | +0.060 |
Everybody | +0.059 |
Neg logit contributions | |
prise | -0.061 |
w | -0.059 |
uch | -0.057 |
e | -0.055 |
a | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
w | +0.033 |
prise | +0.033 |
uch | +0.033 |
asc | +0.030 |
seeker | +0.029 |
Neg logit contributions | |
Everyone | -0.027 |
Then | -0.026 |
der | -0.026 |
� | -0.026 |
' | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
horizon | +0.014 |
der | +0.014 |
Everyone | +0.014 |
Afterwards | +0.013 |
int | +0.013 |
Neg logit contributions | |
prise | -0.017 |
w | -0.017 |
uch | -0.016 |
e | -0.016 |
o | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
horizon | +0.067 |
der | +0.066 |
int | +0.063 |
rily | +0.063 |
rier | +0.062 |
Neg logit contributions | |
o | -0.103 |
prise | -0.101 |
e | -0.099 |
a | -0.097 |
seeker | -0.093 |
Token | car |
Token ID | 1097 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
horizon | +0.071 |
der | +0.069 |
Everyone | +0.068 |
Afterwards | +0.065 |
Everybody | +0.065 |
Neg logit contributions | |
prise | -0.083 |
w | -0.082 |
uch | -0.079 |
o | -0.079 |
e | -0.078 |
Token | hit |
Token ID | 2277 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
der | +0.019 |
horizon | +0.019 |
Everyone | +0.018 |
int | +0.018 |
Afterwards | +0.018 |
Neg logit contributions | |
prise | -0.018 |
w | -0.017 |
uch | -0.016 |
e | -0.016 |
o | -0.016 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
horizon | +0.029 |
der | +0.029 |
Everyone | +0.028 |
Afterwards | +0.028 |
rily | +0.027 |
Neg logit contributions | |
prise | -0.043 |
w | -0.042 |
uch | -0.041 |
e | -0.041 |
o | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
der | +0.000 |
rily | +0.000 |
int | +0.000 |
horizon | +0.000 |
Then | +0.000 |
Neg logit contributions | |
prise | -0.001 |
w | -0.001 |
asc | -0.001 |
seeker | -0.001 |
uch | -0.001 |
Token | Ben |
Token ID | 3932 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
horizon | +0.059 |
der | +0.057 |
Everyone | +0.057 |
Afterwards | +0.056 |
rily | +0.056 |
Neg logit contributions | |
prise | -0.052 |
w | -0.051 |
e | -0.049 |
uch | -0.048 |
a | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
prise | +0.023 |
asc | +0.021 |
seeker | +0.020 |
w | +0.020 |
uch | +0.020 |
Neg logit contributions | |
der | -0.019 |
int | -0.018 |
Then | -0.018 |
horizon | -0.018 |
rily | -0.017 |
Token | made |
Token ID | 925 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
horizon | +0.084 |
rily | +0.080 |
Afterwards | +0.080 |
der | +0.079 |
Everyone | +0.079 |
Neg logit contributions | |
prise | -0.071 |
w | -0.071 |
e | -0.068 |
a | -0.068 |
o | -0.067 |
Token | them |
Token ID | 606 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
horizon | +0.007 |
der | +0.006 |
Afterwards | +0.006 |
Everyone | +0.006 |
rily | +0.006 |
Neg logit contributions | |
prise | -0.007 |
w | -0.007 |
e | -0.007 |
uch | -0.007 |
o | -0.007 |
Token | fall |
Token ID | 2121 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
prise | +0.016 |
w | +0.016 |
uch | +0.015 |
o | +0.015 |
asc | +0.014 |
Neg logit contributions | |
der | -0.017 |
Everyone | -0.017 |
int | -0.017 |
horizon | -0.017 |
rily | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
prise | +0.091 |
uch | +0.086 |
w | +0.086 |
asc | +0.083 |
seeker | +0.080 |
Neg logit contributions | |
Then | -0.074 |
Everyone | -0.073 |
ment | -0.071 |
der | -0.071 |
