TOP ACTIVATIONS
MAX = 18.646

to take them to the charity shop , where other children
know the box was for charity . They thought it was
She drove away to the charity shop . L
. It belongs to the charity . We provide clothes and
. They belong to a charity that helps poor kids .
all your toys to a charity that helps children in need
! They are for the charity ! I was going to
" Let 's go , mate y !" Ben said .
" Ar rr , mate y , give me your
, " Ah oy , mate y ! Land ho !"
You can be the first mate today ." They
shouting " Ah oy , mate y !" and " Sh
It needs to find a mate and lay eggs . Then
" Ar rr , mate y , let 's sail
" Ar rr , mate y , this is our
" Ar rr , mate y , we are the
said , " Ah oy mate y !" to the pirate
say ' Ah oy , mate y !' and ' Land
, " Ah oy , mate y . I 'm Captain
shouted , " Ar gh mate ys !" The

MIN ACTIVATIONS
MIN = -16.020

â M az zy could barely contain her
ors . The other r az ors would laugh and say
the park , the g az eb o would be there
stand like the other r az ors . The other r
. She knew that r az ors were very sharp and
he would never touch r az ors again . He said
mom said . " R az ors are not toys ,
stand like the other r az ors . They laugh at
up tools like delicate r az ors . <|endoftext|> Once upon
a strong lizard named T az . He lived happily among
shapes to design a j az zy picture . Then she
â M az zy was so excited about
One day , T az heard some voices coming from
up . The other r az ors saw this and stopped
no . He said r az ors were sharp and dangerous
was never scared of r az ors again . <|endoftext|> W
the rhythm of a j az zy tune . Everywhere she
that . He thought r az ors were fun and cool
. As they passed T az , the little boy stopped
â M az zy â s

INTERVAL 9.980 - 18.646
CONTAINS 0.432%

about a cave with a treasure inside . The old man
us feel something , or something that reminds us of something
, as he moved his soldiers forward . " You have
. The pilot told him something special ; he said :
. They explored the brilliant coral and watched the fish swimming

INTERVAL 1.313 - 9.980
CONTAINS 34.429%

and his mom my had a brilliant time riding in the
cool . Later that day , Tim my
she replied . " Let 's do it again !"
, and he needed to find a safe place to hide
he made his way , he noticed something strange . He

INTERVAL -7.353 - 1.313
CONTAINS 60.883%

" No !" the little boy yelled . His parents told
Once upon a time , there was a pretty princess .
day , a loud noise came from the village . It
, there was a big bear who loved to play in
whenever he played . One day , Tim my

INTERVAL -16.020 - -7.353
CONTAINS 4.256%

adventure . It went up high on the waves . The
out a small box . It had a colorful sticker on
the x - ray . The doctor was very nice and
What happened ?" her mom my asked . Lily told her
the jungle . But one day , the music was different
Token to
Token ID284
Feature activation+2.93e+00

Pos logit contributions
 around+0.218
 down+0.197
 air+0.194
cy+0.192
et+0.186
Neg logit contributions
ves-0.175
vern-0.175
ades-0.153
keys-0.153
 mercy-0.151
Token take
Token ID1011
Feature activation+3.15e+00

Pos logit contributions
ves+0.190
vern+0.182
ades+0.179
keys+0.173
 mercy+0.158
Neg logit contributions
 around-0.132
 air-0.122
 down-0.117
|-0.116
cy-0.111
Token them
Token ID606
Feature activation+3.86e+00

Pos logit contributions
ves+0.156
vern+0.152
 backup+0.138
ades+0.137
 mercy+0.135
Neg logit contributions
 around-0.181
cy-0.171
 air-0.166
rated-0.165
et-0.163
Token to
Token ID284
Feature activation+2.95e+00

Pos logit contributions
ves+0.250
vern+0.244
ades+0.226
keys+0.222
 mercy+0.222
Neg logit contributions
 around-0.182
 down-0.158
cy-0.155
 air-0.153
et-0.147
Token the
Token ID262
Feature activation-4.03e+00

Pos logit contributions
ves+0.203
vern+0.196
ades+0.191
keys+0.188
 mercy+0.175
Neg logit contributions
 around-0.123
 air-0.110
 down-0.108
|-0.102
cy-0.100
Token charity
Token ID11016
Feature activation+1.72e+01

Pos logit contributions
 around+0.196
 air+0.185
cy+0.174
 down+0.174
et+0.161
Neg logit contributions
ves-0.260
vern-0.246
keys-0.232
ades-0.230
 mercy-0.209
Token shop
Token ID6128
Feature activation+3.85e+00

Pos logit contributions
ves+0.851
vern+0.833
ades+0.760
 backup+0.757
 mercy+0.734
Neg logit contributions
 around-0.964
cy-0.904
rated-0.893
 air-0.884
|-0.877
Token,
Token ID11
Feature activation+9.30e-01

Pos logit contributions
ves+0.253
vern+0.251
ades+0.230
 mercy+0.226
keys+0.223
Neg logit contributions
 around-0.172
cy-0.153
 down-0.149
 air-0.149
et-0.142
Token where
Token ID810
Feature activation+6.04e+00

Pos logit contributions
ves+0.062
vern+0.062
ades+0.057
keys+0.055
 mercy+0.055
Neg logit contributions
 around-0.042
 down-0.036
 air-0.036
cy-0.035
et-0.034
Token other
Token ID584
Feature activation+1.33e+00

Pos logit contributions
vern+0.246
ves+0.240
ades+0.213
 mercy+0.202
 backup+0.201
Neg logit contributions
 around-0.423
 air-0.385
 down-0.384
cy-0.383
et-0.366
Token children
Token ID1751
Feature activation-6.41e-01

Pos logit contributions
vern+0.082
ves+0.081
ades+0.073
 mercy+0.071
 backup+0.070
Neg logit contributions
 around-0.067
 air-0.061
cy-0.058
 down-0.058
et-0.054
Token know
Token ID760
Feature activation+1.72e+00

Pos logit contributions
vern+0.429
 mercy+0.410
ves+0.396
 backup+0.385
 forgiveness+0.378
Neg logit contributions
 around-0.424
cy-0.420
amp-0.412
ening-0.392
 down-0.390
Token the
Token ID262
Feature activation-4.03e+00

Pos logit contributions
vern+0.084
ves+0.081
ades+0.074
 backup+0.072
 mercy+0.070
Neg logit contributions
 around-0.108
 air-0.097
 down-0.095
cy-0.092
et-0.092
Token box
Token ID3091
Feature activation-2.11e-01

Pos logit contributions
 around+0.248
 air+0.231
cy+0.224
 down+0.223
et+0.215
Neg logit contributions
ves-0.196
vern-0.189
ades-0.171
keys-0.169
 mercy-0.165
Token was
Token ID373
Feature activation+1.86e+00

Pos logit contributions
 around+0.010
cy+0.009
 air+0.009
 down+0.008
et+0.008
Neg logit contributions
ves-0.013
vern-0.013
ades-0.012
 mercy-0.012
 backup-0.012
Token for
Token ID329
Feature activation-1.81e+00

Pos logit contributions
ves+0.101
vern+0.099
ades+0.090
 mercy+0.088
 backup+0.087
Neg logit contributions
 around-0.102
cy-0.093
 air-0.092
 down-0.091
et-0.089
Token charity
Token ID11016
Feature activation+1.72e+01

Pos logit contributions
 around+0.095
 air+0.086
 down+0.084
cy+0.080
et+0.079
Neg logit contributions
vern-0.103
ves-0.102
ades-0.093
 mercy-0.091
keys-0.090
Token.
Token ID13
Feature activation-3.17e-01

Pos logit contributions
ves+1.043
vern+1.027
ades+0.937
 mercy+0.926
 backup+0.922
Neg logit contributions
 around-0.801
cy-0.746
 air-0.727
 down-0.716
|-0.706
Token They
Token ID1119
Feature activation-1.78e+00

Pos logit contributions
 around+0.013
et+0.012
rated+0.012
cy+0.011
ening+0.011
Neg logit contributions
ves-0.021
vern-0.020
 backup-0.019
ades-0.019
 forgiveness-0.019
Token thought
Token ID1807
Feature activation-1.33e+00

Pos logit contributions
 around+0.080
cy+0.071
 air+0.071
 down+0.068
et+0.068
Neg logit contributions
ves-0.115
vern-0.115
ades-0.106
 backup-0.103
 mercy-0.102
Token it
Token ID340
Feature activation-4.70e+00

Pos logit contributions
 around+0.074
 air+0.065
 down+0.064
et+0.061
cy+0.061
Neg logit contributions
vern-0.073
ves-0.071
ades-0.067
 mercy-0.065
keys-0.064
Token was
Token ID373
Feature activation+1.87e+00

Pos logit contributions
 around+0.254
 air+0.243
cy+0.240
 down+0.237
|+0.233
Neg logit contributions
ves-0.246
vern-0.225
ades-0.208
 mercy-0.204
 forgiveness-0.204
Token She
Token ID1375
Feature activation-5.68e+00

Pos logit contributions
rated+0.014
 around+0.014
cy+0.014
et+0.014
ening+0.013
Neg logit contributions
ves-0.024
vern-0.023
 backup-0.022
His-0.021
ades-0.021
Token drove
Token ID10357
Feature activation+3.59e+00

Pos logit contributions
 around+0.240
cy+0.203
 air+0.201
et+0.199
 down+0.186
Neg logit contributions
vern-0.416
ves-0.370
ades-0.360
 backup-0.357
keys-0.353
Token away
Token ID1497
Feature activation-4.70e+00

Pos logit contributions
ves+0.185
vern+0.169
 backup+0.165
 mercy+0.156
ades+0.155
Neg logit contributions
cy-0.187
|-0.183
rated-0.180
 air-0.175
amp-0.174
Token to
Token ID284
Feature activation+2.92e+00

Pos logit contributions
 around+0.215
cy+0.194
 air+0.191
 down+0.186
et+0.184
Neg logit contributions
ves-0.296
vern-0.292
ades-0.268
 mercy-0.264
 backup-0.262
Token the
Token ID262
Feature activation-4.05e+00

Pos logit contributions
ves+0.177
vern+0.175
ades+0.159
 mercy+0.158
 backup+0.156
Neg logit contributions
 around-0.141
cy-0.128
 air-0.126
 down-0.124
et-0.121
Token charity
Token ID11016
Feature activation+1.72e+01

Pos logit contributions
 around+0.199
 air+0.179
cy+0.179
 down+0.175
et+0.170
Neg logit contributions
ves-0.247
vern-0.243
ades-0.222
 mercy-0.216
keys-0.216
Token shop
Token ID6128
Feature activation+3.82e+00

Pos logit contributions
ves+0.884
vern+0.864
 backup+0.793
ades+0.791
 forgiveness+0.764
Neg logit contributions
 around-0.904
rated-0.872
cy-0.863
|-0.852
 air-0.823
Token.
Token ID13
Feature activation-3.38e-01

Pos logit contributions
ves+0.251
vern+0.249
ades+0.229
 mercy+0.225
 backup+0.223
Neg logit contributions
 around-0.166
cy-0.147
 air-0.146
 down-0.143
et-0.139
Token
Token ID198
Feature activation+7.61e-01

Pos logit contributions
 around+0.017
rated+0.017
et+0.017
ening+0.016
cy+0.016
Neg logit contributions
ves-0.018
vern-0.018
 backup-0.017
His-0.016
 forgiveness-0.016
Token
Token ID198
Feature activation+7.67e-01

Pos logit contributions
vern+0.047
ves+0.046
 mercy+0.043
ades+0.043
keys+0.042
Neg logit contributions
 around-0.036
 air-0.031
cy-0.031
 down-0.031
|-0.030
TokenL
Token ID43
Feature activation+3.02e+00

Pos logit contributions
vern+0.039
 mercy+0.038
 forgiveness+0.036
ves+0.036
keys+0.035
Neg logit contributions
 around-0.044
 air-0.039
amp-0.039
|-0.039
cy-0.039
Token.
Token ID13
Feature activation-3.81e-01

Pos logit contributions
 around+0.013
cy+0.012
 air+0.012
 down+0.012
et+0.011
Neg logit contributions
ves-0.016
vern-0.016
ades-0.014
 backup-0.014
 mercy-0.014
Token It
Token ID632
Feature activation-9.38e+00

Pos logit contributions
 around+0.017
et+0.016
cy+0.016
rated+0.015
ening+0.015
Neg logit contributions
vern-0.023
ves-0.023
 backup-0.022
 forgiveness-0.021
 mercy-0.021
Token belongs
Token ID14448
Feature activation+4.59e-01

Pos logit contributions
 around+0.430
cy+0.389
 air+0.383
 down+0.377
et+0.370
Neg logit contributions
ves-0.586
vern-0.567
ades-0.521
keys-0.519
 mercy-0.517
Token to
Token ID284
Feature activation+2.90e+00

Pos logit contributions
ves+0.023
vern+0.023
ades+0.020
 mercy+0.020
keys+0.020
Neg logit contributions
 around-0.028
cy-0.025
 down-0.025
 air-0.025
et-0.024
Token the
Token ID262
Feature activation-4.06e+00

Pos logit contributions
vern+0.172
ves+0.169
ades+0.157
 mercy+0.147
 backup+0.146
Neg logit contributions
 around-0.148
 air-0.134
 down-0.130
cy-0.126
et-0.124
Token charity
Token ID11016
Feature activation+1.72e+01

Pos logit contributions
 around+0.211
cy+0.192
 air+0.191
 down+0.187
et+0.183
Neg logit contributions
ves-0.232
vern-0.229
ades-0.209
 mercy-0.204
 backup-0.202
Token.
Token ID13
Feature activation-3.64e-01

Pos logit contributions
ves+0.905
vern+0.885
ades+0.808
keys+0.793
 mercy+0.786
Neg logit contributions
 around-0.926
cy-0.870
 air-0.846
et-0.835
 down-0.835
Token We
Token ID775
Feature activation+4.73e-01

Pos logit contributions
 around+0.015
cy+0.014
et+0.014
rated+0.013
 air+0.013
Neg logit contributions
ves-0.024
vern-0.024
 backup-0.022
 forgiveness-0.022
 mercy-0.022
Token provide
Token ID2148
Feature activation+6.82e+00

Pos logit contributions
ves+0.027
vern+0.027
 mercy+0.025
keys+0.025
 backup+0.024
Neg logit contributions
 around-0.022
 air-0.020
 down-0.020
ening-0.020
et-0.020
Token clothes
Token ID8242
Feature activation+6.73e+00

Pos logit contributions
vern+0.416
ves+0.411
ades+0.385
keys+0.365
 mercy+0.356
Neg logit contributions
 around-0.351
 air-0.309
 down-0.303
cy-0.285
et-0.277
Token and
Token ID290
Feature activation-1.59e+00

Pos logit contributions
ves+0.455
vern+0.452
 mercy+0.416
ades+0.416
 backup+0.412
Neg logit contributions
 around-0.299
 down-0.252
cy-0.247
 air-0.243
et-0.229
Token.
Token ID13
Feature activation-4.15e-01

Pos logit contributions
ves+0.347
vern+0.343
ades+0.315
 mercy+0.310
 backup+0.308
Neg logit contributions
 around-0.251
cy-0.230
 air-0.225
 down-0.217
et-0.216
Token They
Token ID1119
Feature activation-1.88e+00

Pos logit contributions
 around+0.017
cy+0.015
 air+0.015
 down+0.015
et+0.014
Neg logit contributions
ves-0.028
vern-0.028
ades-0.026
 mercy-0.025
 backup-0.025
Token belong
Token ID5594
Feature activation+1.96e+00

Pos logit contributions
 around+0.078
cy+0.068
 air+0.068
 down+0.066
et+0.064
Neg logit contributions
ves-0.128
vern-0.127
ades-0.117
 mercy-0.115
 backup-0.114
Token to
Token ID284
Feature activation+2.85e+00

Pos logit contributions
ves+0.118
vern+0.114
ades+0.105
keys+0.102
 mercy+0.101
Neg logit contributions
 around-0.106
 down-0.094
cy-0.093
 air-0.089
et-0.084
Token a
Token ID257
Feature activation+4.72e+00

Pos logit contributions
ves+0.169
vern+0.168
ades+0.154
 mercy+0.150
 backup+0.149
Neg logit contributions
 around-0.142
 air-0.127
cy-0.127
 down-0.125
et-0.122
Token charity
Token ID11016
Feature activation+1.71e+01

Pos logit contributions
ves+0.259
vern+0.253
ades+0.233
 mercy+0.228
keys+0.222
Neg logit contributions
 around-0.260
 air-0.236
cy-0.234
 down-0.232
|-0.219
Token that
Token ID326
Feature activation+4.06e+00

Pos logit contributions
ves+0.921
vern+0.906
ades+0.824
 backup+0.810
 mercy+0.808
Neg logit contributions
 around-0.903
cy-0.845
 air-0.820
rated-0.813
 down-0.810
Token helps
Token ID5419
Feature activation+4.21e+00

Pos logit contributions
ves+0.246
vern+0.240
ades+0.220
 mercy+0.216
 backup+0.216
Neg logit contributions
 around-0.192
cy-0.175
 air-0.171
 down-0.168
et-0.167
Token poor
Token ID3595
Feature activation+2.13e+00

Pos logit contributions
vern+0.249
ves+0.248
ades+0.227
 mercy+0.221
 backup+0.217
Neg logit contributions
 around-0.214
 air-0.189
 down-0.187
cy-0.186
et-0.180
Token kids
Token ID3988
Feature activation-8.63e-01

Pos logit contributions
vern+0.129
ves+0.126
ades+0.116
 backup+0.113
 mercy+0.112
Neg logit contributions
 around-0.106
 air-0.099
 down-0.094
cy-0.092
et-0.087
Token.
Token ID13
Feature activation-4.09e-01

Pos logit contributions
 around+0.041
cy+0.036
 air+0.035
 down+0.035
et+0.034
Neg logit contributions
ves-0.054
vern-0.053
ades-0.049
 mercy-0.048
 backup-0.048
Token all
Token ID477
Feature activation-2.48e+00

Pos logit contributions
ves+0.396
vern+0.392
ades+0.359
keys+0.350
 mercy+0.340
Neg logit contributions
 around-0.381
 air-0.341
 down-0.335
cy-0.324
et-0.318
Token your
Token ID534
Feature activation+2.74e+00

Pos logit contributions
 around+0.126
 air+0.112
 down+0.107
cy+0.104
et+0.101
Neg logit contributions
ves-0.155
vern-0.153
ades-0.142
keys-0.139
 mercy-0.136
Token toys
Token ID14958
Feature activation+6.50e+00

Pos logit contributions
ves+0.138
vern+0.132
ades+0.121
keys+0.117
 mercy+0.113
Neg logit contributions
 around-0.169
 air-0.158
cy-0.151
 down-0.150
et-0.144
Token to
Token ID284
Feature activation+2.78e+00

Pos logit contributions
ves+0.432
vern+0.422
ades+0.396
 mercy+0.391
keys+0.383
Neg logit contributions
 around-0.300
 down-0.256
cy-0.248
 air-0.247
et-0.235
Token a
Token ID257
Feature activation+4.63e+00

Pos logit contributions
ves+0.166
vern+0.164
ades+0.154
keys+0.146
 mercy+0.144
Neg logit contributions
 around-0.139
 air-0.123
 down-0.120
cy-0.117
|-0.115
Token charity
Token ID11016
Feature activation+1.70e+01

Pos logit contributions
ves+0.255
vern+0.244
ades+0.223
keys+0.217
 mercy+0.215
Neg logit contributions
 around-0.260
 air-0.234
 down-0.233
cy-0.230
|-0.216
Token that
Token ID326
Feature activation+3.95e+00

Pos logit contributions
ves+1.006
vern+0.992
ades+0.909
 backup+0.893
 mercy+0.891
Neg logit contributions
 around-0.790
cy-0.743
 air-0.719
rated-0.709
|-0.708
Token helps
Token ID5419
Feature activation+4.08e+00

Pos logit contributions
ves+0.250
vern+0.244
ades+0.224
 mercy+0.221
 backup+0.220
Neg logit contributions
 around-0.176
cy-0.159
 air-0.156
 down-0.153
et-0.152
Token children
Token ID1751
Feature activation-8.53e-01

Pos logit contributions
vern+0.243
ves+0.242
ades+0.222
 mercy+0.216
 backup+0.213
Neg logit contributions
 around-0.206
 air-0.181
 down-0.179
cy-0.176
et-0.171
Token in
Token ID287
Feature activation-6.85e+00

Pos logit contributions
 around+0.040
 down+0.034
cy+0.034
 air+0.034
et+0.032
Neg logit contributions
ves-0.055
vern-0.054
ades-0.050
 mercy-0.050
 backup-0.049
Token need
Token ID761
Feature activation-9.55e-01

Pos logit contributions
 around+0.321
 air+0.284
cy+0.280
 down+0.278
et+0.263
Neg logit contributions
ves-0.435
vern-0.424
ades-0.396
keys-0.387
 mercy-0.384
Token!
Token ID0
Feature activation+1.24e-01

Pos logit contributions
 around+0.015
 air+0.013
cy+0.013
 down+0.013
et+0.012
Neg logit contributions
ves-0.023
vern-0.023
ades-0.021
 mercy-0.021
 backup-0.020
Token They
Token ID1119
Feature activation-1.97e+00

Pos logit contributions
ves+0.009
vern+0.008
 backup+0.008
ades+0.008
 forgiveness+0.008
Neg logit contributions
 around-0.005
et-0.004
rated-0.004
 air-0.004
cy-0.004
Token are
Token ID389
Feature activation+4.69e-01

Pos logit contributions
 around+0.084
cy+0.076
 down+0.075
 air+0.073
et+0.072
Neg logit contributions
ves-0.128
vern-0.126
ades-0.115
 mercy-0.115
 backup-0.114
Token for
Token ID329
Feature activation-2.02e+00

Pos logit contributions
ves+0.025
vern+0.025
ades+0.022
 mercy+0.022
 backup+0.022
Neg logit contributions
 around-0.026
cy-0.024
 air-0.024
 down-0.023
et-0.023
Token the
Token ID262
Feature activation-4.21e+00

