TOP ACTIVATIONS
MAX = 10.011

One day , a little boy named Tim found a box
One day , a little boy named Tim went to the
One day , a little boy named Tim went for a
upon a time , a boy named Tim went to visit
One day , a little boy named Tim went to the
<|endoftext|> One day , a boy named Tim went to the
<|endoftext|> One day , a boy named Tim found a microphone
One day , a little boy named Tim went for a
<|endoftext|> One day , a boy named Tim found a toy
One day , a little boy named Tim went to the
upon a time , a boy named Tim my went outside
One day , a little boy named Tom went to the
One day , a little boy named Tim found a long
One day , a little boy named Tim found a sc
One day , a little boy named Tim found a magic
<|endoftext|> One day , a boy named Tim found a big
One day , a little boy named Tim found a filthy
sunny day , a little boy named Tim went to the
One day , a little boy named Tim had a toy
One day , a little boy named Tim found some clay

MIN ACTIVATIONS
MIN = -9.516

using them ,' Jack said . ' And don 't forget
r ut and pand an and curry leaf and ne em
moan came from the corner . It was the lady 's
store ', his dad said . John was
words very clearly and slowly . She first explained about shapes
the stairs ,' he replied . His uncle smiled
so interested in their language . J ax smiled and replied
that said " Free Candy ". A man with a beard
discover " written on it . Lu cy was
out and began to speak . The fle a
aces , grape brace lets , and grape crown s .
' Wow !' he said . ' That 's so cool
one of them and grinned . It tasted so good !
" sign on the wall . He looked around the store
and cl apped even louder . Now it was time for
en ug reek and mustard and hors er adish and was
pouring out of the cane ! The little boy was so
feel very puzzled and confused . Suddenly , from
4 , 5 , 6 . Mia picked out her favorite
for what they believe in - something that Gina wanted to

INTERVAL 5.129 - 10.011
CONTAINS 1.058%

meal together . <|endoftext|> Once upon a time , there was
until it was over . <|endoftext|> Once upon a time ,
way . <|endoftext|> Once upon a time , in a small
mail , but I don 't know who it 's from
boy named Alec . Alec was an eager little boy with

INTERVAL 0.247 - 5.129
CONTAINS 43.482%

box was very useful for you ." The man
't believe how big it was ! Everywhere she looked ,
. At the top , she looked around and smiled .
even when she was deaf to her mom my 's reminders
But then , a little boy of three years old came

INTERVAL -4.634 - 0.247
CONTAINS 54.338%

problems won 't solve them . So , she decided to
use these . They are prick ly and fun ."
Lu cy 's friend , a dog named Max ,
. The car hit Lily and Ben and made them fall
, a spider !" she said . Max was