' | -0.070 |
Token | a |
Token ID | 257 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
der | +0.010 |
Everyone | +0.010 |
horizon | +0.010 |
Everybody | +0.009 |
int | +0.009 |
Neg logit contributions | |
w | -0.013 |
prise | -0.013 |
uch | -0.013 |
e | -0.013 |
o | -0.013 |
Token | spider |
Token ID | 19230 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
horizon | +0.017 |
der | +0.016 |
Everyone | +0.015 |
rier | +0.015 |
int | +0.015 |
Neg logit contributions | |
prise | -0.018 |
w | -0.018 |
e | -0.018 |
uch | -0.018 |
o | -0.017 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
prise | +0.034 |
uch | +0.032 |
w | +0.032 |
seeker | +0.031 |
o | +0.031 |
Neg logit contributions | |
der | -0.038 |
horizon | -0.035 |
Everyone | -0.035 |
ment | -0.035 |
rily | -0.034 |
Token | she |
Token ID | 673 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
horizon | +0.091 |
der | +0.086 |
rier | +0.082 |
rily | +0.082 |
Afterwards | +0.081 |
Neg logit contributions | |
o | -0.060 |
e | -0.059 |
a | -0.058 |
prise | -0.057 |
w | -0.057 |
Token | said |
Token ID | 531 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
prise | +0.027 |
w | +0.027 |
uch | +0.026 |
e | +0.025 |
o | +0.025 |
Neg logit contributions | |
der | -0.027 |
horizon | -0.027 |
Everyone | -0.027 |
Afterwards | -0.027 |
int | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
horizon | +0.011 |
Afterwards | +0.010 |
der | +0.010 |
Everyone | +0.010 |
Everybody | +0.010 |
Neg logit contributions | |
prise | -0.008 |
e | -0.008 |
o | -0.008 |
a | -0.008 |
w | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
horizon | +0.044 |
rily | +0.040 |
ment | +0.040 |
der | +0.039 |
rier | +0.038 |
Neg logit contributions | |
o | -0.070 |
e | -0.066 |
a | -0.065 |
prise | -0.063 |
itty | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
o | +0.024 |
prise | +0.024 |
w | +0.023 |
e | +0.023 |
a | +0.023 |
Neg logit contributions | |
der | -0.016 |
horizon | -0.016 |
rier | -0.015 |
rily | -0.015 |
Afterwards | -0.014 |
Token | Max |
Token ID | 11518 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
uch | +0.040 |
prise | +0.039 |
w | +0.039 |
asc | +0.038 |
seeker | +0.038 |
Neg logit contributions | |
Everyone | -0.031 |
Then | -0.031 |
After | -0.030 |
Afterwards | -0.029 |
horizon | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
prise | +0.071 |
w | +0.067 |
uch | +0.063 |
asc | +0.062 |
seeker | +0.061 |
Neg logit contributions | |
der | -0.053 |
Then | -0.052 |
Immediately | -0.049 |
� | -0.049 |
After | -0.048 |
Token | playing |
Token ID | 2712 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
w | +0.054 |
prise | +0.053 |
uch | +0.049 |
a | +0.048 |
o | +0.048 |
Neg logit contributions | |
der | -0.078 |
horizon | -0.077 |
Everyone | -0.076 |
int | -0.076 |
Afterwards | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
der | +0.022 |
horizon | +0.022 |
Everyone | +0.022 |
Afterwards | +0.021 |
rily | +0.021 |
Neg logit contributions | |
prise | -0.017 |
w | -0.017 |
uch | -0.016 |
o | -0.015 |
a | -0.015 |
Token | shaking |
Token ID | 17275 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
horizon | +0.036 |
der | +0.036 |
Everyone | +0.035 |
Afterwards | +0.035 |
rily | +0.034 |
Neg logit contributions | |
prise | -0.030 |
w | -0.029 |
uch | -0.028 |
e | -0.028 |
o | -0.028 |
Token | his |