Pos logit contributions
 around+0.098
 air+0.088
 down+0.086
cy+0.077
 alone+0.077
Neg logit contributions
vern-0.125
ves-0.124
ades-0.114
His-0.109
keys-0.108
Token charity
Token ID11016
Feature activation+1.70e+01

Pos logit contributions
 around+0.243
cy+0.222
 air+0.222
 down+0.217
et+0.213
Neg logit contributions
ves-0.217
vern-0.213
ades-0.192
 mercy-0.188
 backup-0.185
Token!
Token ID0
Feature activation+1.28e-01

Pos logit contributions
ves+0.990
vern+0.977
ades+0.891
 backup+0.880
 mercy+0.877
Neg logit contributions
 around-0.803
cy-0.747
|-0.731
rated-0.730
 air-0.722
Token I
Token ID314
Feature activation+1.23e+00

Pos logit contributions
ves+0.009
vern+0.009
 backup+0.008
ades+0.008
 forgiveness+0.008
Neg logit contributions
 around-0.005
et-0.004
cy-0.004
rated-0.004
 air-0.004
Token was
Token ID373
Feature activation+1.70e+00

Pos logit contributions
ves+0.078
vern+0.076
ades+0.070
 mercy+0.070
 backup+0.069
Neg logit contributions
 around-0.054
 air-0.049
 down-0.048
cy-0.048
et-0.047
Token going
Token ID1016
Feature activation-3.70e+00

Pos logit contributions
ves+0.098
vern+0.097
ades+0.088
 backup+0.087
 mercy+0.087
Neg logit contributions
 around-0.085
cy-0.079
 air-0.077
 down-0.075
et-0.074
Token to
Token ID284
Feature activation+2.76e+00

Pos logit contributions
 around+0.234
cy+0.215
 air+0.213
 down+0.212
et+0.207
Neg logit contributions
ves-0.171
vern-0.168
ades-0.149
 mercy-0.146
keys-0.143
Token"
Token ID1
Feature activation+1.27e+01

Pos logit contributions
cy+0.303
 around+0.296
et+0.290
|+0.287
 air+0.282
Neg logit contributions
ves-0.281
vern-0.277
 mercy-0.243
keys-0.238
 forgiveness-0.234
TokenLet
Token ID5756
Feature activation-1.28e+00

Pos logit contributions
vern+0.776
ves+0.732
ades+0.701
 backup+0.684
 instincts+0.677
Neg logit contributions
 around-0.618
cy-0.596
 air-0.565
|-0.554
 down-0.538
Token's
Token ID338
Feature activation+3.12e+00

Pos logit contributions
 around+0.057
cy+0.050
 air+0.050
 down+0.049
et+0.047
Neg logit contributions
ves-0.084
vern-0.084
ades-0.077
 mercy-0.076
 backup-0.075
Token go
Token ID467
Feature activation+9.86e-01

Pos logit contributions
vern+0.201
ves+0.198
ades+0.182
 backup+0.175
 mercy+0.174
Neg logit contributions
 around-0.151
 down-0.133
cy-0.130
 air-0.129
et-0.119
Token,
Token ID11
Feature activation+1.42e+00

Pos logit contributions
ves+0.062
vern+0.061
ades+0.056
 mercy+0.055
keys+0.055
Neg logit contributions
 around-0.048
cy-0.042
 down-0.042
 air-0.041
et-0.039
Token mate
Token ID16133
Feature activation+1.70e+01

Pos logit contributions
vern+0.089
ves+0.088
ades+0.082
 mercy+0.078
 backup+0.076
Neg logit contributions
 around-0.069
 down-0.062
 air-0.060
cy-0.060
et-0.055
Tokeny
Token ID88
Feature activation-4.62e+00

Pos logit contributions
ves+1.194
vern+1.176
ades+1.103
 mercy+1.081
keys+1.065
Neg logit contributions
 around-0.629
 air-0.557
cy-0.545
 down-0.527
et-0.518
Token!"
Token ID2474
Feature activation-5.49e-01

Pos logit contributions
 around+0.212
 air+0.187
cy+0.187
 down+0.184
et+0.176
Neg logit contributions
vern-0.294
ves-0.294
ades-0.269
 mercy-0.263
 backup-0.262
Token Ben
Token ID3932
Feature activation-3.50e+00

Pos logit contributions
 around+0.032
 down+0.028
 air+0.028
cy+0.027
|+0.026
Neg logit contributions
vern-0.031
ves-0.029
ades-0.027
 mercy-0.026
 backup-0.026
Token said
Token ID531
Feature activation+1.63e+00

Pos logit contributions
 around+0.170
 air+0.150
cy+0.148
 down+0.147
et+0.141
Neg logit contributions
vern-0.216
ves-0.216
ades-0.197
 mercy-0.194
 backup-0.193
Token.
Token ID13
Feature activation-2.82e-01

Pos logit contributions
ves+0.115
vern+0.115
ades+0.109
keys+0.106
 backup+0.106
Neg logit contributions
 around-0.069
 down-0.059
cy-0.051
 air-0.050
et-0.049
Token
Token ID198
Feature activation+1.45e+00

Pos logit contributions
ves+0.095
vern+0.094
ades+0.086
 mercy+0.085
keys+0.084
Neg logit contributions
 around-0.086
cy-0.077
 air-0.077
 down-0.075
|-0.073
Token"
Token ID1
Feature activation+9.90e+00

Pos logit contributions
ves+0.062
vern+0.061
 mercy+0.058
 forgiveness+0.055
ades+0.055
Neg logit contributions
 around-0.092
cy-0.087
|-0.087
 air-0.084
 down-0.082
TokenAr
Token ID3163
Feature activation+1.00e+01

Pos logit contributions
vern+0.670
ves+0.656
ades+0.610
 mercy+0.597
 backup+0.589
Neg logit contributions
 around-0.418
cy-0.407
 air-0.388
et-0.364
|-0.364
Tokenrr
Token ID21062
Feature activation+1.28e+00

Pos logit contributions
ves+0.587
vern+0.562
ades+0.520
 forgiveness+0.506
keys+0.495
Neg logit contributions
 around-0.499
et-0.442
cy-0.438
 air-0.436
 down-0.429
Token,
Token ID11
Feature activation+1.10e+00

Pos logit contributions
ves+0.080
vern+0.080
ades+0.073
 mercy+0.072
 backup+0.071
Neg logit contributions
 around-0.059
cy-0.053
 air-0.053
 down-0.052
et-0.051
Token mate
Token ID16133
Feature activation+1.67e+01

Pos logit contributions
vern+0.066
ves+0.066
ades+0.060
keys+0.054
 mercy+0.054
Neg logit contributions
 around-0.057
 down-0.051
 air-0.051
cy-0.048
 through-0.046
Tokeny
Token ID88
Feature activation-4.77e+00

Pos logit contributions
ves+1.064
vern+1.035
ades+0.979
 mercy+0.950
keys+0.932
Neg logit contributions
 around-0.716
 air-0.648
cy-0.630
 down-0.620
|-0.608
Token,
Token ID11
Feature activation+9.65e-01

Pos logit contributions
 around+0.221
cy+0.197
 air+0.196
 down+0.192
et+0.187
Neg logit contributions
ves-0.299
vern-0.296
ades-0.272
 mercy-0.267
 backup-0.265
Token give
Token ID1577
Feature activation+7.56e+00

Pos logit contributions
ves+0.055
vern+0.054
ades+0.049
keys+0.044
 mercy+0.043
Neg logit contributions
 around-0.056
 down-0.050
 air-0.049
cy-0.047
 through-0.046
Token me
Token ID502
Feature activation-7.19e-01

Pos logit contributions
vern+0.571
ves+0.569
ades+0.520
keys+0.512
 mercy+0.505
Neg logit contributions
 around-0.290
 air-0.241
 down-0.239
cy-0.231
et-0.219
Token your
Token ID534
Feature activation+2.88e+00

Pos logit contributions
 around+0.038
 down+0.034
et+0.033
 air+0.033
cy+0.031
Neg logit contributions
ves-0.043
vern-0.042
ades-0.038
keys-0.037
 forgiveness-0.036
Token,
Token ID11
Feature activation+9.39e-01

Pos logit contributions
vern+0.096
ves+0.092
 mercy+0.087
 backup+0.085
ades+0.084
Neg logit contributions
 around-0.077
 down-0.067
 air-0.063
 through-0.057
et-0.057
Token "
Token ID366
Feature activation+3.59e+00

Pos logit contributions
ves+0.051
vern+0.051
ades+0.045
 mercy+0.045
 backup+0.044
Neg logit contributions
 around-0.052
 down-0.046
 air-0.046
cy-0.046
et-0.045
TokenAh
Token ID10910
Feature activation+2.62e+00

Pos logit contributions
ves+0.221
vern+0.218
ades+0.201
 mercy+0.196
 backup+0.195
Neg logit contributions
 around-0.172
cy-0.154
 air-0.153
 down-0.150
et-0.147
Tokenoy
Token ID726
Feature activation+5.93e+00

Pos logit contributions
vern+0.138
ves+0.133
ades+0.125
 mercy+0.123
 forgiveness+0.121
Neg logit contributions
 around-0.138
et-0.132
 air-0.129
cy-0.126
 down-0.125
Token,
Token ID11
Feature activation+9.33e-01

Pos logit contributions
ves+0.382
vern+0.378
ades+0.342
 mercy+0.341
 forgiveness+0.336
Neg logit contributions
 around-0.271
cy-0.245
 down-0.242
 air-0.236
et-0.230
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
vern+0.047
ves+0.047
ades+0.042
 mercy+0.039
keys+0.038
Neg logit contributions
 around-0.058
 air-0.053
 down-0.052
cy-0.051
et-0.050
Tokeny
Token ID88
Feature activation-4.86e+00

Pos logit contributions
ves+1.141
vern+1.120
ades+1.066
 mercy+1.027
 backup+1.015
Neg logit contributions
 around-0.627
 air-0.555
 down-0.521
cy-0.521
|-0.516
Token!
Token ID0
Feature activation+3.51e-01

Pos logit contributions
 around+0.223
cy+0.199
 air+0.198
 down+0.194
et+0.189
Neg logit contributions
ves-0.307
vern-0.305
ades-0.279
 mercy-0.275
 backup-0.272
Token Land
Token ID6379
Feature activation-2.95e-01

Pos logit contributions
ves+0.023
vern+0.022
ades+0.021
 backup+0.020
 mercy+0.020
Neg logit contributions
 around-0.015
cy-0.014
 air-0.014
et-0.013
 down-0.013
Token ho
Token ID8169
Feature activation+4.14e+00

Pos logit contributions
 around+0.013
cy+0.012
 air+0.012
 down+0.011
et+0.011
Neg logit contributions
ves-0.019
vern-0.018
ades-0.017
keys-0.017
 backup-0.016
Token!"
Token ID2474
Feature activation-6.98e-01

Pos logit contributions
ves+0.226
vern+0.221
ades+0.202
 backup+0.197
keys+0.195
Neg logit contributions
 around-0.226
cy-0.208
 air-0.205
 down-0.200
et-0.197
Token You
Token ID921
Feature activation-8.66e+00

Pos logit contributions
 around+0.014
cy+0.013
et+0.013
 down+0.012
 air+0.012
Neg logit contributions
ves-0.020
vern-0.020
 backup-0.018
 mercy-0.018
 forgiveness-0.018
Token can
Token ID460
Feature activation-4.80e+00

Pos logit contributions
 around+0.358
cy+0.320
 down+0.313
 air+0.312
et+0.309
Neg logit contributions
ves-0.574
vern-0.573
 backup-0.527
 mercy-0.526
ades-0.525
Token be
Token ID307
Feature activation+3.91e+00

Pos logit contributions
 around+0.216
cy+0.192
 air+0.187
 down+0.185
et+0.180
Neg logit contributions
ves-0.313
vern-0.309
ades-0.284
 mercy-0.278
keys-0.278
Token the
Token ID262
Feature activation-4.01e+00

Pos logit contributions
vern+0.163
ves+0.162
 backup+0.142
ades+0.141
 mercy+0.140
Neg logit contributions
 around-0.253
cy-0.243
rated-0.234
 air-0.234
|-0.233
Token first
Token ID717
Feature activation-2.71e+00

Pos logit contributions
 around+0.263
 air+0.250
cy+0.241
et+0.238
 down+0.237
Neg logit contributions
ves-0.187
vern-0.168
ades-0.151
keys-0.147
 mercy-0.141
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
 around+0.164
 air+0.149
cy+0.146
 down+0.146
et+0.144
Neg logit contributions
vern-0.138
ves-0.133
ades-0.121
 mercy-0.118
keys-0.116
Token today
Token ID1909
Feature activation-6.94e-01

Pos logit contributions
ves+0.987
vern+0.969
ades+0.903
 mercy+0.883
keys+0.876
Neg logit contributions
 around-0.748
 air-0.709
cy-0.674
 down-0.665
|-0.660
Token."
Token ID526
Feature activation-2.60e+00

Pos logit contributions
 around+0.034
cy+0.032
|+0.031
rated+0.031
et+0.031
Neg logit contributions
ves-0.040
vern-0.037
ades-0.035
keys-0.034
 mercy-0.033
Token
Token ID198
Feature activation+7.88e-01

Pos logit contributions
 around+0.120
cy+0.107
 air+0.107
 down+0.105
|+0.099
Neg logit contributions
ves-0.167
vern-0.165
ades-0.151
 mercy-0.149
keys-0.149
Token
Token ID198
Feature activation+7.87e-01

Pos logit contributions
vern+0.051
ves+0.051
keys+0.048
 mercy+0.048
 backup+0.048
Neg logit contributions
 around-0.035
 air-0.030
cy-0.029
 down-0.029
|-0.027
TokenThey
Token ID2990
Feature activation+9.93e+00

Pos logit contributions
vern+0.040
 mercy+0.038
 backup+0.037
 crew+0.037
 instincts+0.037
Neg logit contributions
 around-0.040
cy-0.040
 air-0.038
ny-0.037
he-0.035
Token shouting
Token ID19642
Feature activation+1.07e+00

Pos logit contributions
ves+0.056
vern+0.055
ades+0.050
 mercy+0.049
 backup+0.049
Neg logit contributions
 around-0.046
cy-0.042
 air-0.041
 down-0.040
et-0.040
Token "
Token ID366
Feature activation+3.59e+00

Pos logit contributions
ves+0.070
vern+0.070
ades+0.064
 mercy+0.063
 backup+0.063
Neg logit contributions
 around-0.046
cy-0.041
 air-0.041
 down-0.040
et-0.039
TokenAh
Token ID10910
Feature activation+2.62e+00

Pos logit contributions
ves+0.190
vern+0.178
ades+0.172
keys+0.164
 backup+0.160
Neg logit contributions
 around-0.199
 air-0.180
cy-0.177
 down-0.177
ening-0.171
Tokenoy
Token ID726
Feature activation+5.91e+00

Pos logit contributions
vern+0.121
ves+0.110
 forgiveness+0.108
 mercy+0.107
ades+0.101
Neg logit contributions
 around-0.157
et-0.157
 air-0.148
 down-0.145
cy-0.143
Token,
Token ID11
Feature activation+9.29e-01

Pos logit contributions
ves+0.353
vern+0.350
ades+0.318
 mercy+0.314
 backup+0.309
Neg logit contributions
 around-0.292
cy-0.263
 air-0.261
 down-0.257
et-0.251
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
vern+0.048
ves+0.047
ades+0.042
 forgiveness+0.040
 mercy+0.040
Neg logit contributions
 around-0.056
 air-0.052
 down-0.050
cy-0.050
et-0.049
Tokeny
Token ID88
Feature activation-4.85e+00

Pos logit contributions
ves+1.157
vern+1.129
ades+1.078
 mercy+1.034
keys+1.029
Neg logit contributions
 around-0.621
 air-0.545
cy-0.514
 down-0.513
|-0.507
Token!"
Token ID2474
Feature activation-7.12e-01

Pos logit contributions
 around+0.224
cy+0.200
 air+0.199
 down+0.195
et+0.190
Neg logit contributions
ves-0.304
vern-0.302
ades-0.276
 mercy-0.273
 backup-0.270
Token and
Token ID290
Feature activation-1.54e+00

Pos logit contributions
 around+0.027
cy+0.025
et+0.025
rated+0.025
ening+0.024
Neg logit contributions
ves-0.048
vern-0.044
ades-0.044
keys-0.042
 backup-0.042
Token "
Token ID366
Feature activation+3.60e+00

Pos logit contributions
 around+0.079
cy+0.072
 air+0.071
 down+0.070
et+0.069
Neg logit contributions
ves-0.089
vern-0.087
ades-0.079
 mercy-0.078
 backup-0.077
TokenSh
Token ID2484
Feature activation+8.77e+00

Pos logit contributions
ves+0.180
vern+0.176
ades+0.160
 mercy+0.154
 backup+0.154
Neg logit contributions
 around-0.211
cy-0.194
 air-0.192
 down-0.190
et-0.186
Token It
Token ID632
Feature activation-9.32e+00

Pos logit contributions
 around+0.011
cy+0.010
et+0.010
rated+0.009
 down+0.009
Neg logit contributions
ves-0.023
vern-0.023
 forgiveness-0.021
 mercy-0.021
 backup-0.021
Token needs
Token ID2476
Feature activation+1.69e-01

Pos logit contributions
 around+0.377
cy+0.340
 down+0.333
 air+0.330
rated+0.325
Neg logit contributions
ves-0.621
vern-0.600
 mercy-0.556
keys-0.554
ades-0.548
Token to
Token ID284
Feature activation+2.96e+00

Pos logit contributions
ves+0.010
vern+0.010
ades+0.010
keys+0.009
His+0.008
Neg logit contributions
 around-0.009
 air-0.009
 down-0.008
 through-0.007
 night-0.007
Token find
Token ID1064
Feature activation+2.06e+00

Pos logit contributions
vern+0.183
ves+0.182
ades+0.177
keys+0.166
 mercy+0.157
Neg logit contributions
 around-0.136
 air-0.129
 down-0.119
|-0.117
et-0.115
Token a
Token ID257
Feature activation+4.82e+00

Pos logit contributions
vern+0.097
ves+0.096
ades+0.089
keys+0.085
His+0.079
Neg logit contributions
 around-0.136
 air-0.127
 down-0.122
et-0.115
 through-0.113
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
ves+0.302
vern+0.293
ades+0.279
keys+0.268
 mercy+0.266
Neg logit contributions
 around-0.224
 air-0.209
 down-0.204
cy-0.199
 night-0.185
Token and
Token ID290
Feature activation-1.55e+00

Pos logit contributions
ves+1.048
vern+1.033
ades+0.954
 mercy+0.936
keys+0.924
Neg logit contributions
 around-0.740
 air-0.669
cy-0.665
 down-0.644
et-0.633
Token lay
Token ID3830
Feature activation-1.65e+00

Pos logit contributions
 around+0.085
 air+0.078
 down+0.076
 alone+0.068
 through+0.068
Neg logit contributions
vern-0.093
ves-0.091
ades-0.088
keys-0.078
 instincts-0.073
Token eggs
Token ID9653
Feature activation+4.23e+00

Pos logit contributions
|+0.068
cy+0.065
 around+0.065
amp+0.063
rated+0.063
Neg logit contributions
ves-0.101
vern-0.094
ades-0.090
 mercy-0.089
 forgiveness-0.088
Token.
Token ID13
Feature activation-3.20e-01

Pos logit contributions
ves+0.267
vern+0.264
ades+0.241
 mercy+0.238
keys+0.237
Neg logit contributions
 around-0.179
cy-0.169
 air-0.166
|-0.161
et-0.158
Token Then
Token ID3244
Feature activation-3.82e+00

Pos logit contributions
 around+0.013
cy+0.012
et+0.011
 down+0.011
 air+0.011
Neg logit contributions
ves-0.022
vern-0.021
 mercy-0.020
 backup-0.020
ades-0.020
Token
Token ID198
Feature activation+7.81e-01

Pos logit contributions
vern+0.050
ves+0.049
 mercy+0.047
 forgiveness+0.046
 backup+0.046
Neg logit contributions
 around-0.036
 air-0.030
cy-0.030
 down-0.029
|-0.029
Token"
Token ID1
Feature activation+9.41e+00

Pos logit contributions
 forgiveness+0.041
vern+0.041
 mercy+0.041
 instincts+0.038
 backup+0.035
Neg logit contributions
 around-0.046
 air-0.040
cy-0.039
 down-0.039
ny-0.038
TokenAr
Token ID3163
Feature activation+9.66e+00

Pos logit contributions
vern+0.772
ves+0.747
 instincts+0.701
 mercy+0.700
ades+0.691
Neg logit contributions
cy-0.251
 around-0.249
 air-0.243
|-0.218
et-0.199
Tokenrr
Token ID21062
Feature activation+1.03e+00

Pos logit contributions
ves+0.571
vern+0.554
 forgiveness+0.516
 mercy+0.512
 wife+0.509
Neg logit contributions
 around-0.436
cy-0.401
et-0.389
|-0.386
 air-0.369
Token,
Token ID11
Feature activation+9.24e-01

Pos logit contributions
ves+0.065
vern+0.065
 mercy+0.059
ades+0.059
 forgiveness+0.059
Neg logit contributions
 around-0.047
cy-0.042
 air-0.041
 down-0.041
et-0.040
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
vern+0.042
ves+0.041
ades+0.038
His+0.031
keys+0.031
Neg logit contributions
 around-0.063
 air-0.058
 down-0.057
 through-0.054
cy-0.053
Tokeny
Token ID88
Feature activation-4.88e+00

Pos logit contributions
ves+1.205
vern+1.181
ades+1.119
 mercy+1.092
keys+1.078
Neg logit contributions
 around-0.585
 air-0.508
cy-0.486
 down-0.485
et-0.465
Token,
Token ID11
Feature activation+9.22e-01

Pos logit contributions
 around+0.216
 air+0.193
cy+0.192
 down+0.187
et+0.183
Neg logit contributions
vern-0.316
ves-0.315
ades-0.289
 mercy-0.284
 backup-0.283
Token let
Token ID1309
Feature activation+5.73e-01