INTERVAL -9.516 - -4.634
CONTAINS 1.123%

playing and shaking his bell , it suddenly broke . The
, but it didn 't . Mary was sad that the
fierce animal inside the chamber , ready to defend them against
off to the living room . They both had fun playing
her what he could do . Sammy was so worried ,
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1043
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 ID257
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 ID3091
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
 ï¿½-0.046
der-0.043
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1816
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 ID284
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 ID262
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
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1816
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 ID329
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 ID257
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 ID2402
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 ID257
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 ID640
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 ID11
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 ID257
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 ID2933
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 ID3706
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 ID5045
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 ID1816
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 ID284
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 ID3187
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
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1816
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 ID284
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 ID262
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 ID50256
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
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID2933
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 ID3706
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 ID5045
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 ID1816
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 ID284
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 ID262
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 ID50256
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
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID2933
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 ID3706
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 ID5045
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 ID1043
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 ID257
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 ID21822
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
 ï¿½-0.044
 '-0.043
 int-0.042
der-0.041
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1816
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 ID329
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 ID257
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 ID50256
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
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID2933
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 ID3706
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 ID5045
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 ID1043
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 ID257
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 ID13373
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
 ï¿½-0.046
 int-0.045
 "-0.043
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1816
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 ID284
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 ID262
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 ID2402
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 ID257
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 ID640
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 ID11
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 ID257
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 ID2933
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 ID3706
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 ID5045
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
Tokenmy
Token ID1820
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 ID1816
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 ID2354
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
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID4186
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 ID1816
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 ID284
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 ID262
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
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1043
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 ID257
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 ID890
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
 ï¿½-0.047
 "-0.045
 int-0.045
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1043
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 ID257
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 ID629
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
 ï¿½-0.048
 '-0.047
 int-0.045
der-0.044
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1043
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 ID257
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 ID5536
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
 ï¿½-0.047
 '-0.046
 int-0.046
der-0.044
Token<|endoftext|>
Token ID50256
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
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID2933
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 ID3706
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 ID5045
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 ID1043
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 ID257
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 ID1263
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
 ï¿½-0.044
 int-0.044
der-0.042
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1043
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 ID257
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 ID35677
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
 ï¿½-0.050
 '-0.050
 int-0.049
der-0.047
Token sunny
Token ID27737
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1816
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 ID284
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 ID262
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
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID550
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 ID257
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 ID13373
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
 ï¿½-0.044
 '-0.043
 But-0.042
 attent-0.042
TokenOne
Token ID3198
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID3706
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 ID5045
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 ID1043
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 ID617
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 ID21558
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 ID1262
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 ID606
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 ID4032
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 ID3619
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 ID531
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 ID13
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 ID705
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
TokenAnd
Token ID1870
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 ID836
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 ID470
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 ID6044
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
Tokenr
Token ID81
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
Tokenut
Token ID315
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 ID290
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 ID19798
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
Tokenan
Token ID272
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 ID290
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 ID34611
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 ID12835
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 ID290
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 ID497
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
Tokenem
Token ID368
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 ID44567
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 ID1625
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 ID422
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 ID262
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 ID5228
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 ID13
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 ID632
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 ID373
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 ID262
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 ID10846
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 ID338
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 ID3650
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 ID3256
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 ID465
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 ID9955
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 ID531
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 ID13
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 ID220
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 ID198
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 ID198
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
TokenJohn
Token ID7554
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 ID373
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 ID2456
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 ID845
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 ID4084
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 ID290
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 ID6364
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 ID13
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 ID1375
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 ID717
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 ID4893
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 ID546
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 ID15268
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 ID262
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 ID16046
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 ID4032
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 ID339
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 ID8712
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 ID13
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 ID198
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 ID198
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
TokenHis
Token ID6653
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 ID7711
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 ID13541
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 ID523
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 ID4609
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 ID287
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 ID511
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 ID3303
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 ID13
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 ID449
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
Tokenax
Token ID897
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 ID13541
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 ID290
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 ID8712
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 ID326
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 ID531
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 ID366
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
TokenFree
Token ID11146
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 ID24680
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 ID1911
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 ID317
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 ID582
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 ID351
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 ID257
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 ID21213
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 ID7073
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 ID1
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 ID3194
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 ID319
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 ID340
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 ID13
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 ID198
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 ID198
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
TokenLu
Token ID25596
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
Tokency
Token ID948
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 ID373
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 ID503
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 ID290
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 ID2540
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 ID284
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 ID2740
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 ID13
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 ID198
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 ID198
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
TokenThe
Token ID464
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 ID5104
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
Tokena
Token ID64
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
Tokenaces
Token ID2114
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 ID11
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 ID30777
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 ID22581
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
Tokenlets
Token ID5289
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 ID11
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 ID290
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 ID30777
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 ID12389
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
Tokens
Token ID82
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 ID13
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 ID705
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
TokenWow
Token ID22017
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 ID13679
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 ID339
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 ID531
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 ID13
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 ID705
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
TokenThat
Token ID2504
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 ID338
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 ID523
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 ID3608
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 ID530
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 ID286
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 ID606
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 ID290
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 ID36268
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 ID13
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 ID632
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 ID29187
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 ID523
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 ID922
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 ID0
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 ID1
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 ID1051
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 ID319
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 ID262
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 ID3355
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 ID13
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 ID679
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 ID3114
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 ID1088
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 ID262
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 ID3650
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 ID290
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 ID537
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
Tokenapped
Token ID6320
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 ID772
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 ID27089
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 ID13