Token ID | 465 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
horizon | +0.073 |
der | +0.072 |
Afterwards | +0.070 |
Everyone | +0.070 |
rily | +0.068 |
Neg logit contributions | |
prise | -0.092 |
w | -0.092 |
e | -0.089 |
o | -0.088 |
uch | -0.088 |
Token | bell |
Token ID | 8966 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
horizon | +0.072 |
der | +0.072 |
Everyone | +0.070 |
Afterwards | +0.070 |
rily | +0.068 |
Neg logit contributions | |
prise | -0.083 |
w | -0.082 |
uch | -0.079 |
e | -0.079 |
o | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
horizon | +0.051 |
der | +0.051 |
Everyone | +0.050 |
Afterwards | +0.050 |
rily | +0.049 |
Neg logit contributions | |
prise | -0.045 |
w | -0.045 |
uch | -0.043 |
e | -0.043 |
o | -0.043 |
Token | it |
Token ID | 340 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
rily | +0.104 |
horizon | +0.100 |
der | +0.098 |
Afterwards | +0.097 |
rier | +0.094 |
Neg logit contributions | |
w | -0.130 |
mean | -0.125 |
e | -0.124 |
o | -0.124 |
prise | -0.122 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
der | +0.028 |
horizon | +0.027 |
Everyone | +0.026 |
int | +0.026 |
Afterwards | +0.026 |
Neg logit contributions | |
prise | -0.030 |
w | -0.028 |
uch | -0.027 |
asc | -0.027 |
o | -0.027 |
Token | broke |
Token ID | 6265 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
horizon | +0.054 |
der | +0.053 |
Afterwards | +0.053 |
Everyone | +0.053 |
rily | +0.052 |
Neg logit contributions | |
w | -0.035 |
prise | -0.034 |
uch | -0.033 |
a | -0.032 |
e | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
horizon | +0.002 |
der | +0.002 |
Everyone | +0.002 |
Afterwards | +0.002 |
int | +0.002 |
Neg logit contributions | |
prise | -0.002 |
w | -0.002 |
uch | -0.002 |
o | -0.002 |
e | -0.002 |
Token | The |
Token ID | 383 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
rily | +0.161 |
rier | +0.153 |
der | +0.150 |
ment | +0.150 |
horizon | +0.146 |
Neg logit contributions | |
o | -0.095 |
mean | -0.085 |
uch | -0.082 |
e | -0.081 |
w | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
prise | +0.003 |
w | +0.003 |
uch | +0.003 |
e | +0.003 |
o | +0.003 |
Neg logit contributions | |
horizon | -0.003 |
der | -0.003 |
Everyone | -0.003 |
Afterwards | -0.003 |
rily | -0.003 |
Token | but |
Token ID | 475 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
der | +0.085 |
horizon | +0.085 |
Afterwards | +0.084 |
Everyone | +0.083 |
rily | +0.082 |
Neg logit contributions | |
prise | -0.100 |
w | -0.097 |
e | -0.095 |
o | -0.095 |
a | -0.095 |
Token | it |
Token ID | 340 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
der | +0.059 |
horizon | +0.058 |
Everyone | +0.057 |
Afterwards | +0.057 |
rily | +0.056 |
Neg logit contributions | |
w | -0.078 |
prise | -0.078 |
a | -0.075 |
e | -0.074 |
o | -0.073 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
der | +0.013 |
horizon | +0.012 |
int | +0.012 |
rily | +0.012 |
Everyone | +0.012 |
Neg logit contributions | |
prise | -0.017 |
w | -0.015 |
asc | -0.015 |
e | -0.014 |
seeker | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
uch | +0.062 |
w | +0.062 |
prise | +0.062 |
e | +0.059 |
o | +0.057 |
Neg logit contributions | |
horizon | -0.109 |
der | -0.108 |
ment | -0.107 |
rily | -0.106 |
Afterwards | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
w | +0.103 |
prise | +0.103 |
uch | +0.098 |
o | +0.097 |