Pos logit contributions
vern+0.039
ves+0.039
ades+0.034
keys+0.030
 mercy+0.029
Neg logit contributions
 around-0.065
 air-0.060
 down-0.060
 through-0.056
cy-0.056
Token's
Token ID338
Feature activation+2.24e+00

Pos logit contributions
ves+0.036
vern+0.035
ades+0.032
 mercy+0.032
 backup+0.032
Neg logit contributions
 around-0.027
cy-0.024
 air-0.024
 down-0.023
et-0.023
Token sail
Token ID14936
Feature activation+6.17e+00

Pos logit contributions
ves+0.134
vern+0.133
ades+0.121
 mercy+0.119
 backup+0.117
Neg logit contributions
 around-0.113
cy-0.101
 air-0.100
 down-0.099
et-0.096
Token
Token ID198
Feature activation+7.89e-01

Pos logit contributions
vern+0.051
ves+0.050
 mercy+0.049
 forgiveness+0.047
keys+0.047
Neg logit contributions
 around-0.036
cy-0.031
|-0.030
 air-0.030
 down-0.030
Token"
Token ID1
Feature activation+9.42e+00

Pos logit contributions
 mercy+0.038
vern+0.038
 forgiveness+0.037
 backup+0.033
ves+0.033
Neg logit contributions
 around-0.048
cy-0.045
ny-0.043
 air-0.042
et-0.041
TokenAr
Token ID3163
Feature activation+9.70e+00

Pos logit contributions
vern+0.607
ves+0.580
 mercy+0.537
ades+0.532
 backup+0.527
Neg logit contributions
 around-0.448
cy-0.432
 air-0.406
|-0.388
 down-0.385
Tokenrr
Token ID21062
Feature activation+1.05e+00

Pos logit contributions
ves+0.571
vern+0.550
 mercy+0.511
 forgiveness+0.505
 wife+0.504
Neg logit contributions
 around-0.452
cy-0.417
|-0.401
et-0.395
 down-0.380
Token,
Token ID11
Feature activation+9.35e-01

Pos logit contributions
ves+0.064
vern+0.064
ades+0.058
 mercy+0.057
 backup+0.057
Neg logit contributions
 around-0.050
cy-0.045
 air-0.045
 down-0.044
et-0.043
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
vern+0.056
ves+0.056
ades+0.052
 mercy+0.047
His+0.046
Neg logit contributions
 around-0.050
 air-0.044
 down-0.043
cy-0.041
 through-0.040
Tokeny
Token ID88
Feature activation-4.86e+00

Pos logit contributions
ves+1.182
vern+1.158
ades+1.119
 mercy+1.081
keys+1.052
Neg logit contributions
 around-0.557
 air-0.498
 down-0.454
|-0.446
et-0.439
Token,
Token ID11
Feature activation+9.27e-01

Pos logit contributions
 around+0.233
cy+0.211
 air+0.207
 down+0.204
|+0.200
Neg logit contributions
ves-0.294
vern-0.288
ades-0.264
 mercy-0.261
keys-0.257
Token this
Token ID428
Feature activation+2.95e+00

Pos logit contributions
ves+0.052
vern+0.052
ades+0.048
 mercy+0.044
keys+0.043
Neg logit contributions
 around-0.053
 air-0.046
 down-0.046
cy-0.044
et-0.043
Token is
Token ID318
Feature activation-9.80e-01

Pos logit contributions
vern+0.209
ves+0.206
ades+0.192
 mercy+0.191
 backup+0.189
Neg logit contributions
 around-0.114
 air-0.102
cy-0.097
et-0.095
 down-0.094
Token our
Token ID674
Feature activation+6.06e+00

Pos logit contributions
 around+0.056
 air+0.051
 down+0.050
cy+0.050
et+0.049
Neg logit contributions
ves-0.052
vern-0.051
ades-0.047
 mercy-0.045
keys-0.045
Token
Token ID198
Feature activation+7.52e-01

Pos logit contributions
vern+0.047
ves+0.046
 mercy+0.044
 forgiveness+0.043
keys+0.043
Neg logit contributions
 around-0.036
cy-0.031
 air-0.030
 down-0.030
|-0.030
Token"
Token ID1
Feature activation+9.38e+00

Pos logit contributions
vern+0.035
 mercy+0.034
 forgiveness+0.033
ves+0.030
 instincts+0.030
Neg logit contributions
 around-0.048
cy-0.044
 down-0.042
 air-0.042
et-0.042
TokenAr
Token ID3163
Feature activation+9.65e+00

Pos logit contributions
vern+0.694
ves+0.670
 mercy+0.625
ades+0.618
 backup+0.611
Neg logit contributions
 around-0.349
cy-0.328
 air-0.312
|-0.301
et-0.294
Tokenrr
Token ID21062
Feature activation+1.01e+00

Pos logit contributions
ves+0.570
vern+0.550
 mercy+0.516
 forgiveness+0.508
ades+0.497
Neg logit contributions
 around-0.451
cy-0.415
|-0.399
et-0.396
 down-0.380
Token,
Token ID11
Feature activation+8.98e-01

Pos logit contributions
ves+0.063
vern+0.063
ades+0.057
 mercy+0.056
 backup+0.056
Neg logit contributions
 around-0.047
cy-0.042
 air-0.042
 down-0.041
et-0.040
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
vern+0.049
ves+0.048
ades+0.043
 mercy+0.041
keys+0.039
Neg logit contributions
 around-0.053
 air-0.047
 down-0.047
cy-0.045
|-0.043
Tokeny
Token ID88
Feature activation-4.89e+00

Pos logit contributions
ves+1.192
vern+1.167
ades+1.121
 mercy+1.083
keys+1.065
Neg logit contributions
 around-0.566
 air-0.501
 down-0.466
cy-0.454
|-0.450
Token,
Token ID11
Feature activation+9.06e-01

Pos logit contributions
 around+0.231
cy+0.209
 air+0.206
 down+0.202
|+0.198
Neg logit contributions
ves-0.299
vern-0.292
ades-0.270
 mercy-0.265
keys-0.262
Token we
Token ID356
Feature activation+6.05e+00

Pos logit contributions
vern+0.051
ves+0.050
ades+0.045
 mercy+0.043
keys+0.042
Neg logit contributions
 around-0.052
 air-0.046
 down-0.045
cy-0.044
et-0.043
Token are
Token ID389
Feature activation+6.56e-01

Pos logit contributions
vern+0.368
ves+0.366
 backup+0.340
ades+0.335
 mercy+0.333
Neg logit contributions
 around-0.264
 down-0.241
 air-0.239
cy-0.233
ening-0.232
Token the
Token ID262
Feature activation-4.04e+00

Pos logit contributions
ves+0.033
vern+0.033
ades+0.029
 backup+0.029
 mercy+0.029
Neg logit contributions
 around-0.038
cy-0.036
 air-0.035
 down-0.034
et-0.034
Token said
Token ID531
Feature activation+1.50e+00

Pos logit contributions
 around+0.080
 down+0.073
 air+0.065
cy+0.063
 through+0.063
Neg logit contributions
vern-0.115
ves-0.104
ades-0.100
 mercy-0.094
 backup-0.092
Token,
Token ID11
Feature activation+8.90e-01

Pos logit contributions
vern+0.110
ves+0.107
 mercy+0.102
 forgiveness+0.100
 backup+0.100
Neg logit contributions
 around-0.059
 down-0.053
 air-0.043
 through-0.041
et-0.038
Token "
Token ID366
Feature activation+3.56e+00

Pos logit contributions
ves+0.047
vern+0.046
ades+0.042
 mercy+0.041
 backup+0.040
Neg logit contributions
 around-0.050
cy-0.046
 air-0.046
 down-0.045
et-0.044
TokenAh
Token ID10910
Feature activation+2.59e+00

Pos logit contributions
ves+0.239
vern+0.236
ades+0.220
 mercy+0.215
 backup+0.214
Neg logit contributions
 around-0.149
cy-0.130
 air-0.130
 down-0.127
et-0.124
Tokenoy
Token ID726
Feature activation+5.89e+00

Pos logit contributions
vern+0.116
ves+0.115
ades+0.104
 mercy+0.101
 forgiveness+0.098
Neg logit contributions
 around-0.155
et-0.149
cy-0.144
 air-0.144
 down-0.143
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
ves+0.379
vern+0.373
ades+0.339
 mercy+0.335
 forgiveness+0.329
Neg logit contributions
 around-0.271
cy-0.245
 down-0.240
 air-0.236
et-0.229
Tokeny
Token ID88
Feature activation-4.89e+00

Pos logit contributions
ves+1.163
vern+1.153
ades+1.101
 mercy+1.068
 backup+1.050
Neg logit contributions
 around-0.578
 air-0.517
cy-0.472
|-0.468
et-0.468
Token!"
Token ID2474
Feature activation-7.46e-01

Pos logit contributions
 around+0.220
cy+0.196
 air+0.196
 down+0.192
et+0.186
Neg logit contributions
ves-0.314
vern-0.313
ades-0.285
 mercy-0.281
 backup-0.278
Token to
Token ID284
Feature activation+2.93e+00

Pos logit contributions
 around+0.029
cy+0.026
 air+0.025
et+0.025
 down+0.024
Neg logit contributions
ves-0.052
vern-0.050
ades-0.047
 mercy-0.046
 backup-0.046
Token the
Token ID262
Feature activation-4.05e+00

Pos logit contributions
vern+0.223
ves+0.218
ades+0.208
keys+0.203
eed+0.188
Neg logit contributions
 around-0.114
 down-0.098
 air-0.094
 through-0.088
 alone-0.087
Token pirate
Token ID25868
Feature activation+1.01e+01

Pos logit contributions
 around+0.267
 air+0.265
 down+0.249
cy+0.239
 night+0.237
Neg logit contributions
vern-0.191
ves-0.187
ades-0.164
keys-0.160
 mercy-0.151
Token say
Token ID910
Feature activation-2.83e-01

Pos logit contributions
 around+0.247
 down+0.216
 air+0.211
cy+0.211
et+0.202
Neg logit contributions
ves-0.291
vern-0.290
ades-0.265
 forgiveness-0.257
 backup-0.257
Token '
Token ID705
Feature activation+6.84e+00

Pos logit contributions
 around+0.017
 air+0.015
 down+0.015
et+0.014
 through+0.013
Neg logit contributions
vern-0.015
ves-0.014
ades-0.013
 mercy-0.013
keys-0.012
TokenAh
Token ID10910
Feature activation+2.60e+00

Pos logit contributions
ves+0.375
vern+0.346
ades+0.336
keys+0.334
 backup+0.309
Neg logit contributions
 around-0.363
 air-0.332
 down-0.318
rated-0.316
ening-0.315
Tokenoy
Token ID726
Feature activation+5.88e+00

Pos logit contributions
vern+0.142
ves+0.134
 mercy+0.129
ades+0.127
 forgiveness+0.124
Neg logit contributions
 around-0.132
et-0.125
 air-0.119
cy-0.117
 down-0.116
Token,
Token ID11
Feature activation+9.05e-01

Pos logit contributions
ves+0.328
vern+0.324
ades+0.290
 mercy+0.288
 backup+0.282
Neg logit contributions
 around-0.316
cy-0.288
 down-0.283
 air-0.282
et-0.273
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
vern+0.041
ves+0.041
ades+0.036
 mercy+0.034
 forgiveness+0.033
Neg logit contributions
 around-0.060
 down-0.055
 air-0.054
cy-0.053
et-0.053
Tokeny
Token ID88
Feature activation-4.89e+00

Pos logit contributions
ves+1.297
vern+1.282
ades+1.208
 mercy+1.185
keys+1.176
Neg logit contributions
 around-0.496
 air-0.417
cy-0.407
 down-0.396
et-0.382
Token!'
Token ID13679
Feature activation+1.75e+00

Pos logit contributions
 around+0.242
cy+0.218
 air+0.218
 down+0.213
et+0.207
Neg logit contributions
ves-0.291
vern-0.291
ades-0.263
 mercy-0.259
 backup-0.257
Token and
Token ID290
Feature activation-1.57e+00

Pos logit contributions
ves+0.123
vern+0.122
ades+0.113
keys+0.111
 mercy+0.109
Neg logit contributions
 around-0.073
 air-0.065
 down-0.064
cy-0.060
et-0.056
Token '
Token ID705
Feature activation+6.85e+00

Pos logit contributions
 around+0.084
cy+0.077
 air+0.076
 down+0.074
et+0.073
Neg logit contributions
ves-0.087
vern-0.085
ades-0.078
 mercy-0.077
 backup-0.076
TokenLand
Token ID22342
Feature activation+2.03e+00

Pos logit contributions
ves+0.355
vern+0.344
ades+0.322
keys+0.311
 backup+0.307
Neg logit contributions
 around-0.383
 air-0.349
cy-0.340
 down-0.339
et-0.334
Token,
Token ID11
Feature activation+9.01e-01

Pos logit contributions
vern+0.113
ves+0.111
keys+0.107
ades+0.105
 mercy+0.105
Neg logit contributions
 around-0.055
 down-0.048
 air-0.039
 through-0.036
et-0.034
Token "
Token ID366
Feature activation+3.56e+00

Pos logit contributions
vern+0.053
ves+0.052
 mercy+0.047
ades+0.047
 backup+0.046
Neg logit contributions
 around-0.048
 down-0.043
 air-0.042
cy-0.040
et-0.039
TokenAh
Token ID10910
Feature activation+2.59e+00

Pos logit contributions
ves+0.206
vern+0.203
ades+0.186
 mercy+0.182
 backup+0.181
Neg logit contributions
 around-0.183
cy-0.165
 air-0.164
 down-0.162
et-0.158
Tokenoy
Token ID726
Feature activation+5.87e+00

Pos logit contributions
vern+0.170
ves+0.167
ades+0.161
keys+0.153
 mercy+0.153
Neg logit contributions
 around-0.104
et-0.096
 air-0.095
 down-0.092
cy-0.092
Token,
Token ID11
Feature activation+8.97e-01

Pos logit contributions
ves+0.382
vern+0.380
ades+0.345
 mercy+0.341
 forgiveness+0.335
Neg logit contributions
 around-0.263
cy-0.236
 down-0.234
 air-0.230
et-0.222
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
vern+0.041
ves+0.040
ades+0.037
keys+0.033
 mercy+0.031
Neg logit contributions
 around-0.061
 air-0.056
 down-0.055
et-0.054
cy-0.053
Tokeny
Token ID88
Feature activation-4.88e+00

Pos logit contributions
ves+1.132
vern+1.109
ades+1.058
 mercy+1.023
 backup+1.007
Neg logit contributions
 around-0.626
 air-0.550
 down-0.517
|-0.515
cy-0.515
Token.
Token ID13
Feature activation-3.49e-01

Pos logit contributions
 around+0.222
cy+0.199
 air+0.198
 down+0.193
et+0.188
Neg logit contributions
ves-0.311
vern-0.309
ades-0.283
 mercy-0.279
 backup-0.276
Token I
Token ID314
Feature activation+1.41e+00

Pos logit contributions
 around+0.015
cy+0.014
 air+0.014
 down+0.013
et+0.013
Neg logit contributions
ves-0.023
vern-0.022
ades-0.021
 mercy-0.020
 backup-0.020
Token'm
Token ID1101
Feature activation+2.07e+00

Pos logit contributions
ves+0.092
vern+0.091
ades+0.084
 mercy+0.082
 backup+0.082
Neg logit contributions
 around-0.062
cy-0.055
 air-0.054
 down-0.053
et-0.052
Token Captain
Token ID8599
Feature activation+6.11e+00

Pos logit contributions
vern+0.107
ves+0.106
 backup+0.097
 mercy+0.094
ades+0.093
Neg logit contributions
cy-0.113
 around-0.112
rated-0.105
 air-0.105
|-0.103
Token shouted
Token ID17293
Feature activation+1.61e-02

Pos logit contributions
 around+0.050
et+0.042
 air+0.042
cy+0.042
 down+0.041
Neg logit contributions
vern-0.068
ves-0.064
ades-0.061
 backup-0.061
 mercy-0.059
Token,
Token ID11
Feature activation+9.65e-01

Pos logit contributions
ves+0.001
vern+0.001
ades+0.001
 mercy+0.001
keys+0.001
Neg logit contributions
 around-0.001
 down-0.001
 air-0.001
cy-0.001
et-0.001
Token "
Token ID366
Feature activation+3.61e+00

Pos logit contributions
ves+0.050
vern+0.049
ades+0.045
 mercy+0.044
 backup+0.043
Neg logit contributions
 around-0.055
cy-0.050
 air-0.050
 down-0.049
et-0.048
TokenAr
Token ID3163
Feature activation+9.67e+00

Pos logit contributions
ves+0.203
vern+0.203
ades+0.183
 mercy+0.178
 backup+0.177
Neg logit contributions
 around-0.193
cy-0.180
 air-0.175
 down-0.171
et-0.170
Tokengh
Token ID456
Feature activation+2.46e+00

Pos logit contributions
ves+0.564
vern+0.533
ades+0.492
 forgiveness+0.483
keys+0.473
Neg logit contributions
 around-0.481
et-0.439
cy-0.433
 down-0.414
 air-0.410
Token mate
Token ID16133
Feature activation+1.66e+01

Pos logit contributions
ves+0.158
vern+0.157
 mercy+0.145
 forgiveness+0.142
ades+0.142
Neg logit contributions
 around-0.110
cy-0.098
 down-0.098
et-0.094
 air-0.092
Tokenys
Token ID893
Feature activation-1.70e+00

Pos logit contributions
ves+1.137
vern+1.112
ades+1.058
 mercy+1.027
keys+1.013
Neg logit contributions
 around-0.620
 air-0.562
cy-0.533
 down-0.520
|-0.514
Token!"
Token ID2474
Feature activation-7.86e-01

Pos logit contributions
 around+0.078
cy+0.070
 air+0.069
 down+0.068
et+0.066
Neg logit contributions
ves-0.107
vern-0.105
ades-0.097
 mercy-0.095
 backup-0.094
Token
Token ID198
Feature activation+6.90e-01

Pos logit contributions
 around+0.034
 air+0.030
cy+0.030
 down+0.030
et+0.028
Neg logit contributions
vern-0.052
ves-0.051
ades-0.047
 mercy-0.046
 backup-0.046
Token
Token ID198
Feature activation+6.81e-01

Pos logit contributions
vern+0.047
 mercy+0.045
 forgiveness+0.044
ves+0.044
 instincts+0.043
Neg logit contributions
 around-0.027
|-0.024
cy-0.021
amp-0.021
 air-0.021
TokenThe
Token ID464
Feature activation+2.96e+00

Pos logit contributions
vern+0.035
 forgiveness+0.034
 mercy+0.033
 instincts+0.031
ves+0.031
Neg logit contributions
|-0.035
 around-0.034
ny-0.032
amp-0.032
cy-0.031
Tokenâ
Token ID22940
Feature activation-1.71e+00

Pos logit contributions
 around+0.023
et+0.021
rated+0.021
cy+0.021
 down+0.020
Neg logit contributions
vern-0.034
ves-0.034
 backup-0.031
 forgiveness-0.031
ades-0.031
Token
Token ID26391
Feature activation-1.48e+01

Pos logit contributions
 around+0.069
 down+0.062
 through+0.056
cy+0.054
ening+0.052
Neg logit contributions
vern-0.101
ves-0.101
ggy-0.093
 forgiveness-0.091
His-0.090
Token
Token ID198
Feature activation+5.56e-01

Pos logit contributions
 around+0.862
cy+0.788
 air+0.777
et+0.773
 down+0.772
Neg logit contributions
ves-0.793
vern-0.750
ades-0.685
keys-0.659
 backup-0.627
Token
Token ID198
Feature activation+5.36e-01

Pos logit contributions
ves+0.032
vern+0.032
 mercy+0.029
ades+0.029
 backup+0.029
Neg logit contributions
 around-0.028
 air-0.025
cy-0.025
 down-0.024
|-0.024
TokenM
Token ID44
Feature activation+5.88e+00

Pos logit contributions
vern+0.024
ves+0.024
 mercy+0.023
 backup+0.022
 forgiveness+0.022
Neg logit contributions
 around-0.033
|-0.030
cy-0.030
amp-0.029
 air-0.029
Tokenaz
Token ID1031
Feature activation-1.60e+01

Pos logit contributions
ves+0.249
vern+0.244
ades+0.214
 mercy+0.211
 backup+0.207
Neg logit contributions
 around-0.392
cy-0.365
 air-0.363
 down-0.356
et-0.353
Tokenzy
Token ID7357
Feature activation-1.09e+01

Pos logit contributions
 around+0.640
 air+0.597
cy+0.593
 down+0.587
|+0.544
Neg logit contributions
ves-1.145
vern-1.004
ades-0.970
ggy-0.961
keys-0.937
Token could
Token ID714
Feature activation-5.14e+00

Pos logit contributions
 around+0.555
cy+0.504
 air+0.503
 down+0.503
|+0.491
Neg logit contributions
ves-0.611
vern-0.568
ades-0.535
keys-0.530
 mercy-0.512
Token barely
Token ID8523
Feature activation+4.99e+00

Pos logit contributions
 around+0.294
 air+0.257
 down+0.256
cy+0.250
et+0.243
Neg logit contributions
vern-0.277
ves-0.275
ades-0.253
 mercy-0.245
 backup-0.244
Token contain
Token ID3994
Feature activation-2.44e-01

Pos logit contributions
ves+0.279
vern+0.278
ades+0.256
 mercy+0.244
 backup+0.242
Neg logit contributions
 around-0.271
cy-0.239
 air-0.238
 down-0.235
et-0.230
Token her
Token ID607
Feature activation+1.35e+00

Pos logit contributions
 around+0.012
 air+0.010
 down+0.010
cy+0.010
et+0.010
Neg logit contributions
ves-0.015
vern-0.015
ades-0.014
keys-0.014
 mercy-0.014
Tokenors
Token ID669
Feature activation-5.21e+00

Pos logit contributions
 around+0.806
cy+0.754
 air+0.737
 down+0.726
|+0.716
Neg logit contributions
ves-0.966
vern-0.870
ades-0.829
keys-0.783
ggy-0.778
Token.
Token ID13
Feature activation-5.47e-01