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 ID2735
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 ID340
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 ID373
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 ID640
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 ID329
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
Tokenen
Token ID268
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
Tokenug
Token ID1018
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
Tokenreek
Token ID10316
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 ID290
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 ID33694
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 ID290
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 ID45334
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
Tokener
Token ID263
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
Tokenadish
Token ID48563
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 ID290
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 ID373
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 ID23147
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 ID503
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 ID286
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 ID262
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 ID33009
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 ID0
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 ID383
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 ID1310
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 ID2933
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 ID373
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 ID523
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 ID1254
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 ID845
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 ID36907
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 ID290
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 ID10416
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 ID13
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 ID198
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 ID198
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
TokenSuddenly
Token ID38582
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 ID11
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 ID422
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 ID604
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 ID11
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 ID642
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 ID11
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 ID718
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 ID13
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 ID32189
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 ID6497
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 ID503
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 ID607
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 ID4004
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 ID329
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 ID644
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 ID484
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 ID1975
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 ID287
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 ID532
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 ID1223
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 ID326
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 ID43002
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 ID2227
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 ID284
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 ID9799
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 ID1978
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 ID13
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 ID50256
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
TokenOnce
Token ID7454
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 ID2402
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 ID257
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 ID640
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 ID11
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 ID612
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 ID373
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 ID1566
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 ID340
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 ID373
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 ID625
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 ID13
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 ID50256
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
TokenOnce
Token ID7454
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 ID2402
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 ID257
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 ID640
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 ID11
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 ID835
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 ID13
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 ID50256
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
TokenOnce
Token ID7454
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 ID2402
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 ID257
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 ID640
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 ID11
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 ID287
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 ID257
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 ID1402
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 ID6920
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 ID11
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 ID475
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 ID314
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 ID836
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 ID470
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 ID760
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 ID508
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 ID340
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 ID338
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 ID422
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 ID2933
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 ID3706
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 ID38285
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 ID13
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 ID38285
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 ID373
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 ID281
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 ID11069
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 ID1310
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 ID2933
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 ID351
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 ID3091
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 ID373
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 ID845
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 ID4465
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 ID329
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 ID345
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 ID526
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 ID198
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 ID198
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
TokenThe
Token ID464
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 ID582
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 ID470
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 ID1975
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 ID703
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 ID1263
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 ID340
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 ID373
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 ID0
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 ID48201
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 ID673
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 ID3114
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 ID11
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 ID13
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 ID1629
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 ID262
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 ID1353
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 ID11
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 ID673
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 ID3114
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 ID1088
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 ID290
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 ID13541
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 ID13
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 ID772
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 ID618
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 ID673
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 ID373
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 ID21815
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 ID284
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 ID607
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 ID1995
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
Tokenmy
Token ID1820
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 ID338
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 ID40687
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
TokenBut
Token ID1537
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 ID788
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 ID11
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 ID257
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 ID1310
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 ID2933
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 ID286
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 ID1115
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 ID812
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 ID1468
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 ID1625
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 ID2761
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 ID1839
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 ID470
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 ID8494
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 ID606
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 ID13
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 ID1406
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 ID11
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 ID673
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 ID3066
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 ID284
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 ID779
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 ID777
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 ID13
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 ID1119
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 ID389
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 ID41409
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
Tokenly
Token ID306
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 ID290
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 ID1257
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 ID526
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 ID198
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 ID198
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
TokenLu
Token ID25596
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
Tokency
Token ID948
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 ID338
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 ID1545
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 ID11
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 ID257
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 ID3290
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 ID3706
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
 ï¿½-0.037
 Then-0.036
 '-0.036
der-0.035
Token Max
Token ID5436
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 ID11
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
 ï¿½-0.026
 '-0.025
Token.
Token ID13
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 ID383
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 ID1097
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 ID2277
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 ID20037
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 ID290
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 ID3932
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 ID290
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 ID925
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 ID606
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 ID2121
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 ID11
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 ID257
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 ID19230
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 ID2474
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 ID673
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 ID531
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 ID13
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 ID198
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 ID198
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
TokenMax
Token ID11518
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 ID373
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
 ï¿½-0.049
 After-0.048
Token playing
Token ID2712
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 ID290
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 ID17275
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 ID465
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 ID8966
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 ID11
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 ID340
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 ID6451
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 ID6265
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 ID13
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 ID383
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 ID11
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 ID475
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 ID340
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 ID1422
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 ID470
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 ID13
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 ID5335
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 ID373
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 ID6507
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 ID326
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 ID262
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 ID14800
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 ID5044
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 ID2641
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 ID262
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 ID11847
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 ID11
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 ID3492
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 ID284
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 ID4404
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 ID606
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 ID1028
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 ID572
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 ID284
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 ID262
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 ID2877
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 ID2119
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 ID13
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 ID1119
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 ID1111
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 ID550
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 ID1257
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 ID2712
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 ID607
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 ID644
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 ID339
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 ID714
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 ID466
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 ID13
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 ID44067
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 ID373
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 ID523
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 ID7960
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 ID11
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