asc | +0.097 |
Neg logit contributions | |
Everyone | -0.090 |
der | -0.087 |
horizon | -0.087 |
Everybody | -0.085 |
int | -0.084 |
Token | Mary |
Token ID | 5335 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
rier | +0.144 |
der | +0.141 |
rily | +0.140 |
lights | +0.130 |
horizon | +0.128 |
Neg logit contributions | |
o | -0.107 |
e | -0.101 |
a | -0.098 |
ow | -0.096 |
w | -0.096 |
Token | was |
Token ID | 373 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
der | +0.010 |
Then | +0.010 |
Everyone | +0.010 |
horizon | +0.010 |
rily | +0.010 |
Neg logit contributions | |
prise | -0.014 |
w | -0.013 |
asc | -0.013 |
uch | -0.012 |
seeker | -0.012 |
Token | sad |
Token ID | 6507 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
prise | +0.084 |
w | +0.083 |
uch | +0.077 |
o | +0.073 |
e | +0.072 |
Neg logit contributions | |
der | -0.077 |
Everyone | -0.076 |
int | -0.075 |
Then | -0.074 |
horizon | -0.074 |
Token | that |
Token ID | 326 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
horizon | +0.006 |
Afterwards | +0.006 |
rily | +0.006 |
Everyone | +0.006 |
Everybody | +0.006 |
Neg logit contributions | |
prise | -0.004 |
w | -0.004 |
o | -0.004 |
a | -0.004 |
seeker | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
der | +0.088 |
horizon | +0.086 |
rily | +0.086 |
Afterwards | +0.085 |
Everyone | +0.083 |
Neg logit contributions | |
prise | -0.115 |
w | -0.115 |
e | -0.111 |
a | -0.110 |
uch | -0.109 |
Token | fierce |
Token ID | 14800 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
horizon | +0.055 |
der | +0.052 |
Everyone | +0.052 |
int | +0.051 |
Afterwards | +0.050 |
Neg logit contributions | |
w | -0.061 |
prise | -0.059 |
uch | -0.059 |
o | -0.058 |
e | -0.057 |
Token | animal |
Token ID | 5044 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
horizon | +0.070 |
der | +0.069 |
Everyone | +0.067 |
int | +0.065 |
Everybody | +0.064 |
Neg logit contributions | |
prise | -0.077 |
w | -0.077 |
uch | -0.075 |
o | -0.073 |
e | -0.071 |
Token | inside |
Token ID | 2641 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
der | +0.065 |
horizon | +0.064 |
Everyone | +0.063 |
int | +0.062 |
rily | +0.061 |
Neg logit contributions | |
w | -0.073 |
prise | -0.071 |
uch | -0.071 |
asc | -0.066 |
seeker | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
horizon | +0.059 |
der | +0.058 |
Everyone | +0.057 |
Afterwards | +0.056 |
rily | +0.056 |
Neg logit contributions | |
prise | -0.062 |
w | -0.061 |
uch | -0.059 |
o | -0.058 |
a | -0.057 |
Token | chamber |
Token ID | 11847 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
horizon | +0.099 |
Everyone | +0.092 |
der | +0.091 |
Everybody | +0.088 |
Afterwards | +0.088 |
Neg logit contributions | |
w | -0.086 |
prise | -0.085 |
o | -0.085 |
uch | -0.083 |
e | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
horizon | +0.071 |
der | +0.071 |
Everyone | +0.069 |
Afterwards | +0.069 |
rily | +0.068 |
Neg logit contributions | |
prise | -0.067 |
w | -0.066 |
uch | -0.063 |
o | -0.062 |
e | -0.062 |
Token | ready |
Token ID | 3492 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
horizon | +0.117 |
der | +0.116 |
Everyone | +0.114 |
Afterwards | +0.113 |
rily | +0.111 |
Neg logit contributions | |
prise | -0.108 |
w | -0.106 |
uch | -0.101 |
e | -0.100 |
o | -0.100 |
Token | to |
Token ID | 284 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