Pos logit contributions
 air+0.248
cy+0.243
rated+0.241
|+0.236
amp+0.231
Neg logit contributions
ves-0.268
vern-0.239
keys-0.239
ades-0.233
 else-0.232
Token The
Token ID383
Feature activation-8.33e+00

Pos logit contributions
 around+0.022
rated+0.020
cy+0.020
et+0.020
 down+0.019
Neg logit contributions
ves-0.037
vern-0.035
ades-0.034
His-0.034
 forgiveness-0.033
Token other
Token ID584
Feature activation+1.11e+00

Pos logit contributions
 around+0.494
cy+0.454
 air+0.450
 down+0.444
et+0.436
Neg logit contributions
ves-0.418
vern-0.411
ades-0.369
 mercy-0.361
 backup-0.357
Token r
Token ID374
Feature activation+2.70e+00

Pos logit contributions
ves+0.052
vern+0.050
ades+0.047
 forgiveness+0.046
 mercy+0.045
Neg logit contributions
 around-0.065
|-0.061
cy-0.059
 down-0.059
rated-0.058
Tokenaz
Token ID1031
Feature activation-1.60e+01

Pos logit contributions
vern+0.158
ves+0.155
ades+0.152
 mercy+0.137
 forgiveness+0.137
Neg logit contributions
 around-0.132
|-0.120
 down-0.119
cy-0.117
 air-0.115
Tokenors
Token ID669
Feature activation-5.21e+00

Pos logit contributions
 around+0.801
cy+0.756
 air+0.747
 down+0.737
|+0.706
Neg logit contributions
ves-0.979
vern-0.870
ades-0.835
ggy-0.782
keys-0.777
Token would
Token ID561
Feature activation-2.79e+00

Pos logit contributions
 air+0.240
amp+0.230
|+0.230
 around+0.229
rated+0.228
Neg logit contributions
ves-0.274
vern-0.246
ades-0.245
keys-0.236
 else-0.234
Token laugh
Token ID6487
Feature activation-2.42e+00

Pos logit contributions
 around+0.144
 air+0.127
cy+0.125
 down+0.125
et+0.122
Neg logit contributions
ves-0.164
vern-0.162
ades-0.149
keys-0.144
 mercy-0.143
Token and
Token ID290
Feature activation-1.79e+00

Pos logit contributions
cy+0.108
|+0.102
 around+0.102
 air+0.101
rated+0.096
Neg logit contributions
ves-0.148
vern-0.140
ades-0.134
keys-0.127
 forgiveness-0.125
Token say
Token ID910
Feature activation-5.07e-01

Pos logit contributions
 around+0.091
cy+0.083
 air+0.081
 down+0.080
et+0.079
Neg logit contributions
ves-0.103
vern-0.101
ades-0.092
 mercy-0.091
 backup-0.090
Token the
Token ID262
Feature activation-4.24e+00

Pos logit contributions
ves+0.163
vern+0.160
ades+0.147
 mercy+0.144
 backup+0.143
Neg logit contributions
 around-0.137
cy-0.124
 air-0.123
 down-0.120
et-0.118
Token park
Token ID3952
Feature activation+2.12e-01

Pos logit contributions
 around+0.219
cy+0.199
 air+0.197
 down+0.194
et+0.190
Neg logit contributions
ves-0.242
vern-0.239
ades-0.218
 mercy-0.214
 backup-0.213
Token,
Token ID11
Feature activation+7.23e-01

Pos logit contributions
ves+0.012
vern+0.012
ades+0.011
 mercy+0.011
 forgiveness+0.011
Neg logit contributions
 around-0.010
cy-0.010
 air-0.010
|-0.009
et-0.009
Token the
Token ID262
Feature activation-4.25e+00

Pos logit contributions
ves+0.037
vern+0.036
ades+0.032
 mercy+0.032
 backup+0.032
Neg logit contributions
 around-0.041
cy-0.038
 air-0.037
et-0.037
 down-0.037
Token g
Token ID308
Feature activation-2.63e+00

Pos logit contributions
 around+0.224
cy+0.203
 air+0.203
 down+0.198
et+0.194
Neg logit contributions
ves-0.239
vern-0.236
ades-0.215
 mercy-0.210
 backup-0.208
Tokenaz
Token ID1031
Feature activation-1.60e+01

Pos logit contributions
 around+0.120
cy+0.109
 down+0.108
 air+0.104
|+0.100
Neg logit contributions
ves-0.169
vern-0.166
ades-0.159
keys-0.145
 mercy-0.144
Tokeneb
Token ID1765
Feature activation-3.32e+00

Pos logit contributions
 around+0.632
 air+0.573
cy+0.571
 down+0.560
|+0.520
Neg logit contributions
ves-1.146
vern-1.076
ades-1.019
keys-0.966
ggy-0.956
Tokeno
Token ID78
Feature activation-5.36e+00

Pos logit contributions
 around+0.190
et+0.179
cy+0.176
 down+0.170
 air+0.165
Neg logit contributions
vern-0.165
ves-0.162
 mercy-0.153
 backup-0.150
 forgiveness-0.147
Token would
Token ID561
Feature activation-2.77e+00

Pos logit contributions
 around+0.256
cy+0.233
 air+0.230
 down+0.225
et+0.220
Neg logit contributions
ves-0.325
vern-0.317
ades-0.291
 mercy-0.286
keys-0.284
Token be
Token ID307
Feature activation+3.67e+00

Pos logit contributions
 around+0.146
 air+0.129
 down+0.128
cy+0.127
et+0.125
Neg logit contributions
ves-0.160
vern-0.155
ades-0.146
keys-0.140
 backup-0.137
Token there
Token ID612
Feature activation-1.12e+00

Pos logit contributions
ves+0.205
vern+0.203
ades+0.184
 mercy+0.181
 backup+0.180
Neg logit contributions
 around-0.192
cy-0.178
 air-0.175
 down-0.170
et-0.167
Token stand
Token ID1302
Feature activation-1.24e+00

Pos logit contributions
ves+0.485
vern+0.477
ades+0.443
 mercy+0.426
 backup+0.425
Neg logit contributions
 around-0.412
 air-0.358
 down-0.358
cy-0.355
et-0.343
Token like
Token ID588
Feature activation-4.95e+00

Pos logit contributions
cy+0.050
 around+0.050
 air+0.049
|+0.048
et+0.045
Neg logit contributions
vern-0.078
ves-0.078
ades-0.072
keys-0.069
 mercy-0.069
Token the
Token ID262
Feature activation-4.22e+00

Pos logit contributions
 around+0.250
 air+0.230
 down+0.220
et+0.202
ening+0.196
Neg logit contributions
ves-0.296
vern-0.294
ades-0.274
keys-0.268
 mercy-0.258
Token other
Token ID584
Feature activation+1.11e+00

Pos logit contributions
 around+0.238
cy+0.226
|+0.220
 down+0.213
et+0.211
Neg logit contributions
ves-0.210
vern-0.209
 mercy-0.189
ades-0.188
 forgiveness-0.188
Token r
Token ID374
Feature activation+2.72e+00

Pos logit contributions
ves+0.051
vern+0.049
 forgiveness+0.046
 mercy+0.045
ades+0.045
Neg logit contributions
 around-0.066
|-0.062
cy-0.061
rated-0.059
 down-0.059
Tokenaz
Token ID1031
Feature activation-1.60e+01

Pos logit contributions
vern+0.173
ades+0.166
ves+0.165
ups+0.152
 mercy+0.152
Neg logit contributions
 around-0.116
|-0.107
cy-0.102
 down-0.102
rated-0.098
Tokenors
Token ID669
Feature activation-5.21e+00

Pos logit contributions
 around+0.806
cy+0.754
 air+0.737
 down+0.726
|+0.716
Neg logit contributions
ves-0.966
vern-0.870
ades-0.829
keys-0.783
ggy-0.778
Token.
Token ID13
Feature activation-5.47e-01

Pos logit contributions
 air+0.248
cy+0.243
rated+0.241
|+0.236
amp+0.231
Neg logit contributions
ves-0.268
vern-0.239
keys-0.239
ades-0.233
 else-0.232
Token The
Token ID383
Feature activation-8.33e+00

Pos logit contributions
 around+0.022
rated+0.020
cy+0.020
et+0.020
 down+0.019
Neg logit contributions
ves-0.037
vern-0.035
ades-0.034
His-0.034
 forgiveness-0.033
Token other
Token ID584
Feature activation+1.11e+00

Pos logit contributions
 around+0.494
cy+0.454
 air+0.450
 down+0.444
et+0.436
Neg logit contributions
ves-0.418
vern-0.411
ades-0.369
 mercy-0.361
 backup-0.357
Token r
Token ID374
Feature activation+2.70e+00

Pos logit contributions
ves+0.052
vern+0.050
ades+0.047
 forgiveness+0.046
 mercy+0.045
Neg logit contributions
 around-0.065
|-0.061
cy-0.059
 down-0.059
rated-0.058
Token.
Token ID13
Feature activation-5.33e-01

Pos logit contributions
ves+0.485
vern+0.478
ades+0.440
 mercy+0.433
 backup+0.429
Neg logit contributions
 around-0.349
cy-0.314
 air-0.310
 down-0.303
et-0.296
Token She
Token ID1375
Feature activation-5.85e+00

Pos logit contributions
 around+0.023
cy+0.022
et+0.022
rated+0.022
|+0.021
Neg logit contributions
ves-0.032
vern-0.030
 forgiveness-0.029
 backup-0.029
His-0.029
Token knew
Token ID2993
Feature activation-3.26e-01

Pos logit contributions
 around+0.248
cy+0.210
 air+0.209
 down+0.203
et+0.202
Neg logit contributions
vern-0.426
ves-0.387
 backup-0.377
ades-0.374
 mercy-0.361
Token that
Token ID326
Feature activation+3.97e+00

Pos logit contributions
 around+0.017
 down+0.015
 air+0.014
et+0.014
cy+0.013
Neg logit contributions
vern-0.020
ves-0.019
ades-0.019
keys-0.017
 backup-0.017
Token r
Token ID374
Feature activation+2.74e+00

Pos logit contributions
vern+0.225
ves+0.224
ades+0.207
 mercy+0.197
 backup+0.197
Neg logit contributions
 around-0.215
 air-0.192
cy-0.190
 down-0.190
et-0.182
Tokenaz
Token ID1031
Feature activation-1.60e+01

Pos logit contributions
vern+0.129
ades+0.129
ves+0.127
 forgiveness+0.109
ups+0.109
Neg logit contributions
 around-0.163
|-0.148
 air-0.146
 down-0.143
cy-0.143
Tokenors
Token ID669
Feature activation-5.15e+00

Pos logit contributions
 around+0.816
 air+0.760
cy+0.758
 down+0.742
|+0.736
Neg logit contributions
ves-0.964
vern-0.783
ggy-0.766
ades-0.756
keys-0.714
Token were
Token ID547
Feature activation+5.92e-01

Pos logit contributions
 air+0.222
 around+0.222
|+0.214
rated+0.211
amp+0.210
Neg logit contributions
ves-0.287
vern-0.262
ades-0.252
 forgiveness-0.248
keys-0.247
Token very
Token ID845
Feature activation-6.35e+00

Pos logit contributions
ves+0.034
vern+0.033
ades+0.031
 mercy+0.030
 backup+0.029
Neg logit contributions
 around-0.031
 air-0.028
 down-0.028
cy-0.028
et-0.027
Token sharp
Token ID7786
Feature activation+1.68e+00

Pos logit contributions
 around+0.315
 air+0.273
 down+0.269
cy+0.266
et+0.250
Neg logit contributions
ves-0.387
vern-0.379
ades-0.355
 mercy-0.352
keys-0.348
Token and
Token ID290
Feature activation-1.72e+00

Pos logit contributions
ves+0.095
vern+0.091
 mercy+0.084
 forgiveness+0.084
ades+0.083
Neg logit contributions
|-0.079
cy-0.078
 around-0.076
amp-0.070
rated-0.070
Token he
Token ID339
Feature activation+9.35e+00

Pos logit contributions
vern+0.066
ves+0.062
ades+0.058
keys+0.054
 mercy+0.053
Neg logit contributions
 around-0.093
 down-0.084
 air-0.083
 alone-0.076
et-0.075
Token would
Token ID561
Feature activation-2.68e+00

Pos logit contributions
ves+0.572
vern+0.563
ades+0.516
 mercy+0.508
 backup+0.502
Neg logit contributions
 around-0.448
cy-0.402
 air-0.401
 down-0.393
et-0.384
Token never
Token ID1239
Feature activation+6.07e-02

Pos logit contributions
 around+0.147
 air+0.128
 down+0.128
cy+0.126
et+0.122
Neg logit contributions
ves-0.149
vern-0.144
ades-0.138
keys-0.133
 mercy-0.127
Token touch
Token ID3638
Feature activation+9.52e-01

Pos logit contributions
ves+0.004
vern+0.004
ades+0.003
 mercy+0.003
 backup+0.003
Neg logit contributions
 around-0.003
cy-0.003
 air-0.003
 down-0.003
et-0.002
Token r
Token ID374
Feature activation+2.77e+00

Pos logit contributions
ves+0.048
vern+0.045
ades+0.042
 mercy+0.042
 forgiveness+0.042
Neg logit contributions
 around-0.053
cy-0.051
rated-0.050
|-0.049
 air-0.048
Tokenaz
Token ID1031
Feature activation-1.60e+01

Pos logit contributions
ades+0.167
ves+0.154
vern+0.153
ups+0.140
keys+0.139
Neg logit contributions
 around-0.130
rated-0.120
 air-0.118
ening-0.114
|-0.108
Tokenors
Token ID669
Feature activation-5.16e+00

Pos logit contributions
 around+0.731
cy+0.669
 air+0.668
 down+0.637
|+0.630
Neg logit contributions
ves-1.022
vern-0.948
ades-0.906
keys-0.872
 mercy-0.855
Token again
Token ID757
Feature activation-5.56e-01

Pos logit contributions
 air+0.248
 around+0.242
cy+0.241
|+0.236
rated+0.233
Neg logit contributions
ves-0.270
vern-0.257
keys-0.244
 mercy-0.243
ades-0.242
Token.
Token ID13
Feature activation-5.43e-01

Pos logit contributions
 around+0.025
cy+0.022
 air+0.022
 down+0.022
et+0.021
Neg logit contributions
ves-0.036
vern-0.035
ades-0.032
 mercy-0.032
 backup-0.032
Token He
Token ID679
Feature activation-1.40e+00

Pos logit contributions
 around+0.025
cy+0.023
 air+0.023
et+0.022
 down+0.022
Neg logit contributions
ves-0.034
vern-0.033
ades-0.030
 backup-0.030
 mercy-0.030
Token said
Token ID531
Feature activation+1.33e+00

Pos logit contributions
 around+0.071
cy+0.064
 air+0.063
et+0.062
 down+0.060
Neg logit contributions
vern-0.084
ves-0.081
ades-0.076
 backup-0.075
 mercy-0.073
Token mom
Token ID1995
Feature activation+3.66e+00

Pos logit contributions
ves+0.062
vern+0.061
ades+0.058
keys+0.056
 backup+0.054
Neg logit contributions
 around-0.089
 down-0.083
cy-0.081
 air-0.081
et-0.078
Token said
Token ID531
Feature activation+1.37e+00

Pos logit contributions
vern+0.223
ves+0.219
ades+0.205
 backup+0.201
keys+0.191
Neg logit contributions
 around-0.188
et-0.162
 down-0.160
cy-0.159
 air-0.158
Token.
Token ID13
Feature activation-5.11e-01

Pos logit contributions
ves+0.092
vern+0.091
ades+0.085
 backup+0.082
keys+0.082
Neg logit contributions
 around-0.059
 down-0.051
 air-0.050
cy-0.049
et-0.047
Token "
Token ID366
Feature activation+3.42e+00

Pos logit contributions
 around+0.026
cy+0.023
 air+0.023
 down+0.023
et+0.022
Neg logit contributions
ves-0.030
vern-0.030
ades-0.027
 mercy-0.027
 backup-0.026
TokenR
Token ID49
Feature activation+4.90e+00

Pos logit contributions
ves+0.174
vern+0.172
ades+0.155
 mercy+0.152
 backup+0.150
Neg logit contributions
 around-0.199
cy-0.183
 air-0.181
 down-0.178
et-0.174
Tokenaz
Token ID1031
Feature activation-1.60e+01

Pos logit contributions
ves+0.244
vern+0.242
ades+0.217
 mercy+0.210
 backup+0.208
Neg logit contributions
 around-0.300
 down-0.268
 air-0.266
cy-0.265
et-0.258
Tokenors
Token ID669
Feature activation-5.15e+00

Pos logit contributions
 around+0.735
 air+0.679
|+0.678
cy+0.672
 down+0.663
Neg logit contributions
ves-1.034
vern-0.898
ggy-0.864
ades-0.843
 instincts-0.804
Token are
Token ID389
Feature activation+5.17e-01

Pos logit contributions
 around+0.230
|+0.217
rated+0.213
cy+0.213
 air+0.212
Neg logit contributions
ves-0.287
vern-0.280
 forgiveness-0.263
 mercy-0.260
ades-0.259
Token not
Token ID407
Feature activation+8.08e+00

Pos logit contributions
ves+0.025
vern+0.025
ades+0.022
 mercy+0.021
keys+0.021
Neg logit contributions
 around-0.032
 air-0.029
cy-0.029
 down-0.029
et-0.028
Token toys
Token ID14958
Feature activation+6.49e+00

Pos logit contributions
ves+0.424
vern+0.418
ades+0.377
 mercy+0.370
 backup+0.366
Neg logit contributions
 around-0.459
cy-0.420
 air-0.416
 down-0.409
et-0.402
Token,
Token ID11
Feature activation+7.67e-01

Pos logit contributions
ves+0.405
vern+0.400
ades+0.367
 mercy+0.362
 backup+0.359
Neg logit contributions
 around-0.302
cy-0.271
 air-0.268
 down-0.263
et-0.257
Token stand
Token ID1302
Feature activation-1.22e+00

Pos logit contributions
ves+0.033
vern+0.033
ades+0.030
 backup+0.029
 mercy+0.029
Neg logit contributions
 around-0.032
cy-0.028
 air-0.028
 down-0.028
et-0.027
Token like
Token ID588
Feature activation-4.91e+00

Pos logit contributions
 around+0.045
cy+0.045
 air+0.044
|+0.043
rated+0.041
Neg logit contributions
ves-0.081
vern-0.081
ades-0.075
 backup-0.073
 mercy-0.073
Token the
Token ID262
Feature activation-4.17e+00

Pos logit contributions
 around+0.258
 air+0.231
 down+0.227
et+0.208
cy+0.205
Neg logit contributions
ves-0.292
vern-0.289
ades-0.265
keys-0.254
 mercy-0.250
Token other
Token ID584
Feature activation+1.19e+00

Pos logit contributions
 around+0.246
cy+0.233
|+0.224
 down+0.221
et+0.217
Neg logit contributions
ves-0.200
vern-0.200
 mercy-0.179
 forgiveness-0.177
 backup-0.177
Token r
Token ID374
Feature activation+2.79e+00

Pos logit contributions
ves+0.056
vern+0.055
 mercy+0.050
 forgiveness+0.049
ades+0.049
Neg logit contributions
 around-0.071
cy-0.066
|-0.065
 down-0.064
rated-0.063
Tokenaz
Token ID1031
Feature activation-1.59e+01

Pos logit contributions
vern+0.191
ves+0.183
ades+0.179
 mercy+0.170
 forgiveness+0.168
Neg logit contributions
 around-0.111
|-0.101
cy-0.096
 down-0.095
rated-0.090
Tokenors
Token ID669
Feature activation-5.12e+00

Pos logit contributions
 around+0.764
cy+0.720
 air+0.696
 down+0.678
|+0.677
Neg logit contributions
ves-0.996
vern-0.921
ades-0.859
keys-0.825
 mercy-0.807
Token.
Token ID13
Feature activation-4.60e-01

Pos logit contributions
|+0.239
cy+0.234
 air+0.230
rated+0.228
 around+0.226
Neg logit contributions
ves-0.255
vern-0.248
keys-0.245
ades-0.233
 forgiveness-0.231
Token They
Token ID1119
Feature activation-1.91e+00

Pos logit contributions
 around+0.021
et+0.020
cy+0.020
rated+0.019
ening+0.019
Neg logit contributions
ves-0.026
vern-0.025
keys-0.025
 backup-0.025
 forgiveness-0.024
Token laugh
Token ID6487
Feature activation-2.31e+00

Pos logit contributions
 around+0.084
cy+0.081
et+0.078
 air+0.077
amp+0.077
Neg logit contributions
ves-0.112
vern-0.111
keys-0.103
 mercy-0.102
ades-0.100
Token at
Token ID379
Feature activation-2.82e+00

Pos logit contributions
cy+0.109
|+0.107
amp+0.099
 around+0.098
et+0.098
Neg logit contributions
ves-0.130
vern-0.125
ades-0.119
keys-0.115
 mercy-0.111
Tokenup
Token ID929
Feature activation+1.13e+01

Pos logit contributions
ves+0.414
vern+0.398
ades+0.368
keys+0.362
 mercy+0.355
Neg logit contributions
 around-0.478
 down-0.432
 air-0.426
cy-0.418
et-0.413
Token tools
Token ID4899
Feature activation+9.19e+00

Pos logit contributions
ves+0.722
vern+0.714
ades+0.657
 mercy+0.647
 backup+0.641
Neg logit contributions
 around-0.507
cy-0.452
 air-0.448
 down-0.438
et-0.428
Token like
Token ID588
Feature activation-4.87e+00

Pos logit contributions
ves+0.561
vern+0.556
ades+0.507
 mercy+0.501
 backup+0.497
Neg logit contributions
 around-0.433
cy-0.393
 air-0.389
 down-0.378
et-0.371
Token delicate
Token ID19217
Feature activation-1.65e-01

Pos logit contributions
 around+0.275
 air+0.254
 down+0.242
et+0.230
ening+0.222
Neg logit contributions
ves-0.261
vern-0.257
ades-0.234
keys-0.229
 mercy-0.226
Token r
Token ID374
Feature activation+2.84e+00

Pos logit contributions
 around+0.010
 air+0.009
cy+0.009
 down+0.009
et+0.009
Neg logit contributions
ves-0.008
vern-0.008
ades-0.007
 mercy-0.007
 backup-0.007
Tokenaz
Token ID1031
Feature activation-1.59e+01

Pos logit contributions
vern+0.176
ades+0.169
ves+0.161
ups+0.154
eed+0.151
Neg logit contributions
 around-0.128
|-0.123
cy-0.112
 down-0.110
rated-0.109
Tokenors
Token ID669
Feature activation-5.07e+00

Pos logit contributions
 around+0.723
cy+0.675
 air+0.657
|+0.647
 down+0.641
Neg logit contributions
ves-1.035
vern-0.976
ades-0.904
keys-0.855
 forgiveness-0.843
Token.
Token ID13
Feature activation-4.02e-01

Pos logit contributions
 air+0.199
|+0.198
rated+0.190
cy+0.187
 around+0.186
Neg logit contributions
vern-0.294
ves-0.289
 forgiveness-0.277
ades-0.267
keys-0.266
Token<|endoftext|>
Token ID50256
Feature activation+1.30e+00

Pos logit contributions
 around+0.022
et+0.020
cy+0.020
 down+0.020
 air+0.019
Neg logit contributions
vern-0.022
ves-0.022
ades-0.019
 forgiveness-0.019
 mercy-0.019
TokenOnce
Token ID7454
Feature activation+2.95e+00

Pos logit contributions
ves+0.044
ades+0.039
vern+0.038
His+0.034
 forgiveness+0.031
Neg logit contributions
rated-0.094
et-0.092
ening-0.089
ishy-0.087
 around-0.082
Token upon
Token ID2402
Feature activation+3.59e+00

Pos logit contributions
ves+0.143
vern+0.142
ades+0.126
 backup+0.120
 forgiveness+0.119
Neg logit contributions
 around-0.169
 air-0.164
et-0.162
cy-0.158
rated-0.156
Token a
Token ID257
Feature activation+4.71e+00

Pos logit contributions
ves+0.071
vern+0.070
ades+0.061
 mercy+0.059
 backup+0.059
Neg logit contributions
 around-0.120
cy-0.113
rated-0.111
et-0.111
 down-0.110
Token strong
Token ID1913
Feature activation-2.56e+00

Pos logit contributions
ves+0.224
vern+0.220
ades+0.197
 mercy+0.191
 backup+0.191
Neg logit contributions
 around-0.288
cy-0.263
 air-0.262
 down-0.259
et-0.256
Token lizard
Token ID42406
Feature activation+1.72e-01

Pos logit contributions
|+0.166
 around+0.166
ained+0.159
rated+0.158
cy+0.156
Neg logit contributions
 wife-0.094
ves-0.092
 crew-0.084
keys-0.081
 fisherman-0.080
Token named
Token ID3706
Feature activation+4.55e-01

Pos logit contributions
vern+0.010
ves+0.010
ades+0.010
 backup+0.009
 mercy+0.009
Neg logit contributions
 around-0.009
cy-0.007
 down-0.007
 air-0.007
et-0.007
Token T
Token ID309
Feature activation-3.29e+00

Pos logit contributions
ves+0.024
vern+0.022
 backup+0.020
keys+0.020
ggy+0.020
Neg logit contributions
 around-0.024
cy-0.024
rated-0.023
 air-0.023
et-0.023
Tokenaz
Token ID1031
Feature activation-1.59e+01

Pos logit contributions
 around+0.204
cy+0.188
 air+0.187
et+0.186
 down+0.182
Neg logit contributions
ves-0.149
vern-0.143
 mercy-0.131
 backup-0.131
ades-0.129
Token.
Token ID13
Feature activation-4.07e-01

Pos logit contributions
 around+0.790
cy+0.749
 air+0.747
 down+0.723
|+0.698
Neg logit contributions
ves-0.956
vern-0.887
ades-0.811
keys-0.792
 mercy-0.773
Token He
Token ID679
Feature activation-1.26e+00

Pos logit contributions
 around+0.025
rated+0.023
cy+0.023
et+0.023
|+0.022
Neg logit contributions
ves-0.017
vern-0.016
His-0.016
 backup-0.016
ades-0.015
Token lived
Token ID5615
Feature activation-5.36e-01

Pos logit contributions
 around+0.057
cy+0.054
 down+0.052
 air+0.052
rated+0.050
Neg logit contributions
ves-0.080
vern-0.075
ades-0.069
keys-0.068
 mercy-0.067
Token happily
Token ID18177
Feature activation-3.51e-02

Pos logit contributions
 around+0.019
cy+0.017
 air+0.017
et+0.017
rated+0.016
Neg logit contributions
ves-0.038
vern-0.038
ades-0.035
 mercy-0.034
 backup-0.034
Token among
Token ID1871
Feature activation-2.04e+00

Pos logit contributions
 around+0.001
cy+0.001
 air+0.001
rated+0.001
et+0.001
Neg logit contributions
ves-0.002
vern-0.002
keys-0.002
ades-0.002
 mercy-0.002
Token shapes
Token ID15268
Feature activation+1.44e+00

Pos logit contributions
 around+0.083
 air+0.074
 down+0.071
cy+0.069
et+0.068
Neg logit contributions
vern-0.107
ves-0.102
ades-0.095
 mercy-0.095
keys-0.092
Token to
Token ID284
Feature activation+2.86e+00

Pos logit contributions
vern+0.091
ves+0.090
 mercy+0.083
 backup+0.081
ades+0.081
Neg logit contributions
 around-0.072
 down-0.061
 air-0.060
cy-0.059
et-0.058
Token design
Token ID1486
Feature activation+5.62e-01

Pos logit contributions
ves+0.158
vern+0.156
ades+0.142
 mercy+0.139
 backup+0.137
Neg logit contributions
 around-0.154
cy-0.139
 air-0.139
 down-0.136
et-0.134
Token a
Token ID257
Feature activation+4.72e+00

Pos logit contributions
ves+0.029
vern+0.028
ades+0.025
 mercy+0.025
 backup+0.024
Neg logit contributions
 around-0.032
cy-0.030
 air-0.030
 down-0.029
et-0.029
Token j
Token ID474
Feature activation-4.06e+00

Pos logit contributions
vern+0.254
ves+0.253
 mercy+0.228
ades+0.225
keys+0.220
Neg logit contributions
 around-0.264
 air-0.241
 down-0.234
cy-0.233
et-0.223
Tokenaz
Token ID1031
Feature activation-1.59e+01

Pos logit contributions
 around+0.230
 down+0.214
 air+0.211
cy+0.208
rated+0.206
Neg logit contributions
vern-0.211
ves-0.210
ades-0.192
 backup-0.178
keys-0.169
Tokenzy
Token ID7357
Feature activation-1.07e+01

Pos logit contributions
 around+0.750
 air+0.735
cy+0.728
|+0.696
 down+0.682
Neg logit contributions
ves-0.998
vern-0.891
ades-0.831
keys-0.796
ggy-0.793
Token picture
Token ID4286
Feature activation-2.48e-01

Pos logit contributions
 around+0.559
cy+0.527
 air+0.510
 down+0.506
|+0.503
Neg logit contributions
ves-0.589
vern-0.550
ades-0.512
keys-0.503
 forgiveness-0.495
Token.
Token ID13
Feature activation-4.07e-01

Pos logit contributions
 around+0.013
cy+0.012
 air+0.012
 down+0.011
|+0.011
Neg logit contributions
ves-0.014
vern-0.014
ades-0.013
 mercy-0.012
 backup-0.012
Token Then
Token ID3244
Feature activation-3.92e+00

Pos logit contributions
rated+0.017
et+0.017
 around+0.016
|+0.015
ening+0.015
Neg logit contributions
ves-0.023
vern-0.023
 backup-0.022
 forgiveness-0.022
ades-0.022
Token she
Token ID673
Feature activation+5.17e+00

Pos logit contributions
 around+0.239
 air+0.218
 down+0.217
cy+0.215
et+0.204
Neg logit contributions
vern-0.199
ves-0.196
ades-0.178
 mercy-0.169
keys-0.168
Tokenâ
Token ID22940
Feature activation-1.54e+00

Pos logit contributions
 around+0.018
et+0.017
rated+0.017
cy+0.016
ening+0.016
Neg logit contributions
vern-0.022
ves-0.022
 backup-0.020
ades-0.020
 forgiveness-0.020
Token
Token ID26391
Feature activation-1.46e+01

Pos logit contributions
 around+0.063
 down+0.056
 through+0.052
ening+0.052
cy+0.052
Neg logit contributions
ves-0.090
vern-0.087
ggy-0.082
His-0.077
 forgiveness-0.077
Token
Token ID198
Feature activation+7.28e-01

Pos logit contributions
 around+0.832
cy+0.763
et+0.750
 air+0.744
rated+0.743
Neg logit contributions
ves-0.797
vern-0.756
ades-0.689
keys-0.662
 backup-0.632
Token
Token ID198
Feature activation+7.40e-01

Pos logit contributions
ves+0.043
vern+0.043
 mercy+0.040
ades+0.040
 backup+0.040
Neg logit contributions
 around-0.035
 air-0.031
cy-0.031
 down-0.030
|-0.030
TokenM
Token ID44
Feature activation+6.07e+00

Pos logit contributions
vern+0.033
 mercy+0.032
ves+0.032
 backup+0.030
 forgiveness+0.030
Neg logit contributions
 around-0.045
|-0.042
cy-0.041
amp-0.041
 air-0.040
Tokenaz
Token ID1031
Feature activation-1.58e+01

Pos logit contributions
ves+0.255
vern+0.251
ades+0.220
 mercy+0.215
 backup+0.212
Neg logit contributions
 around-0.409
cy-0.379
 air-0.377
 down-0.372
et-0.366
Tokenzy
Token ID7357
Feature activation-1.06e+01

Pos logit contributions
 around+0.660
 air+0.638
cy+0.624
 down+0.619
|+0.580
Neg logit contributions
ves-1.100
vern-0.946
ades-0.916
ggy-0.900
keys-0.868
Token was
Token ID373
Feature activation+1.82e+00

Pos logit contributions
 around+0.535
 down+0.482
 air+0.481
cy+0.480
|+0.469
Neg logit contributions
ves-0.610
vern-0.577
ades-0.536
 mercy-0.525
keys-0.524
Token so
Token ID523
Feature activation-5.47e+00

Pos logit contributions
ves+0.100
vern+0.100
 mercy+0.088
 wife+0.088
 backup+0.087
Neg logit contributions
cy-0.089
 around-0.083
|-0.082
rated-0.080
 air-0.079
Token excited
Token ID6568
Feature activation-3.50e+00

Pos logit contributions
 around+0.290
cy+0.271
et+0.269
 air+0.269
|+0.260
Neg logit contributions
vern-0.296
ves-0.294
ades-0.262
 mercy-0.255
keys-0.254
Token about
Token ID546
Feature activation-1.36e+00

Pos logit contributions
 around+0.184
cy+0.170
 air+0.167
 down+0.163
et+0.162
Neg logit contributions
ves-0.195
vern-0.191
ades-0.175
 mercy-0.171
 backup-0.169
Token
Token ID198
Feature activation+7.32e-01

Pos logit contributions
vern+0.047
ves+0.046
 mercy+0.044
 backup+0.043
ades+0.043
Neg logit contributions
 around-0.035
cy-0.030
|-0.029
 air-0.029
 down-0.029
TokenOne
Token ID3198
Feature activation+6.71e+00

Pos logit contributions
vern+0.035
ves+0.033
 mercy+0.032
 forgiveness+0.031
keys+0.030
Neg logit contributions
 around-0.046
 air-0.041
|-0.041
cy-0.040
et-0.040
Token day
Token ID1110
Feature activation-1.16e+01

Pos logit contributions
ves+0.467
vern+0.447
 wife+0.423
His+0.418
keys+0.416
Neg logit contributions
 around-0.220
ening-0.204
et-0.199
 air-0.197
 down-0.194
Token,
Token ID11
Feature activation+8.80e-01

Pos logit contributions
 around+0.470
 down+0.410
 air+0.402
cy+0.394
 through+0.354
Neg logit contributions
vern-0.830
ves-0.798
 mercy-0.759
ades-0.749
keys-0.734
Token T
Token ID309
Feature activation-3.25e+00

Pos logit contributions
vern+0.058
ves+0.056
ades+0.052
 mercy+0.052
keys+0.050
Neg logit contributions
 around-0.041
 down-0.037
 air-0.036
cy-0.036
et-0.033
Tokenaz
Token ID1031
Feature activation-1.58e+01

Pos logit contributions
 around+0.187
cy+0.172
 air+0.170
 down+0.168
et+0.164
Neg logit contributions
ves-0.168
vern-0.166
ades-0.149
 mercy-0.145
 backup-0.143
Token heard
Token ID2982
Feature activation+2.24e+00

Pos logit contributions
 around+0.716
cy+0.695
 air+0.686
 down+0.666
|+0.649
Neg logit contributions
ves-1.016
vern-0.913
ades-0.854
ggy-0.835
His-0.826
Token some
Token ID617
Feature activation+9.54e+00

Pos logit contributions
vern+0.137
ves+0.127
keys+0.119
ades+0.118
 mercy+0.113
Neg logit contributions
 around-0.122
 air-0.110
 down-0.103
 through-0.097
et-0.094
Token voices
Token ID10839
Feature activation+3.98e+00

Pos logit contributions
ves+0.548
vern+0.547
ades+0.494
 backup+0.481
 mercy+0.481
Neg logit contributions
 around-0.495
 air-0.451
cy-0.436
 down-0.435
et-0.421
Token coming
Token ID2406
Feature activation+8.34e-01

Pos logit contributions
ves+0.277
vern+0.273
ades+0.255
 mercy+0.251
 backup+0.248
Neg logit contributions
 around-0.152
cy-0.138
 air-0.134
 down-0.129
et-0.127
Token from
Token ID422
Feature activation+6.28e+00

Pos logit contributions
vern+0.042
ves+0.041
 mercy+0.038
ades+0.038
 backup+0.037
Neg logit contributions
 around-0.046
 air-0.044
cy-0.044
et-0.043
|-0.041
Token up
Token ID510
Feature activation-7.09e+00

Pos logit contributions
 around+0.043
cy+0.040
 air+0.039
|+0.037
 down+0.036
Neg logit contributions
ves-0.075
vern-0.074
ades-0.069
 mercy-0.067
 backup-0.066
Token.
Token ID13
Feature activation-3.66e-01

Pos logit contributions
 around+0.317
cy+0.312
|+0.308
 air+0.302
rated+0.295
Neg logit contributions
ves-0.413
vern-0.409
ades-0.380
 mercy-0.371
 forgiveness-0.366
Token The
Token ID383
Feature activation-8.15e+00

Pos logit contributions
 around+0.013
cy+0.012
et+0.012
rated+0.012
|+0.011
Neg logit contributions
ves-0.026
vern-0.025
ades-0.024
 backup-0.024
 forgiveness-0.023
Token other
Token ID584
Feature activation+1.29e+00

Pos logit contributions
 around+0.467
 air+0.453
cy+0.423
 down+0.420
et+0.407
Neg logit contributions
ves-0.437
vern-0.423
ades-0.391
keys-0.372
 mercy-0.360
Token r
Token ID374
Feature activation+2.91e+00

Pos logit contributions
ves+0.066
vern+0.065
ades+0.059
 mercy+0.057
 backup+0.057
Neg logit contributions
 around-0.076
cy-0.069
 air-0.069
 down-0.068
et-0.066
Tokenaz
Token ID1031
Feature activation-1.58e+01

Pos logit contributions
vern+0.172
ves+0.169
ades+0.159
 mercy+0.154
 forgiveness+0.151
Neg logit contributions
 around-0.147
cy-0.129
 down-0.129
|-0.129
 air-0.126
Tokenors
Token ID669
Feature activation-5.01e+00

Pos logit contributions
 around+0.836
cy+0.778
 air+0.766
 down+0.753
|+0.732
Neg logit contributions
ves-0.910
vern-0.848
ades-0.781
keys-0.748
 mercy-0.739
Token saw
Token ID2497
Feature activation+3.62e-01

Pos logit contributions
 around+0.231
 air+0.223
|+0.219
amp+0.214
rated+0.213
Neg logit contributions
ves-0.271
vern-0.253
ades-0.249
keys-0.243
 forgiveness-0.239
Token this
Token ID428
Feature activation+2.92e+00

Pos logit contributions
vern+0.023
ves+0.023
ades+0.020
keys+0.020
 mercy+0.020
Neg logit contributions
 around-0.018
 air-0.016
 down-0.016
et-0.014
cy-0.014
Token and
Token ID290
Feature activation-1.58e+00

Pos logit contributions
ves+0.188
vern+0.186
ades+0.171
 mercy+0.168
 backup+0.167
Neg logit contributions
 around-0.130
cy-0.117
 air-0.114
 down-0.112
|-0.110
Token stopped
Token ID5025
Feature activation+2.81e+00

Pos logit contributions
 around+0.081
 down+0.070
 air+0.068
cy+0.064
et+0.063
Neg logit contributions
vern-0.107
ves-0.097
 backup-0.094
ades-0.093
 mercy-0.091
Token no
Token ID645
Feature activation+6.27e+00

Pos logit contributions
vern+0.076
ves+0.069
ades+0.069
 backup+0.065
keys+0.063
Neg logit contributions
 around-0.088
 air-0.079
 down-0.077
et-0.075
ening-0.071
Token.
Token ID13
Feature activation-3.67e-01

Pos logit contributions
ves+0.384
vern+0.379
ades+0.345
 mercy+0.344
 forgiveness+0.340
Neg logit contributions
 around-0.298
cy-0.272
 air-0.264
 down-0.259
|-0.258
Token He
Token ID679
Feature activation-1.22e+00

Pos logit contributions
 around+0.018
cy+0.017
rated+0.017
et+0.017
ening+0.017
Neg logit contributions
ves-0.020
vern-0.019
His-0.019
ades-0.019
 backup-0.018
Token said
Token ID531
Feature activation+1.48e+00

Pos logit contributions
 around+0.060
cy+0.054
 air+0.052
et+0.052
 down+0.050
Neg logit contributions
vern-0.076
ves-0.072
ades-0.069
 backup-0.067
keys-0.065
Token r
Token ID374
Feature activation+2.89e+00

Pos logit contributions
vern+0.083
ves+0.076
ades+0.071
 mercy+0.069
 backup+0.067
Neg logit contributions
 around-0.083
 air-0.074
 down-0.073
et-0.068
ening-0.065
Tokenaz
Token ID1031
Feature activation-1.58e+01

Pos logit contributions
vern+0.138
ades+0.137
ves+0.136
 mercy+0.117
 forgiveness+0.116
Neg logit contributions
 around-0.172
|-0.159
 air-0.158
 down-0.154
cy-0.153
Tokenors
Token ID669
Feature activation-5.03e+00

Pos logit contributions
 around+0.735
 air+0.704
cy+0.686
 down+0.674
|+0.649
Neg logit contributions
ves-1.006
vern-0.882
ades-0.863
His-0.825
ggy-0.811
Token were
Token ID547
Feature activation+7.37e-01

Pos logit contributions
 around+0.221
 air+0.216
cy+0.212
|+0.212
rated+0.203
Neg logit contributions
ves-0.298
vern-0.280
ades-0.267
 mercy-0.259
 forgiveness-0.258
Token sharp
Token ID7786
Feature activation+1.81e+00

Pos logit contributions
ves+0.041
vern+0.040
ades+0.037
 mercy+0.036
keys+0.035
Neg logit contributions
 around-0.040
 air-0.036
 down-0.036
cy-0.035
et-0.035
Token and
Token ID290
Feature activation-1.59e+00

Pos logit contributions
ves+0.100
vern+0.095
 mercy+0.090
 forgiveness+0.087
ades+0.087
Neg logit contributions
|-0.092
cy-0.088
 around-0.088
amp-0.081
rated-0.080
Token dangerous
Token ID4923
Feature activation+1.83e+00

Pos logit contributions
 around+0.094
cy+0.087
 air+0.086
 down+0.085
et+0.083
Neg logit contributions
ves-0.078
vern-0.077
ades-0.069
 mercy-0.068
 backup-0.067
Token was
Token ID373
Feature activation+1.84e+00

Pos logit contributions
 around+0.377
 air+0.364
cy+0.364
 down+0.362
rated+0.350
Neg logit contributions
ves-0.428
vern-0.389
keys-0.362
ades-0.356
ggy-0.343
Token never
Token ID1239
Feature activation+1.86e-01

Pos logit contributions
ves+0.103
vern+0.102
ades+0.095
keys+0.091
 mercy+0.091
Neg logit contributions
 around-0.100
 air-0.088
 down-0.088
cy-0.087
et-0.086
Token scared
Token ID12008
Feature activation-3.77e+00

Pos logit contributions
vern+0.011
ves+0.011
 mercy+0.010
 backup+0.010
 forgiveness+0.010
Neg logit contributions
 around-0.008
cy-0.008
 air-0.008
et-0.007
|-0.007
Token of
Token ID286
Feature activation+4.74e+00

Pos logit contributions
cy+0.205
 around+0.203
|+0.200
 air+0.199
et+0.196
Neg logit contributions
vern-0.176
ves-0.172
 backup-0.163
 mercy-0.162
 forgiveness-0.160
Token r
Token ID374
Feature activation+2.90e+00

Pos logit contributions
ves+0.258
vern+0.255
ades+0.230
 mercy+0.227
 backup+0.225
Neg logit contributions
 around-0.255
cy-0.236
 air-0.231
 down-0.227
et-0.224
Tokenaz
Token ID1031
Feature activation-1.58e+01

Pos logit contributions
vern+0.171
ades+0.168
ves+0.162
 mercy+0.150
ups+0.149
Neg logit contributions
 around-0.136
 air-0.124
|-0.123
cy-0.121
 down-0.118
Tokenors
Token ID669
Feature activation-5.01e+00

Pos logit contributions
 around+0.730
cy+0.694
 air+0.669
|+0.653
 down+0.646
Neg logit contributions
ves-0.989
vern-0.934
ades-0.868
keys-0.850
 mercy-0.837
Token again
Token ID757
Feature activation-3.75e-01