der | +0.042 |
Everyone | +0.042 |
Afterwards | +0.042 |
horizon | +0.041 |
Everybody | +0.041 |
Neg logit contributions | |
prise | -0.036 |
w | -0.035 |
a | -0.033 |
o | -0.033 |
e | -0.033 |
Token | defend |
Token ID | 4404 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
prise | +0.004 |
w | +0.004 |
e | +0.004 |
uch | +0.004 |
a | +0.004 |
Neg logit contributions | |
der | -0.005 |
horizon | -0.005 |
Afterwards | -0.004 |
rily | -0.004 |
Everyone | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
der | +0.041 |
horizon | +0.041 |
Afterwards | +0.040 |
Everyone | +0.037 |
Everybody | +0.037 |
Neg logit contributions | |
e | -0.078 |
a | -0.076 |
prise | -0.074 |
w | -0.073 |
o | -0.072 |
Token | against |
Token ID | 1028 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
horizon | +0.061 |
der | +0.061 |
Everyone | +0.059 |
Afterwards | +0.059 |
rily | +0.058 |
Neg logit contributions | |
prise | -0.061 |
w | -0.060 |
uch | -0.058 |
o | -0.057 |
e | -0.057 |
Token | off |
Token ID | 572 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
prise | +0.063 |
w | +0.062 |
uch | +0.060 |
e | +0.060 |
o | +0.060 |
Neg logit contributions | |
horizon | -0.046 |
der | -0.045 |
Everyone | -0.044 |
Afterwards | -0.044 |
rily | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
der | +0.002 |
horizon | +0.002 |
Afterwards | +0.002 |
Everyone | +0.002 |
rily | +0.002 |
Neg logit contributions | |
prise | -0.002 |
o | -0.002 |
e | -0.002 |
w | -0.002 |
a | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
prise | +0.003 |
e | +0.003 |
o | +0.003 |
w | +0.003 |
a | +0.003 |
Neg logit contributions | |
der | -0.005 |
horizon | -0.005 |
rily | -0.004 |
ment | -0.004 |
rier | -0.004 |
Token | living |
Token ID | 2877 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
horizon | +0.019 |
der | +0.019 |
Everyone | +0.019 |
Afterwards | +0.019 |
int | +0.018 |
Neg logit contributions | |
w | -0.017 |
prise | -0.017 |
uch | -0.016 |
o | -0.016 |
e | -0.016 |
Token | room |
Token ID | 2119 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
prise | +0.027 |
w | +0.026 |
uch | +0.024 |
o | +0.024 |
e | +0.024 |
Neg logit contributions | |
horizon | -0.052 |
der | -0.052 |
Everyone | -0.051 |
Afterwards | -0.051 |
rily | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
horizon | +0.027 |
der | +0.026 |
Afterwards | +0.026 |
Everyone | +0.026 |
rily | +0.026 |
Neg logit contributions | |
prise | -0.024 |
e | -0.022 |
o | -0.022 |
w | -0.022 |
a | -0.022 |
Token | They |
Token ID | 1119 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
rier | +0.099 |
der | +0.095 |
rily | +0.090 |
horizon | +0.087 |
bread | +0.086 |
Neg logit contributions | |
o | -0.129 |
hiding | -0.101 |
a | -0.098 |
prise | -0.094 |
itty | -0.094 |
Token | both |
Token ID | 1111 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
prise | +0.005 |
w | +0.005 |
uch | +0.005 |
asc | +0.005 |
ymes | +0.004 |
Neg logit contributions | |
Afterwards | -0.005 |
Everyone | -0.005 |
Then | -0.005 |
int | -0.005 |
horizon | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
prise | +0.003 |
w | +0.003 |
uch | +0.003 |
asc | +0.002 |
seeker | +0.002 |
Neg logit contributions | |
Afterwards | -0.003 |
Everyone | -0.003 |
der | -0.003 |
horizon | -0.003 |
Then | -0.003 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
prise | +0.033 |