Pos logit contributions
 around+0.242
cy+0.236
 air+0.236
|+0.225
rated+0.223
Neg logit contributions
ves-0.273
vern-0.272
 mercy-0.249
 forgiveness-0.248
keys-0.245
Token.
Token ID13
Feature activation-3.49e-01

Pos logit contributions
 around+0.017
cy+0.016
 air+0.015
 down+0.015
et+0.015
Neg logit contributions
ves-0.023
vern-0.023
ades-0.021
 mercy-0.021
 backup-0.021
Token<|endoftext|>
Token ID50256
Feature activation+1.37e+00

Pos logit contributions
 around+0.021
et+0.020
rated+0.020
 down+0.019
cy+0.019
Neg logit contributions
vern-0.016
ves-0.015
 forgiveness-0.014
His-0.014
 backup-0.014
TokenW
Token ID54
Feature activation+8.92e-01

Pos logit contributions
ves+0.050
ades+0.044
His+0.039
vern+0.039
lor+0.036
Neg logit contributions
rated-0.095
et-0.093
ishy-0.090
ening-0.089
 around-0.081
Token the
Token ID262
Feature activation-4.06e+00

Pos logit contributions
ves+0.164
vern+0.158
 mercy+0.146
 backup+0.145
 forgiveness+0.143
Neg logit contributions
 around-0.147
cy-0.145
|-0.133
 air-0.132
rated-0.132
Token rhythm
Token ID18662
Feature activation+1.18e+00

Pos logit contributions
 around+0.181
cy+0.168
 down+0.157
et+0.155
|+0.155
Neg logit contributions
ves-0.257
vern-0.253
ades-0.235
 mercy-0.232
 backup-0.231
Token of
Token ID286
Feature activation+4.73e+00

Pos logit contributions
ves+0.063
vern+0.057
ades+0.054
 backup+0.051
keys+0.051
Neg logit contributions
cy-0.063
 around-0.061
|-0.060
rated-0.059
 air-0.058
Token a
Token ID257
Feature activation+4.78e+00

Pos logit contributions
ves+0.285
vern+0.280
ades+0.256
 mercy+0.254
 backup+0.253
Neg logit contributions
 around-0.227
cy-0.211
 air-0.200
 down-0.199
et-0.196
Token j
Token ID474
Feature activation-4.01e+00

Pos logit contributions
ves+0.260
vern+0.257
ades+0.232
 mercy+0.228
 backup+0.225
Neg logit contributions
 around-0.262
cy-0.237
 air-0.237
 down-0.232
et-0.227
Tokenaz
Token ID1031
Feature activation-1.58e+01

Pos logit contributions
 around+0.246
 down+0.236
rated+0.234
cy+0.230
 air+0.229
Neg logit contributions
ves-0.185
vern-0.183
ades-0.165
 backup-0.147
ggy-0.135
Tokenzy
Token ID7357
Feature activation-1.06e+01

Pos logit contributions
cy+0.773
 around+0.756
 air+0.734
|+0.710
 down+0.695
Neg logit contributions
ves-0.990
vern-0.849
ades-0.792
ggy-0.784
keys-0.773
Token tune
Token ID14009
Feature activation-1.41e+00

Pos logit contributions
cy+0.501
 around+0.485
|+0.480
rated+0.469
 down+0.449
Neg logit contributions
ves-0.613
vern-0.524
keys-0.523
ades-0.513
 forgiveness-0.492
Token.
Token ID13
Feature activation-3.49e-01

Pos logit contributions
 around+0.064
cy+0.059
 air+0.057
 down+0.056
|+0.055
Neg logit contributions
ves-0.089
vern-0.087
ades-0.080
 mercy-0.079
 backup-0.078
Token Everywhere
Token ID48201
Feature activation-3.54e+00

Pos logit contributions
cy+0.015
rated+0.014
|+0.014
et+0.013
ening+0.013
Neg logit contributions
ves-0.022
 backup-0.020
His-0.019
 wife-0.019
vern-0.019
Token she
Token ID673
Feature activation+5.21e+00

Pos logit contributions
 around+0.259
rated+0.258
|+0.257
cy+0.256
et+0.254
Neg logit contributions
ves-0.111
vern-0.095
 backup-0.080
 forgiveness-0.077
ades-0.077
Token that
Token ID326
Feature activation+4.15e+00

Pos logit contributions
vern+0.080
ves+0.079
ades+0.072
 mercy+0.070
 backup+0.070
Neg logit contributions
 around-0.088
 air-0.080
 down-0.078
cy-0.077
et-0.077
Token.
Token ID13
Feature activation-3.16e-01

Pos logit contributions
vern+0.205
ves+0.198
ades+0.181
keys+0.174
 mercy+0.173
Neg logit contributions
 around-0.257
 air-0.235
 down-0.229
et-0.224
cy-0.224
Token He
Token ID679
Feature activation-1.20e+00

Pos logit contributions
 around+0.017
cy+0.016
rated+0.016
et+0.016
ening+0.015
Neg logit contributions
ves-0.017
vern-0.016
His-0.016
ades-0.016
 backup-0.015
Token thought
Token ID1807
Feature activation-1.33e+00

Pos logit contributions
 around+0.057
cy+0.051
 air+0.050
et+0.049
 down+0.048
Neg logit contributions
vern-0.076
ves-0.074
ades-0.068
 backup-0.067
 mercy-0.066
Token r
Token ID374
Feature activation+2.93e+00

Pos logit contributions
 around+0.076
 air+0.066
 down+0.065
et+0.064
cy+0.062
Neg logit contributions
vern-0.072
ves-0.070
 mercy-0.064
ades-0.063
keys-0.063
Tokenaz
Token ID1031
Feature activation-1.58e+01

Pos logit contributions
ades+0.133
ves+0.129
vern+0.127
keys+0.107
ups+0.104
Neg logit contributions
 around-0.183
 air-0.174
|-0.167
 down-0.166
cy-0.165
Tokenors
Token ID669
Feature activation-4.99e+00

Pos logit contributions
 around+0.755
 air+0.718
cy+0.702
 down+0.693
|+0.673
Neg logit contributions
ves-0.976
ades-0.824
vern-0.821
His-0.795
ggy-0.761
Token were
Token ID547
Feature activation+7.78e-01

Pos logit contributions
 air+0.214
 around+0.212
|+0.208
cy+0.202
rated+0.199
Neg logit contributions
ves-0.288
vern-0.263
ades-0.258
 forgiveness-0.248
keys-0.245
Token fun
Token ID1257
Feature activation-5.96e-01

Pos logit contributions
ves+0.044
vern+0.043
ades+0.039
 mercy+0.038
 backup+0.038
Neg logit contributions
 around-0.042
 air-0.038
 down-0.037
cy-0.037
et-0.036
Token and
Token ID290
Feature activation-1.55e+00

Pos logit contributions
 around+0.027
 air+0.023
cy+0.023
 down+0.023
et+0.022
Neg logit contributions
ves-0.039
vern-0.039
ades-0.036
 mercy-0.035
keys-0.035
Token cool
Token ID3608
Feature activation-4.24e+00

Pos logit contributions
 around+0.083
 air+0.074
 down+0.072
cy+0.072
et+0.070
Neg logit contributions
vern-0.089
ves-0.088
ades-0.081
 backup-0.077
 mercy-0.077
Token.
Token ID13
Feature activation-3.25e-01

Pos logit contributions
ves+0.168
vern+0.165
ades+0.152
 mercy+0.149
 backup+0.147
Neg logit contributions
 around-0.120
cy-0.114
 air-0.110
|-0.107
et-0.105
Token As
Token ID1081
Feature activation+2.34e+00

Pos logit contributions
 around+0.015
cy+0.014
et+0.014
rated+0.014
 air+0.014
Neg logit contributions
ves-0.019
vern-0.018
ades-0.018
 backup-0.017
 forgiveness-0.016
Token they
Token ID484
Feature activation+9.33e+00

Pos logit contributions
vern+0.118
ves+0.111
ades+0.104
 mercy+0.102
keys+0.101
Neg logit contributions
 around-0.146
 air-0.131
 down-0.131
cy-0.130
 through-0.123
Token passed
Token ID3804
Feature activation+1.42e+00

Pos logit contributions
ves+0.536
vern+0.521
ades+0.482
 mercy+0.472
keys+0.470
Neg logit contributions
 around-0.471
 air-0.426
cy-0.425
 down-0.417
et-0.410
Token T
Token ID309
Feature activation-3.21e+00

Pos logit contributions
ves+0.081
vern+0.078
ades+0.075
 backup+0.073
 mercy+0.072
Neg logit contributions
 around-0.064
rated-0.064
 air-0.061
et-0.061
|-0.060
Tokenaz
Token ID1031
Feature activation-1.58e+01

Pos logit contributions
 around+0.149
cy+0.134
 air+0.132
 down+0.130
|+0.126
Neg logit contributions
ves-0.203
vern-0.201
ades-0.186
 mercy-0.179
 backup-0.178
Token,
Token ID11
Feature activation+9.42e-01

Pos logit contributions
 around+0.684
cy+0.645
 air+0.638
 down+0.611
|+0.604
Neg logit contributions
ves-1.051
vern-0.946
ades-0.895
keys-0.878
 mercy-0.857
Token the
Token ID262
Feature activation-4.02e+00

Pos logit contributions
vern+0.062
ves+0.059
ades+0.055
 mercy+0.054
keys+0.053
Neg logit contributions
 around-0.045
 air-0.040
 down-0.040
cy-0.039
 through-0.036
Token little
Token ID1310
Feature activation+2.55e+00

Pos logit contributions
 around+0.231
cy+0.221
et+0.213
|+0.212
rated+0.212
Neg logit contributions
ves-0.194
vern-0.191
 mercy-0.176
ades-0.172
 backup-0.171
Token boy
Token ID2933
Feature activation-6.57e+00

Pos logit contributions
 wife+0.108
ves+0.104
 mercy+0.103
vern+0.100
 forgiveness+0.100
Neg logit contributions
|-0.144
rated-0.140
 around-0.138
ained-0.134
et-0.131
Token stopped
Token ID5025
Feature activation+2.83e+00

Pos logit contributions
 around+0.316
cy+0.270
 down+0.270
 air+0.269
et+0.261
Neg logit contributions
vern-0.430
ves-0.411
 mercy-0.381
ades-0.379
 backup-0.377
Tokenâ
Token ID22940
Feature activation-9.82e-01

Pos logit contributions
ves+0.064
vern+0.062
ades+0.057
keys+0.057
 forgiveness+0.056
Neg logit contributions
 around-0.043
cy-0.039
et-0.039
 air-0.039
rated-0.038
Token
Token ID26391
Feature activation-1.42e+01

Pos logit contributions
 around+0.043
 down+0.039
 air+0.035
 through+0.034
cy+0.033
Neg logit contributions
ves-0.054
vern-0.053
His-0.049
 forgiveness-0.048
keys-0.048
Token
Token ID198
Feature activation+1.04e+00

Pos logit contributions
 around+0.734
 air+0.668
cy+0.666
et+0.653
 down+0.652
Neg logit contributions
ves-0.840
vern-0.797
ades-0.737
keys-0.714
ggy-0.678
Token
Token ID198
Feature activation+9.58e-01

Pos logit contributions
ves+0.059
vern+0.058
ades+0.053
 mercy+0.052
 backup+0.052
Neg logit contributions
 around-0.054
cy-0.049
 air-0.049
 down-0.048
et-0.047
TokenM
Token ID44
Feature activation+6.26e+00

Pos logit contributions
ves+0.042
vern+0.041
 mercy+0.039
 forgiveness+0.037
ades+0.037
Neg logit contributions
 around-0.060
|-0.056
cy-0.055
 air-0.054
amp-0.053
Tokenaz
Token ID1031
Feature activation-1.57e+01

Pos logit contributions
ves+0.298
vern+0.293
ades+0.260
 mercy+0.256
 backup+0.254
Neg logit contributions
 around-0.382
cy-0.354
 air-0.353
 down-0.342
et-0.341
Tokenzy
Token ID7357
Feature activation-1.06e+01

Pos logit contributions
 around+0.639
 air+0.608
cy+0.596
 down+0.595
|+0.533
Neg logit contributions
ves-1.086
vern-0.985
ades-0.940
ggy-0.916
keys-0.901
Tokenâ
Token ID22940
Feature activation-1.45e+00

Pos logit contributions
 around+0.563
 air+0.514
cy+0.514
 down+0.513
|+0.506
Neg logit contributions
ves-0.567
vern-0.522
keys-0.493
ades-0.492
 mercy-0.477
Token
Token ID26391
Feature activation-1.46e+01

Pos logit contributions
 around+0.059
 down+0.051
 through+0.046
cy+0.044
 air+0.043
Neg logit contributions
vern-0.085
His-0.081
ves-0.080
 forgiveness-0.078
ggy-0.077
Token
Token ID8151
Feature activation-1.45e+00

Pos logit contributions
 around+0.816
 air+0.742
cy+0.741
 down+0.727
et+0.715
Neg logit contributions
ves-0.784
vern-0.764
ades-0.695
keys-0.670
 backup-0.663
Tokens
Token ID82
Feature activation+6.38e+00

Pos logit contributions
 around+0.071
 air+0.068
cy+0.064
 down+0.064
ening+0.063
Neg logit contributions
ves-0.086
vern-0.083
ades-0.077
keys-0.072
 backup-0.071
Token about
Token ID546
Feature activation-1.32e+00

Pos logit contributions
vern+0.125
ves+0.123
ades+0.111
keys+0.108
 backup+0.102
Neg logit contributions
 around-0.133
 air-0.121
 down-0.115
et-0.109
ening-0.106
Token a
Token ID257
Feature activation+4.83e+00

Pos logit contributions
 around+0.069
 down+0.060
 air+0.059
ening+0.055
et+0.054
Neg logit contributions
ves-0.080
vern-0.078
ades-0.074
keys-0.071
 backup-0.068
Token cave
Token ID11527
Feature activation+2.00e+00

Pos logit contributions
ves+0.279
vern+0.264
ades+0.250
keys+0.239
 mercy+0.230
Neg logit contributions
 around-0.260
 air-0.239
 down-0.234
cy-0.230
 night-0.215
Token with
Token ID351
Feature activation+4.37e+00

Pos logit contributions
ves+0.126
vern+0.124
ades+0.114
 mercy+0.112
 backup+0.111
Neg logit contributions
 around-0.092
cy-0.082
 air-0.082
 down-0.080
et-0.078
Token a
Token ID257
Feature activation+4.81e+00

Pos logit contributions
ves+0.248
vern+0.245
ades+0.223
keys+0.222
 mercy+0.202
Neg logit contributions
 around-0.250
 air-0.231
 down-0.216
et-0.205
 through-0.202
Token treasure
Token ID14068
Feature activation+1.15e+01

Pos logit contributions
ves+0.286
vern+0.274
ades+0.255
keys+0.250
 mercy+0.246
Neg logit contributions
 around-0.250
 air-0.230
 down-0.222
cy-0.204
ening-0.197
Token inside
Token ID2641
Feature activation-3.20e+00

Pos logit contributions
vern+0.710
ves+0.708
ades+0.649
 mercy+0.636
 backup+0.632
Neg logit contributions
 around-0.558
 air-0.488
 down-0.482
cy-0.473
et-0.466
Token.
Token ID13
Feature activation-3.11e-01

Pos logit contributions
 around+0.152
cy+0.144
 air+0.138
|+0.136
et+0.134
Neg logit contributions
ves-0.190
vern-0.184
ades-0.170
 mercy-0.167
 forgiveness-0.165
Token The
Token ID383
Feature activation-8.09e+00

Pos logit contributions
 around+0.012
cy+0.011
 air+0.010
et+0.010
 down+0.010
Neg logit contributions
ves-0.022
vern-0.021
ades-0.020
 mercy-0.020
 backup-0.020
Token old
Token ID1468
Feature activation-2.28e+00

Pos logit contributions
 around+0.379
 air+0.344
cy+0.326
 down+0.326
et+0.312
Neg logit contributions
ves-0.518
vern-0.513
ades-0.471
keys-0.461
 mercy-0.456
Token man
Token ID582
Feature activation+3.85e+00

Pos logit contributions
 around+0.145
 air+0.135
 down+0.132
cy+0.127
et+0.124
Neg logit contributions
vern-0.110
ves-0.109
ades-0.098
keys-0.096
 backup-0.094
Token us
Token ID514
Feature activation+1.28e-01

Pos logit contributions
 around+0.021
 air+0.019
cy+0.019
 down+0.018
et+0.018
Neg logit contributions
ves-0.021
vern-0.021
ades-0.019
 mercy-0.019
 backup-0.019
Token feel
Token ID1254
Feature activation-2.98e+00

Pos logit contributions
ves+0.008
vern+0.008
ades+0.007
 mercy+0.007
 backup+0.007
Neg logit contributions
 around-0.006
 air-0.006
 down-0.006
cy-0.005
et-0.005
Token something
Token ID1223
Feature activation+1.38e+01

Pos logit contributions
 around+0.162
cy+0.153
 air+0.148
 down+0.146
|+0.145
Neg logit contributions
ves-0.157
vern-0.157
ades-0.140
 mercy-0.138
 backup-0.137
Token,
Token ID11
Feature activation+9.31e-01

Pos logit contributions
ves+0.755
vern+0.742
ades+0.676
 mercy+0.665
 backup+0.660
Neg logit contributions
 around-0.777
 air-0.690
 down-0.681
cy-0.662
et-0.647
Token or
Token ID393
Feature activation+1.07e+00

Pos logit contributions
ves+0.064
vern+0.064
ades+0.059
 mercy+0.058
 backup+0.057
Neg logit contributions
 around-0.039
 air-0.034
 down-0.033
cy-0.032
et-0.031
Token something
Token ID1223
Feature activation+1.38e+01

Pos logit contributions
vern+0.061
ves+0.061
ades+0.056
 backup+0.051
 mercy+0.051
Neg logit contributions
 around-0.061
 air-0.054
 down-0.053
cy-0.049
 through-0.048
Token that
Token ID326
Feature activation+4.16e+00

Pos logit contributions
vern+0.803
ves+0.801
ades+0.733
 mercy+0.723
 backup+0.716
Neg logit contributions
 around-0.721
 air-0.636
 down-0.619
cy-0.601
et-0.589
Token reminds
Token ID17603
Feature activation+1.89e+00

Pos logit contributions
ves+0.282
vern+0.277
ades+0.257
 mercy+0.253
 backup+0.251
Neg logit contributions
 around-0.170
cy-0.151
 air-0.148
 down-0.145
et-0.142
Token us
Token ID514
Feature activation+1.22e-01

Pos logit contributions
vern+0.120
ves+0.120
ades+0.110
 mercy+0.107
 backup+0.106
Neg logit contributions
 around-0.087
 air-0.077
cy-0.074
 down-0.074
et-0.072
Token of
Token ID286
Feature activation+4.78e+00

Pos logit contributions
ves+0.008
vern+0.007
ades+0.007
 mercy+0.007
keys+0.007
Neg logit contributions
 around-0.006
 air-0.005
 down-0.005
 through-0.005
 over-0.004
Token something
Token ID1223
Feature activation+1.38e+01

Pos logit contributions
ves+0.273
vern+0.273
ades+0.251
 mercy+0.243
keys+0.239
Neg logit contributions
 around-0.249
 air-0.225
 down-0.216
et-0.213
cy-0.213
Token,
Token ID11
Feature activation+9.43e-01

Pos logit contributions
 around+0.003
cy+0.003
 air+0.003
et+0.003
|+0.002
Neg logit contributions
ves-0.004
vern-0.004
ades-0.003
 mercy-0.003
 backup-0.003
Token as
Token ID355
Feature activation+4.69e+00

Pos logit contributions
ves+0.051
vern+0.051
ades+0.046
 mercy+0.045
 backup+0.044
Neg logit contributions
 around-0.053
 down-0.047
 air-0.047
cy-0.047
et-0.046
Token he
Token ID339
Feature activation+9.49e+00

Pos logit contributions
ves+0.204
vern+0.200
ades+0.176
 mercy+0.173
 backup+0.170
Neg logit contributions
 around-0.306
cy-0.284
 air-0.282
 down-0.278
et-0.275
Token moved
Token ID3888
Feature activation+3.26e-01

Pos logit contributions
vern+0.624
ves+0.590
 mercy+0.553
 forgiveness+0.548
 backup+0.542
Neg logit contributions
 around-0.449
cy-0.391
 air-0.388
 down-0.377
et-0.376
Token his
Token ID465
Feature activation+7.87e+00

Pos logit contributions
ves+0.019
vern+0.018
ades+0.017
 backup+0.017
 mercy+0.017
Neg logit contributions
 around-0.015
cy-0.015
 air-0.014
rated-0.014
|-0.014
Token soldiers
Token ID5795
Feature activation+1.10e+01

Pos logit contributions
ves+0.417
vern+0.413
ades+0.369
 mercy+0.363
keys+0.357
Neg logit contributions
 around-0.455
 air-0.412
cy-0.406
 down-0.405
et-0.390
Token forward
Token ID2651
Feature activation-9.96e+00

Pos logit contributions
ves+0.816
vern+0.809
ades+0.752
 mercy+0.747
 backup+0.746
Neg logit contributions
 around-0.342
cy-0.325
 air-0.310
|-0.297
et-0.290
Token.
Token ID13
Feature activation-3.12e-01

Pos logit contributions
 around+0.496
cy+0.465
 air+0.459
et+0.440
|+0.440
Neg logit contributions
ves-0.567
vern-0.558
ades-0.511
 mercy-0.501
 backup-0.499
Token "
Token ID366
Feature activation+3.59e+00

Pos logit contributions
 around+0.013
cy+0.013
et+0.012
rated+0.012
 air+0.012
Neg logit contributions
ves-0.020
vern-0.019
ades-0.018
 backup-0.018
 mercy-0.017
TokenYou
Token ID1639
Feature activation-4.63e+00

Pos logit contributions
ves+0.195
vern+0.191
ades+0.175
 backup+0.169
 mercy+0.169
Neg logit contributions
 around-0.193
cy-0.177
 air-0.174
 down-0.173
et-0.170
Token have
Token ID423
Feature activation-3.45e+00

Pos logit contributions
 around+0.186
cy+0.163
 air+0.162
 down+0.158
et+0.153
Neg logit contributions
ves-0.319
vern-0.315
ades-0.292
 mercy-0.287
 backup-0.285
Token.
Token ID13
Feature activation-3.23e-01

Pos logit contributions
ves+0.095
vern+0.093
ades+0.085
keys+0.083
 mercy+0.083
Neg logit contributions
 around-0.088
 down-0.077
 air-0.077
cy-0.075
et-0.073
Token The
Token ID383
Feature activation-8.11e+00

Pos logit contributions
 around+0.014
cy+0.012
et+0.012
rated+0.012
 air+0.012
Neg logit contributions
vern-0.021
ves-0.021
 backup-0.020
ades-0.019
 mercy-0.019
Token pilot
Token ID8022
Feature activation+2.35e+00

Pos logit contributions
 around+0.482
 air+0.442
cy+0.439
 down+0.431
et+0.423
Neg logit contributions
ves-0.411
vern-0.406
ades-0.365
 mercy-0.354
 backup-0.351
Token told
Token ID1297
Feature activation+5.46e+00

Pos logit contributions
vern+0.132
ves+0.132
ades+0.120
 backup+0.117
 mercy+0.116
Neg logit contributions
 around-0.125
cy-0.113
 air-0.112
 down-0.110
et-0.108
Token him
Token ID683
Feature activation-1.15e+00

Pos logit contributions
ves+0.319
vern+0.312
 mercy+0.286
ades+0.285
 backup+0.282
Neg logit contributions
 around-0.275
cy-0.255
 air-0.246
 down-0.244
et-0.238
Token something
Token ID1223
Feature activation+1.38e+01

Pos logit contributions
 around+0.074
 down+0.064
 air+0.063
 through+0.059
et+0.059
Neg logit contributions
vern-0.055
ves-0.054
ades-0.052
keys-0.047
 backup-0.046
Token special
Token ID2041
Feature activation+5.17e+00

Pos logit contributions
ves+0.777
vern+0.765
ades+0.702
 mercy+0.683
 backup+0.682
Neg logit contributions
 around-0.739
 air-0.656
cy-0.649
 down-0.647
et-0.630
Token;
Token ID26
Feature activation+4.72e+00

Pos logit contributions
ves+0.318
vern+0.315
ades+0.291
 mercy+0.284
 backup+0.284
Neg logit contributions
 around-0.248
cy-0.218
 air-0.218
 down-0.213
et-0.209
Token he
Token ID339
Feature activation+9.49e+00

Pos logit contributions
ves+0.259
vern+0.258
ades+0.238
keys+0.221
 mercy+0.218
Neg logit contributions
 around-0.276
 down-0.247
 air-0.244
 through-0.223
cy-0.219
Token said
Token ID531
Feature activation+1.53e+00

Pos logit contributions
ves+0.605
vern+0.602
ades+0.556
 backup+0.543
 mercy+0.542
Neg logit contributions
 around-0.438
cy-0.384
 air-0.379
 down-0.372
et-0.364
Token:
Token ID25
Feature activation+4.62e+00

Pos logit contributions
ves+0.075
vern+0.075
ades+0.069
 backup+0.064
keys+0.063
Neg logit contributions
 around-0.096
 air-0.083
 down-0.082
ening-0.076
et-0.075
Token.
Token ID13
Feature activation+2.96e+00

Pos logit contributions
 around+0.060
 down+0.052
cy+0.052
 air+0.050
et+0.048
Neg logit contributions
ves-0.087
vern-0.086
ades-0.080
 mercy-0.079
keys-0.079
Token They
Token ID1119
Feature activation-4.38e-01

Pos logit contributions
ves+0.194
vern+0.188
ades+0.176
keys+0.173
 backup+0.172
Neg logit contributions
 around-0.120
cy-0.109
et-0.108
 air-0.108
rated-0.106
Token explored
Token ID18782
Feature activation+1.86e+00

Pos logit contributions
 around+0.021
cy+0.020
 air+0.020
 down+0.019
et+0.019
Neg logit contributions
ves-0.025
vern-0.024
 mercy-0.023
ades-0.022
 backup-0.022
Token the
Token ID262
Feature activation-3.35e+00

Pos logit contributions
ves+0.112
vern+0.107
ades+0.100
 mercy+0.097
 backup+0.097
Neg logit contributions
 around-0.086
cy-0.083
 air-0.081
|-0.078
et-0.078
Token brilliant
Token ID10457
Feature activation-8.40e-01

Pos logit contributions
 around+0.171
cy+0.157
 down+0.154
 air+0.151
et+0.151
Neg logit contributions
ves-0.184
vern-0.180
ades-0.170
 backup-0.165
 mercy-0.162
Token coral
Token ID29537
Feature activation+1.03e+01

Pos logit contributions
 around+0.042
|+0.040
rated+0.040
cy+0.039
ained+0.039
Neg logit contributions
ves-0.043
ades-0.041
vern-0.041
 forgiveness-0.038
 backup-0.038
Token and
Token ID290
Feature activation-1.30e+00

Pos logit contributions
vern+0.514
ves+0.508
 mercy+0.457
 backup+0.453
ades+0.442
Neg logit contributions
 around-0.629
 air-0.567
cy-0.560
 down-0.553
et-0.536
Token watched
Token ID7342
Feature activation+1.20e+00

Pos logit contributions
 around+0.065
cy+0.059
 air+0.058
 down+0.057
et+0.056
Neg logit contributions
ves-0.077
vern-0.075
ades-0.069
 mercy-0.068
 backup-0.067
Token the
Token ID262
Feature activation-3.88e+00

Pos logit contributions
ves+0.070
vern+0.069
ades+0.063
 mercy+0.062
 backup+0.062
Neg logit contributions
 around-0.060
cy-0.055
 air-0.054
 down-0.053
et-0.052
Token fish
Token ID5916
Feature activation+7.21e+00

Pos logit contributions
 around+0.229
 air+0.210
cy+0.207
 down+0.204
et+0.197
Neg logit contributions
ves-0.198
vern-0.197
ades-0.174
 mercy-0.171
 backup-0.169
Token swimming
Token ID14899
Feature activation+4.11e+00

Pos logit contributions
vern+0.427
ves+0.424
 mercy+0.380
ades+0.379
 backup+0.376
Neg logit contributions
 around-0.382
 down-0.335
 air-0.331
cy-0.327
et-0.314
Token and
Token ID290
Feature activation-1.72e+00

Pos logit contributions
ves+0.115
vern+0.100
His+0.095
ades+0.092
keys+0.092
Neg logit contributions
 around-0.119
cy-0.117
|-0.116
 air-0.114
 down-0.110
Token his
Token ID465
Feature activation+7.72e+00

Pos logit contributions
 around+0.124
cy+0.117
 air+0.116
et+0.113
|+0.113
Neg logit contributions
ves-0.060
vern-0.055
 forgiveness-0.051
 mercy-0.049
His-0.047
Token mom
Token ID1995
Feature activation+3.68e+00

Pos logit contributions
ves+0.303
vern+0.296
ades+0.256
keys+0.248
 mercy+0.247
Neg logit contributions
 around-0.549
 air-0.512
cy-0.508
 down-0.500
et-0.487
Tokenmy
Token ID1820
Feature activation-8.98e+00

Pos logit contributions
ves+0.258
vern+0.245
ades+0.243
His+0.241
 mercy+0.236
Neg logit contributions
 around-0.102
|-0.099
 air-0.097
rated-0.092
cy-0.089
Token had
Token ID550
Feature activation-4.15e+00

Pos logit contributions
 around+0.477
 air+0.447
cy+0.446
|+0.444
rated+0.430
Neg logit contributions
ves-0.471
vern-0.441
ades-0.410
 mercy-0.398
keys-0.397
Token a
Token ID257
Feature activation+4.66e+00

Pos logit contributions
 around+0.173
 air+0.152
 down+0.146
et+0.138
cy+0.133
Neg logit contributions
ves-0.291
vern-0.283
keys-0.265
ades-0.263
 mercy-0.259
Token brilliant
Token ID10457
Feature activation-1.47e+00

Pos logit contributions
ves+0.266
vern+0.259
ades+0.237
 mercy+0.234
keys+0.233
Neg logit contributions
 around-0.245
cy-0.224
 air-0.222
 down-0.218
et-0.211
Token time
Token ID640
Feature activation-8.25e+00

Pos logit contributions
 around+0.057
cy+0.051
 down+0.049
|+0.049
 air+0.049
Neg logit contributions
ves-0.102
vern-0.101
ades-0.093
 backup-0.090
 mercy-0.090
Token riding
Token ID10311
Feature activation-1.39e+00

Pos logit contributions
 around+0.356
 down+0.301
 air+0.300
cy+0.296
et+0.284
Neg logit contributions
ves-0.559
vern-0.556
ades-0.512
 mercy-0.509
keys-0.501
Token in
Token ID287
Feature activation-6.78e+00

Pos logit contributions
cy+0.063
rated+0.063
|+0.061
 air+0.059
 around+0.058
Neg logit contributions
ves-0.084
vern-0.075
ades-0.072
His-0.069
 mercy-0.069
Token the
Token ID262
Feature activation-4.16e+00

Pos logit contributions
 around+0.332
rated+0.324
cy+0.321
|+0.304
et+0.302
Neg logit contributions
ves-0.375
vern-0.373
 backup-0.340
 mercy-0.337
 forgiveness-0.336
Token cool
Token ID3608
Feature activation-4.41e+00

Pos logit contributions
 around+0.319
cy+0.308
et+0.301
 air+0.293
ening+0.289
Neg logit contributions
vern-0.285
ves-0.284
ades-0.255
His-0.242
 backup-0.237
Token.
Token ID13
Feature activation-4.90e-01

Pos logit contributions
|+0.283
cy+0.264
rated+0.258
amp+0.247
zie+0.244
Neg logit contributions
ves-0.184
vern-0.169
ades-0.157
 mercy-0.152
 backup-0.147
Token
Token ID220
Feature activation-4.20e+00

Pos logit contributions
 around+0.026
et+0.026
cy+0.025
ening+0.025
rated+0.025
Neg logit contributions
ves-0.025
vern-0.023
His-0.023
ades-0.023
 backup-0.021
Token
Token ID198
Feature activation+6.12e-01

Pos logit contributions
 around+0.220
cy+0.202
 air+0.201
 down+0.195
et+0.194
Neg logit contributions
ves-0.236
vern-0.233
ades-0.212
 mercy-0.205
 backup-0.204
Token
Token ID198
Feature activation+6.12e-01

Pos logit contributions
ves+0.036
vern+0.035
ades+0.032
 mercy+0.032
 backup+0.031
Neg logit contributions
 around-0.031
cy-0.028
 air-0.028
 down-0.027
et-0.027
TokenLater
Token ID18602
Feature activation+5.99e+00

Pos logit contributions
vern+0.029
ves+0.027
 mercy+0.026
 forgiveness+0.025
 backup+0.025
Neg logit contributions
 around-0.040
cy-0.036
 down-0.036
 air-0.035
et-0.034
Token that
Token ID326
Feature activation+3.99e+00

Pos logit contributions
ves+0.216
vern+0.207
ades+0.182
 mercy+0.181
 backup+0.177
Neg logit contributions
 around-0.425
cy-0.402
 air-0.394
et-0.392
|-0.389
Token day
Token ID1110
Feature activation-1.17e+01

Pos logit contributions
ves+0.295
vern+0.284
ades+0.262
 forgiveness+0.262
His+0.261
Neg logit contributions
 around-0.118
et-0.111
cy-0.105
 air-0.100
ening-0.096
Token,
Token ID11
Feature activation+7.57e-01

Pos logit contributions
 around+0.564
cy+0.510
 air+0.504
et+0.493
 down+0.489
Neg logit contributions
ves-0.709
vern-0.689
ades-0.637
 backup-0.622
 mercy-0.622
Token Tim
Token ID5045
Feature activation-7.47e+00

Pos logit contributions
vern+0.060
ves+0.060
ades+0.056
 mercy+0.055
keys+0.055
Neg logit contributions
 around-0.023
cy-0.019
 air-0.019
 down-0.019
et-0.017
Tokenmy
Token ID1820
Feature activation-9.00e+00

Pos logit contributions
 around+0.277
 air+0.228
ening+0.226
|+0.216
 down+0.208
Neg logit contributions
vern-0.472
ves-0.456
His-0.446
 mercy-0.446
 forgiveness-0.444
Token she
Token ID673
Feature activation+5.01e+00

Pos logit contributions
 around+0.053
 air+0.048
 down+0.047
cy+0.047
et+0.044
Neg logit contributions
vern-0.050
ves-0.049
ades-0.045
 backup-0.043
 mercy-0.042
Token replied
Token ID8712
Feature activation+9.50e-01

Pos logit contributions
vern+0.329
ves+0.311
 backup+0.307
ades+0.304
 charity+0.291
Neg logit contributions
 around-0.241
 air-0.204
 down-0.201
et-0.190
cy-0.189
Token.
Token ID13
Feature activation-5.59e-01

Pos logit contributions
ves+0.063
vern+0.063
ades+0.059
 backup+0.057
 mercy+0.057
Neg logit contributions
 around-0.042
 down-0.037
 air-0.036
cy-0.035
et-0.034
Token "
Token ID366
Feature activation+3.36e+00

Pos logit contributions
 around+0.027
cy+0.024
 air+0.024
et+0.023
 down+0.023
Neg logit contributions
ves-0.034
vern-0.033
ades-0.031
 mercy-0.030
 backup-0.030
TokenLet
Token ID5756
Feature activation-2.86e+00

Pos logit contributions
ves+0.177
vern+0.174
ades+0.157
 mercy+0.154
 backup+0.152
Neg logit contributions
 around-0.189
cy-0.172
 air-0.172
 down-0.169
et-0.166
Token's
Token ID338
Feature activation+2.01e+00

Pos logit contributions
 around+0.141
cy+0.131
 air+0.127
|+0.125
 down+0.125
Neg logit contributions
ves-0.169
vern-0.163
ades-0.149
keys-0.146
 mercy-0.146
Token do
Token ID466
Feature activation-5.16e+00

Pos logit contributions
ves+0.116
vern+0.114
ades+0.104
 mercy+0.103
 backup+0.102
Neg logit contributions
 around-0.101
cy-0.092
 air-0.091
 down-0.089
et-0.088
Token it
Token ID340
Feature activation-4.93e+00

Pos logit contributions
 around+0.262
 air+0.226
 down+0.225
et+0.207
 through+0.197
Neg logit contributions
vern-0.313
ves-0.291
 mercy-0.281
ades-0.279
 backup-0.275
Token again
Token ID757
Feature activation-5.89e-01

Pos logit contributions
 around+0.231
cy+0.205
 air+0.203
 down+0.201
et+0.195
Neg logit contributions
ves-0.308
vern-0.305
ades-0.279
 mercy-0.276
 backup-0.274
Token!"
Token ID2474
Feature activation-9.70e-01

Pos logit contributions
 around+0.030
cy+0.027
 air+0.027
 down+0.027
et+0.025
Neg logit contributions
ves-0.035
vern-0.035
ades-0.032
 mercy-0.031
 backup-0.031
Token
Token ID198
Feature activation+5.47e-01

Pos logit contributions
 around+0.044
cy+0.040
 air+0.039
et+0.039
rated+0.038
Neg logit contributions
ves-0.061
vern-0.060
ades-0.055
 mercy-0.054
keys-0.053
Token,
Token ID11
Feature activation+8.54e-01

Pos logit contributions
ves+0.043
vern+0.043
 mercy+0.040
 backup+0.040
ades+0.039
Neg logit contributions
cy-0.037
 air-0.036
 around-0.036
|-0.035
et-0.035
Token and
Token ID290
Feature activation-1.63e+00

Pos logit contributions
ves+0.054
vern+0.052
ades+0.049
 mercy+0.048
 forgiveness+0.048
Neg logit contributions
 around-0.037
cy-0.036
 air-0.033
et-0.032
|-0.032
Token he
Token ID339
Feature activation+9.41e+00

Pos logit contributions
 around+0.092
 down+0.082
 air+0.079
cy+0.074
 through+0.073
Neg logit contributions
vern-0.097
ves-0.095
ades-0.088
keys-0.082
 mercy-0.079
Token needed
Token ID2622
Feature activation-7.99e-01

Pos logit contributions
vern+0.602
ves+0.599
ades+0.552
 backup+0.537
 mercy+0.536
Neg logit contributions
 around-0.435
cy-0.381
 air-0.379
 down-0.373
et-0.360
Token to
Token ID284
Feature activation+2.89e+00

Pos logit contributions
 around+0.042
 air+0.038
 down+0.037
 through+0.035
 night+0.035
Neg logit contributions
ves-0.049
keys-0.048
ades-0.048
sters-0.045
vern-0.044
Token find
Token ID1064
Feature activation+1.99e+00

Pos logit contributions
ves+0.171
vern+0.168
ades+0.166
keys+0.152
 backup+0.144
Neg logit contributions
 around-0.143
 air-0.133
 down-0.127
et-0.120
|-0.119
Token a
Token ID257
Feature activation+4.75e+00

Pos logit contributions
ves+0.118
vern+0.115
ades+0.110
keys+0.107
oral+0.096
Neg logit contributions
 around-0.110
 down-0.100
 air-0.099
 through-0.089
et-0.088
Token safe
Token ID3338
Feature activation-2.68e+00

Pos logit contributions
ves+0.329
ades+0.300
vern+0.297
keys+0.290
His+0.271
Neg logit contributions
 around-0.204
 down-0.194
 air-0.188
 night-0.166
cy-0.163
Token place
Token ID1295
Feature activation+4.84e-01

Pos logit contributions
 around+0.117
 air+0.103
 down+0.101
cy+0.100
et+0.095
Neg logit contributions
ves-0.180
vern-0.177
ades-0.166
keys-0.161
 mercy-0.159
Token to
Token ID284
Feature activation+2.90e+00

Pos logit contributions
ves+0.027
vern+0.026
ades+0.024
keys+0.023
 mercy+0.023
Neg logit contributions
 around-0.027
 down-0.024
cy-0.024
 air-0.023
et-0.023
Token hide
Token ID7808
Feature activation+2.21e+00

Pos logit contributions
ves+0.177
vern+0.175
ades+0.170
keys+0.164
 backup+0.154
Neg logit contributions
 around-0.139
 air-0.125
 down-0.122
|-0.116
et-0.115
Token he
Token ID339
Feature activation+9.51e+00

Pos logit contributions
vern+0.095
ves+0.088
ades+0.082
 mercy+0.075
 forgiveness+0.074
Neg logit contributions
 around-0.173
 down-0.160
 air-0.158
cy-0.156
 through-0.149
Token made
Token ID925
Feature activation-1.56e+00

Pos logit contributions
vern+0.564
ves+0.557
ades+0.507
 mercy+0.504
 backup+0.498
Neg logit contributions
 around-0.482
cy-0.435
 air-0.431
 down-0.423
et-0.412
Token his
Token ID465
Feature activation+7.88e+00

Pos logit contributions
 around+0.083
 air+0.075
 down+0.075
 through+0.066
et+0.065
Neg logit contributions
vern-0.094
ves-0.090
keys-0.087
ades-0.086
 forgiveness-0.083
Token way
Token ID835
Feature activation-1.33e+00

Pos logit contributions
ves+0.462
vern+0.456
 mercy+0.414
ades+0.410
 backup+0.406
Neg logit contributions
 around-0.381
cy-0.352
et-0.340
 air-0.335
|-0.334
Token,
Token ID11
Feature activation+9.34e-01

Pos logit contributions
 around+0.032
cy+0.030
 air+0.029
et+0.028
|+0.027
Neg logit contributions
vern-0.107
ves-0.107
ades-0.099
 mercy-0.098
 backup-0.098
Token he
Token ID339
Feature activation+9.49e+00

Pos logit contributions
vern+0.041
ves+0.037
ades+0.035
keys+0.031
 backup+0.030
Neg logit contributions
 around-0.067
 down-0.063
 air-0.062
cy-0.059
 through-0.058
Token noticed
Token ID6810
Feature activation+3.43e+00

Pos logit contributions
vern+0.633
ves+0.603
 mercy+0.567
ades+0.563
 forgiveness+0.562
Neg logit contributions
 around-0.445
 air-0.377
 down-0.377
cy-0.373
et-0.365
Token something
Token ID1223
Feature activation+1.38e+01

Pos logit contributions
vern+0.208
ves+0.195
keys+0.184
ades+0.175
 backup+0.171
Neg logit contributions
 around-0.197
 air-0.174
 down-0.168
 through-0.156
et-0.154
Token strange
Token ID6283
Feature activation+2.54e+00

Pos logit contributions
vern+0.775
ves+0.775
ades+0.699
 backup+0.693
 mercy+0.689
Neg logit contributions
 around-0.775
 down-0.666
 air-0.661
et-0.629
cy-0.629
Token.
Token ID13
Feature activation-3.22e-01

Pos logit contributions
ves+0.156
vern+0.150
ades+0.140
 mercy+0.138
 forgiveness+0.135
Neg logit contributions
 around-0.113
cy-0.111
|-0.106
 air-0.105
 down-0.100
Token He
Token ID679
Feature activation-1.17e+00

Pos logit contributions
 around+0.013
et+0.012
cy+0.012
rated+0.011
ening+0.011
Neg logit contributions
ves-0.021
vern-0.021
His-0.020
ades-0.020
 backup-0.020
Token "
Token ID366
Feature activation+3.58e+00

Pos logit contributions
 around+0.014
et+0.013
rated+0.013
cy+0.012
ening+0.012
Neg logit contributions
ves-0.019
vern-0.019
His-0.019
ades-0.018
 backup-0.018
TokenNo
Token ID2949
Feature activation+1.55e+00

Pos logit contributions
vern+0.209
ves+0.208
ades+0.188
 mercy+0.183
 backup+0.180
Neg logit contributions
 around-0.187
cy-0.172
 air-0.166
|-0.162
 down-0.162
Token!"
Token ID2474
Feature activation-7.24e-01