w | +0.033 |
uch | +0.032 |
o | +0.030 |
e | +0.030 |
Neg logit contributions | |
horizon | -0.028 |
Everyone | -0.028 |
der | -0.028 |
Afterwards | -0.028 |
Then | -0.027 |
Token | playing |
Token ID | 2712 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
prise | +0.030 |
w | +0.030 |
uch | +0.030 |
asc | +0.027 |
a | +0.027 |
Neg logit contributions | |
der | -0.063 |
Everyone | -0.061 |
int | -0.061 |
After | -0.061 |
Then | -0.060 |
Token | her |
Token ID | 607 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
horizon | +0.038 |
der | +0.037 |
Everyone | +0.036 |
Afterwards | +0.036 |
rily | +0.035 |
Neg logit contributions | |
prise | -0.045 |
w | -0.045 |
uch | -0.043 |
e | -0.043 |
o | -0.043 |
Token | what |
Token ID | 644 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
horizon | +0.066 |
der | +0.065 |
Everyone | +0.064 |
Afterwards | +0.063 |
rily | +0.062 |
Neg logit contributions | |
prise | -0.069 |
w | -0.068 |
uch | -0.065 |
e | -0.065 |
o | -0.065 |
Token | he |
Token ID | 339 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
Everyone | +0.022 |
der | +0.021 |
horizon | +0.021 |
Everybody | +0.021 |
Afterwards | +0.020 |
Neg logit contributions | |
prise | -0.049 |
w | -0.048 |
uch | -0.047 |
asc | -0.046 |
e | -0.046 |
Token | could |
Token ID | 714 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
horizon | +0.000 |
Then | +0.000 |
der | +0.000 |
Everyone | +0.000 |
int | +0.000 |
Neg logit contributions | |
prise | -0.000 |
w | -0.000 |
asc | -0.000 |
seeker | -0.000 |
uch | -0.000 |
Token | do |
Token ID | 466 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
prise | +0.031 |
w | +0.031 |
uch | +0.029 |
o | +0.028 |
e | +0.028 |
Neg logit contributions | |
horizon | -0.057 |
der | -0.057 |
Everyone | -0.056 |
Afterwards | -0.056 |
rily | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
prise | +0.020 |
w | +0.019 |
uch | +0.019 |
o | +0.018 |
e | +0.018 |
Neg logit contributions | |
der | -0.018 |
horizon | -0.018 |
Everyone | -0.018 |
int | -0.018 |
Afterwards | -0.017 |
Token | Sammy |
Token ID | 44067 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
rier | +0.150 |
rily | +0.146 |
lights | +0.146 |
ment | +0.143 |
der | +0.142 |
Neg logit contributions | |
o | -0.107 |
e | -0.085 |
itty | -0.083 |
seeker | -0.082 |
a | -0.081 |
Token | was |
Token ID | 373 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
prise | +0.020 |
w | +0.019 |
uch | +0.019 |
e | +0.018 |
o | +0.018 |
Neg logit contributions | |
der | -0.019 |
horizon | -0.019 |
Everyone | -0.019 |
Afterwards | -0.018 |
int | -0.018 |
Token | so |
Token ID | 523 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
w | +0.074 |
prise | +0.073 |
uch | +0.069 |
o | +0.066 |
e | +0.065 |
Neg logit contributions | |
Everyone | -0.078 |
horizon | -0.078 |
der | -0.078 |
Afterwards | -0.077 |
int | -0.076 |
Token | worried |
Token ID | 7960 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
prise | +0.049 |
w | +0.049 |
uch | +0.047 |
o | +0.045 |
e | +0.045 |
Neg logit contributions | |
Everyone | -0.041 |
der | -0.040 |
horizon | -0.040 |
Afterwards | -0.040 |
int | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
horizon | +0.035 |
Afterwards | +0.034 |
rily | +0.034 |
Everyone | +0.033 |
der | +0.032 |
Neg logit contributions | |
w | -0.029 |
prise | -0.029 |
o | -0.029 |
e | -0.028 |
a | -0.028 |