Pos logit contributions
vern+0.096
ves+0.096
ades+0.089
keys+0.085
 backup+0.084
Neg logit contributions
 around-0.072
 air-0.068
cy-0.065
 down-0.064
et-0.064
Token the
Token ID262
Feature activation-4.02e+00

Pos logit contributions
 around+0.038
 air+0.035
 down+0.034
cy+0.032
et+0.030
Neg logit contributions
vern-0.046
ves-0.042
ades-0.040
 backup-0.039
 mercy-0.038
Token little
Token ID1310
Feature activation+2.54e+00

Pos logit contributions
 around+0.138
 air+0.126
cy+0.119
 down+0.116
et+0.103
Neg logit contributions
ves-0.307
vern-0.307
keys-0.278
ades-0.276
 mercy-0.275
Token boy
Token ID2933
Feature activation-6.59e+00

Pos logit contributions
ves+0.135
vern+0.131
 mercy+0.127
ades+0.127
 forgiveness+0.127
Neg logit contributions
 around-0.127
|-0.116
et-0.113
amp-0.112
rated-0.110
Token yelled
Token ID22760
Feature activation+7.72e-01

Pos logit contributions
 around+0.363
cy+0.321
 air+0.319
 down+0.319
et+0.313
Neg logit contributions
vern-0.368
ves-0.358
ades-0.333
 backup-0.325
 mercy-0.318
Token.
Token ID13
Feature activation-3.05e-01

Pos logit contributions
ves+0.045
vern+0.044
 mercy+0.041
 forgiveness+0.040
 backup+0.040
Neg logit contributions
 around-0.036
cy-0.036
 air-0.034
|-0.034
et-0.034
Token His
Token ID2399
Feature activation+7.71e+00

Pos logit contributions
 around+0.016
cy+0.015
 air+0.014
et+0.014
 down+0.014
Neg logit contributions
ves-0.017
vern-0.017
ades-0.016
 mercy-0.015
 backup-0.015
Token parents
Token ID3397
Feature activation+9.89e+00

Pos logit contributions
ves+0.333
vern+0.325
keys+0.290
ades+0.278
 mercy+0.267
Neg logit contributions
 around-0.529
 air-0.508
 down-0.488
cy-0.468
 night-0.459
Token told
Token ID1297
Feature activation+5.48e+00

Pos logit contributions
ves+0.544
vern+0.516
 mercy+0.479
ades+0.477
 forgiveness+0.474
Neg logit contributions
 around-0.500
cy-0.480
 air-0.475
|-0.466
et-0.453
TokenOnce
Token ID7454
Feature activation+2.90e+00

Pos logit contributions
ves+0.045
ades+0.039
His+0.034
vern+0.034
lor+0.032
Neg logit contributions
rated-0.088
et-0.086
ening-0.084
ishy-0.083
 around-0.075
Token upon
Token ID2402
Feature activation+3.53e+00

Pos logit contributions
ves+0.139
vern+0.137
ades+0.123
 backup+0.116
 mercy+0.114
Neg logit contributions
 around-0.167
 air-0.164
et-0.160
cy-0.156
rated-0.154
Token a
Token ID257
Feature activation+4.66e+00

Pos logit contributions
ves+0.193
vern+0.192
ades+0.177
keys+0.172
 backup+0.172
Neg logit contributions
 around-0.194
 air-0.174
 down-0.171
|-0.168
cy-0.168
Token time
Token ID640
Feature activation-8.25e+00

Pos logit contributions
vern+0.342
ves+0.341
ades+0.311
 backup+0.306
 mercy+0.302
Neg logit contributions
 around-0.160
 down-0.143
 air-0.141
cy-0.132
ening-0.128
Token,
Token ID11
Feature activation+7.85e-01

Pos logit contributions
 around+0.373
cy+0.331
 air+0.324
 down+0.323
et+0.308
Neg logit contributions
ves-0.529
vern-0.522
ades-0.481
 mercy-0.477
 backup-0.470
Token there
Token ID612
Feature activation-1.00e+00

Pos logit contributions
ves+0.030
vern+0.025
His+0.025
 else+0.024
ades+0.023
Neg logit contributions
 air-0.052
et-0.051
rated-0.049
ening-0.049
amp-0.048
Token was
Token ID373
Feature activation+1.75e+00

Pos logit contributions
 around+0.060
rated+0.058
 air+0.058
et+0.058
 down+0.056
Neg logit contributions
ves-0.047
vern-0.040
ades-0.038
ggy-0.037
His-0.036
Token a
Token ID257
Feature activation+4.68e+00

Pos logit contributions
ves+0.076
vern+0.075
ades+0.066
 mercy+0.064
 backup+0.064
Neg logit contributions
 around-0.114
cy-0.106
 air-0.104
 down-0.104
et-0.103
Token pretty
Token ID2495
Feature activation-2.36e+00

Pos logit contributions
ves+0.229
vern+0.225
ades+0.202
 mercy+0.198
 backup+0.195
Neg logit contributions
 around-0.281
cy-0.258
 air-0.257
 down-0.253
et-0.248
Token princess
Token ID21752
Feature activation+2.63e+00

Pos logit contributions
 around+0.147
|+0.136
rated+0.135
cy+0.133
 air+0.132
Neg logit contributions
ves-0.103
vern-0.098
ades-0.090
 wife-0.090
 forgiveness-0.086
Token.
Token ID13
Feature activation-4.37e-01

Pos logit contributions
vern+0.160
ves+0.156
ades+0.145
 backup+0.145
 mercy+0.144
Neg logit contributions
 around-0.134
cy-0.117
 down-0.114
et-0.113
 air-0.113
Token day
Token ID1110
Feature activation-1.18e+01

Pos logit contributions
 around+0.049
et+0.045
 down+0.044
cy+0.044
 air+0.042
Neg logit contributions
ves-0.096
vern-0.090
keys-0.087
 forgiveness-0.086
 mercy-0.085
Token,
Token ID11
Feature activation+6.92e-01

Pos logit contributions
 around+0.463
 down+0.402
 air+0.388
cy+0.369
 through+0.341
Neg logit contributions
vern-0.871
ves-0.835
ades-0.793
 mercy-0.780
keys-0.765
Token a
Token ID257
Feature activation+4.57e+00

Pos logit contributions
vern+0.042
ves+0.040
ades+0.036
 mercy+0.035
 backup+0.034
Neg logit contributions
 around-0.037
 down-0.034
 air-0.034
cy-0.032
 through-0.031
Token loud
Token ID7812
Feature activation-2.67e+00

Pos logit contributions
ves+0.257
vern+0.253
ades+0.224
 mercy+0.218
keys+0.211
Neg logit contributions
 around-0.245
 air-0.229
cy-0.222
 down-0.219
 wind-0.199
Token noise
Token ID7838
Feature activation+6.40e-02

Pos logit contributions
cy+0.165
 around+0.161
|+0.153
ained+0.151
amp+0.150
Neg logit contributions
ves-0.122
keys-0.101
vern-0.101
 mercy-0.100
ggy-0.099
Token came
Token ID1625
Feature activation+8.82e-01

Pos logit contributions
ves+0.004
vern+0.004
ades+0.003
 mercy+0.003
 backup+0.003
Neg logit contributions
 around-0.003
cy-0.003
 air-0.003
 down-0.003
et-0.003
Token from
Token ID422
Feature activation+6.10e+00

Pos logit contributions
vern+0.046
ves+0.046
ades+0.042
 mercy+0.041
 backup+0.040
Neg logit contributions
cy-0.043
 around-0.043
et-0.043
 air-0.041
|-0.041
Token the
Token ID262
Feature activation-4.24e+00

Pos logit contributions
 mercy+0.284
 backup+0.276
ves+0.272
vern+0.263
 forgiveness+0.262
Neg logit contributions
cy-0.299
rated-0.293
amp-0.290
et-0.288
|-0.285
Token village
Token ID7404
Feature activation-5.24e-01

Pos logit contributions
 around+0.204
cy+0.189
et+0.184
 down+0.179
|+0.178
Neg logit contributions
ves-0.245
vern-0.241
 backup-0.226
 mercy-0.225
ades-0.224
Token.
Token ID13
Feature activation-5.42e-01

Pos logit contributions
 around+0.025
cy+0.024
 air+0.023
et+0.022
|+0.022
Neg logit contributions
ves-0.031
vern-0.030
ades-0.028
keys-0.027
 mercy-0.027
Token It
Token ID632
Feature activation-9.56e+00

Pos logit contributions
 around+0.021
et+0.021
cy+0.021
rated+0.020
ening+0.019
Neg logit contributions
ves-0.036
vern-0.034
ades-0.033
His-0.033
keys-0.032
Token,
Token ID11
Feature activation+9.04e-01

Pos logit contributions
 around+0.347
cy+0.303
 down+0.299
 air+0.288
|+0.279
Neg logit contributions
ves-0.548
vern-0.538
 mercy-0.503
ades-0.501
 backup-0.493
Token there
Token ID612
Feature activation-8.94e-01

Pos logit contributions
ves+0.038
vern+0.035
His+0.032
ades+0.032
 else+0.031
Neg logit contributions
 air-0.054
et-0.054
 around-0.053
ening-0.051
rated-0.051
Token was
Token ID373
Feature activation+1.87e+00

Pos logit contributions
 around+0.053
 air+0.050
rated+0.050
et+0.050
 down+0.049
Neg logit contributions
ves-0.043
vern-0.037
ades-0.035
ggy-0.034
His-0.033
Token a
Token ID257
Feature activation+4.80e+00

Pos logit contributions
ves+0.075
vern+0.074
ades+0.064
 mercy+0.062
 backup+0.062
Neg logit contributions
 around-0.126
cy-0.117
 air-0.116
et-0.115
 down-0.115
Token big
Token ID1263
Feature activation+1.02e+00

Pos logit contributions
ves+0.224
vern+0.220
ades+0.196
 mercy+0.191
 backup+0.191
Neg logit contributions
 around-0.298
cy-0.272
 air-0.272
 down-0.268
et-0.265
Token bear
Token ID6842
Feature activation-8.00e-01

Pos logit contributions
 wife+0.040
ves+0.037
 crew+0.036
 backup+0.035
 forgiveness+0.035
Neg logit contributions
rated-0.064
 around-0.061
|-0.061
ained-0.060
idget-0.058
Token who
Token ID508
Feature activation+3.86e+00

Pos logit contributions
 around+0.039
cy+0.034
 down+0.033
 air+0.032
et+0.032
Neg logit contributions
vern-0.051
ves-0.050
ades-0.046
 mercy-0.045
 backup-0.045
Token loved
Token ID6151
Feature activation-2.80e+00

Pos logit contributions
ves+0.205
vern+0.188
His+0.183
ggy+0.176
ades+0.168
Neg logit contributions
 around-0.191
 air-0.187
amp-0.182
 down-0.182
ening-0.181
Token to
Token ID284
Feature activation+2.95e+00

Pos logit contributions
 around+0.168
 down+0.153
 air+0.152
cy+0.143
et+0.138
Neg logit contributions
ves-0.150
vern-0.147
ades-0.130
keys-0.127
 mercy-0.124
Token play
Token ID711
Feature activation-1.91e+00

Pos logit contributions
vern+0.184
ves+0.184
ades+0.169
keys+0.164
 mercy+0.164
Neg logit contributions
 around-0.140
 air-0.125
 down-0.123
cy-0.120
et-0.119
Token in
Token ID287
Feature activation-6.64e+00

Pos logit contributions
 around+0.075
 down+0.061
 air+0.058
cy+0.054
et+0.054
Neg logit contributions
vern-0.143
ves-0.140
 mercy-0.131
keys-0.130
 backup-0.129
Token whenever
Token ID8797
Feature activation+1.92e+00

Pos logit contributions
 around+0.044
 down+0.038
 air+0.037
cy+0.037
et+0.036
Neg logit contributions
vern-0.077
ves-0.076
ades-0.070
 mercy-0.070
 backup-0.069
Token he
Token ID339
Feature activation+9.30e+00

Pos logit contributions
vern+0.093
ves+0.082
ades+0.079
keys+0.075
 mercy+0.073
Neg logit contributions
 around-0.128
 down-0.119
 air-0.112
cy-0.111
 night-0.110
Token played
Token ID2826
Feature activation-3.07e+00

Pos logit contributions
ves+0.471
 else+0.412
vern+0.410
ades+0.408
His+0.392
Neg logit contributions
 around-0.462
rated-0.459
 air-0.443
ening-0.443
|-0.439
Token.
Token ID13
Feature activation-4.90e-01

Pos logit contributions
 around+0.168
cy+0.166
 air+0.159
rated+0.158
|+0.156
Neg logit contributions
ves-0.159
vern-0.155
ades-0.142
 backup-0.135
 forgiveness-0.135
Token
Token ID198
Feature activation+5.98e-01

Pos logit contributions
 around+0.028
rated+0.026
cy+0.026
ening+0.026
et+0.026
Neg logit contributions
ves-0.024
vern-0.022
His-0.022
ades-0.021
 forgiveness-0.020
Token
Token ID198
Feature activation+6.12e-01

Pos logit contributions
ves+0.035
vern+0.034
ades+0.031
 mercy+0.031
 backup+0.031
Neg logit contributions
 around-0.030
cy-0.027
 air-0.027
 down-0.027
et-0.026
TokenOne
Token ID3198
Feature activation+6.57e+00

Pos logit contributions
vern+0.026
ves+0.025
 mercy+0.023
 backup+0.022
 forgiveness+0.022
Neg logit contributions
 around-0.041
cy-0.038
et-0.037
 air-0.037
 down-0.037
Token day
Token ID1110
Feature activation-1.17e+01

Pos logit contributions
ves+0.501
vern+0.489
 forgiveness+0.454
ades+0.451
 wife+0.451
Neg logit contributions
 around-0.189
 air-0.163
et-0.162
ening-0.155
 down-0.155
Token,
Token ID11
Feature activation+7.61e-01

Pos logit contributions
 around+0.468
 down+0.415
cy+0.398
 air+0.396
et+0.351
Neg logit contributions
vern-0.850
ves-0.823
ades-0.769
 mercy-0.766
keys-0.757
Token Tim
Token ID5045
Feature activation-7.47e+00

Pos logit contributions
vern+0.068
ves+0.065
ades+0.061
 mercy+0.060
keys+0.060
Neg logit contributions
 around-0.020
 down-0.017
cy-0.016
 air-0.015
et-0.012
Tokenmy
Token ID1820
Feature activation-9.01e+00

Pos logit contributions
 around+0.276
ening+0.246
 air+0.229
|+0.222
amp+0.218
Neg logit contributions
ves-0.450
vern-0.439
His-0.428
 wife-0.428
 forgiveness-0.420
Token adventure
Token ID8855
Feature activation+1.22e+00

Pos logit contributions
ves+0.043
vern+0.042
ades+0.038
 backup+0.038
 mercy+0.038
Neg logit contributions
 around-0.055
cy-0.053
rated-0.050
 air-0.050
|-0.050
Token.
Token ID13
Feature activation-4.38e-01

Pos logit contributions
ves+0.071
vern+0.068
ades+0.063
 mercy+0.062
 backup+0.061
Neg logit contributions
 around-0.058
cy-0.057
 air-0.055
et-0.053
|-0.052
Token It
Token ID632
Feature activation-9.44e+00

Pos logit contributions
cy+0.018
 around+0.017
et+0.017
rated+0.016
ening+0.016
Neg logit contributions
ves-0.027
His-0.026
 backup-0.025
 mercy-0.024
 wife-0.024
Token went
Token ID1816
Feature activation-3.06e+00

Pos logit contributions
 around+0.456
cy+0.411
 air+0.407
 down+0.399
et+0.390
Neg logit contributions
ves-0.574
vern-0.566
ades-0.519
 mercy-0.510
 backup-0.505
Token up
Token ID510
Feature activation-7.14e+00

Pos logit contributions
cy+0.157
et+0.143
 around+0.143
 air+0.142
rated+0.141
Neg logit contributions
ves-0.165
vern-0.158
 backup-0.151
ades-0.149
 mercy-0.142
Token high
Token ID1029
Feature activation-9.89e+00

Pos logit contributions
 around+0.348
cy+0.346
et+0.340
 air+0.329
rated+0.328
Neg logit contributions
ves-0.388
vern-0.373
ades-0.349
 backup-0.341
 mercy-0.333
Token on
Token ID319
Feature activation-7.95e+00

Pos logit contributions
|+0.452
cy+0.439
rated+0.417
idget+0.416
et+0.412
Neg logit contributions
ves-0.540
ades-0.495
vern-0.484
keys-0.459
 mercy-0.452
Token the
Token ID262
Feature activation-4.10e+00

Pos logit contributions
 around+0.361
cy+0.322
 air+0.319
 down+0.313
et+0.305
Neg logit contributions
ves-0.510
vern-0.504
ades-0.464
 mercy-0.456
 backup-0.452
Token waves
Token ID9813
Feature activation+1.64e+00

Pos logit contributions
 around+0.233
cy+0.229
|+0.215
 down+0.212
et+0.211
Neg logit contributions
ves-0.205
vern-0.198
ades-0.182
 backup-0.174
 mercy-0.174
Token.
Token ID13
Feature activation-4.09e-01

Pos logit contributions
ves+0.094
vern+0.088
ades+0.083
 backup+0.081
keys+0.080
Neg logit contributions
cy-0.076
 around-0.074
|-0.073
rated-0.071
 air-0.070
Token The
Token ID383
Feature activation-8.20e+00

Pos logit contributions
cy+0.018
et+0.017
rated+0.016
 around+0.016
ening+0.015
Neg logit contributions
ves-0.025
His-0.023
 backup-0.022
 wife-0.022
ades-0.022
Token out
Token ID503
Feature activation-5.22e-01

Pos logit contributions
ves+0.050
vern+0.048
 backup+0.045
ades+0.045
 mercy+0.044
Neg logit contributions
 around-0.044
cy-0.041
rated-0.040
 air-0.040
|-0.039
Token a
Token ID257
Feature activation+4.59e+00

Pos logit contributions
 around+0.027
 down+0.024
 air+0.024
cy+0.022
 through+0.022
Neg logit contributions
vern-0.032
ves-0.032
keys-0.029
ades-0.028
 mercy-0.028
Token small
Token ID1402
Feature activation+2.39e+00

Pos logit contributions
ves+0.254
vern+0.251
 mercy+0.229
keys+0.225
ades+0.223
Neg logit contributions
 around-0.248
 air-0.230
 down-0.229
cy-0.212
 through-0.198
Token box
Token ID3091
Feature activation-4.44e-01

Pos logit contributions
ves+0.129
vern+0.126
ades+0.114
keys+0.111
 mercy+0.110
Neg logit contributions
 around-0.135
 air-0.125
cy-0.123
 down-0.122
et-0.117
Token.
Token ID13
Feature activation-5.47e-01

Pos logit contributions
 around+0.021
 down+0.018
 air+0.016
cy+0.016
et+0.016
Neg logit contributions
vern-0.030
ves-0.030
ades-0.027
 forgiveness-0.027
 mercy-0.027
Token It
Token ID632
Feature activation-9.56e+00

Pos logit contributions
 around+0.021
cy+0.018
 air+0.018
et+0.017
 down+0.017
Neg logit contributions
ves-0.039
vern-0.038
ades-0.036
 backup-0.035
 mercy-0.035
Token had
Token ID550
Feature activation-4.22e+00

Pos logit contributions
 around+0.401
cy+0.341
 down+0.331
 air+0.322
et+0.318
Neg logit contributions
vern-0.710
ves-0.651
 backup-0.627
ades-0.624
 mercy-0.614
Token a
Token ID257
Feature activation+4.57e+00

Pos logit contributions
 air+0.219
 around+0.219
 down+0.190
et+0.187
 through+0.180
Neg logit contributions
vern-0.252
ves-0.241
keys-0.228
ades-0.223
 forgiveness-0.216
Token colorful
Token ID20239
Feature activation-6.77e-01

Pos logit contributions
ves+0.264
vern+0.262
keys+0.236
ades+0.236
 mercy+0.235
Neg logit contributions
 around-0.236
 air-0.222
 down-0.213
cy-0.198
et-0.189
Token sticker
Token ID27735
Feature activation+7.32e+00

Pos logit contributions
 around+0.037
 air+0.036
 down+0.034
et+0.032
cy+0.032
Neg logit contributions
vern-0.038
ves-0.037
keys-0.034
 mercy-0.033
ades-0.033
Token on
Token ID319
Feature activation-8.11e+00

Pos logit contributions
vern+0.471
ves+0.466
ades+0.429
 mercy+0.426
 backup+0.420
Neg logit contributions
 around-0.338
 air-0.293
 down-0.289
cy-0.288
et-0.281
Token the
Token ID262
Feature activation-4.10e+00

Pos logit contributions
 around+0.302
 down+0.271
 air+0.271
et+0.255
cy+0.249
Neg logit contributions
vern-0.248
ves-0.241
ades-0.228
keys-0.222
 mercy-0.212
Token x
Token ID2124
Feature activation-3.10e+00

Pos logit contributions
 around+0.245
 air+0.226
cy+0.223
 down+0.221
et+0.216
Neg logit contributions
ves-0.204
vern-0.200
ades-0.182
keys-0.173
 mercy-0.173
Token-
Token ID12
Feature activation+5.38e-01

Pos logit contributions
 around+0.168
et+0.153
 down+0.146
 air+0.144
cy+0.138
Neg logit contributions
vern-0.172
ves-0.163
ades-0.162
keys-0.152
 backup-0.149
Tokenray
Token ID2433
Feature activation+3.45e+00

Pos logit contributions
ves+0.026
vern+0.026
ades+0.024
 mercy+0.023
 backup+0.022
Neg logit contributions
 around-0.033
cy-0.030
 air-0.029
 down-0.029
et-0.029
Token.
Token ID13
Feature activation-3.98e-01

Pos logit contributions
ves+0.201
vern+0.197
ades+0.180
 mercy+0.178
 backup+0.176
Neg logit contributions
 around-0.173
cy-0.158
 air-0.155
 down-0.152
et-0.149
Token The
Token ID383
Feature activation-8.17e+00

Pos logit contributions
 around+0.016
cy+0.014
et+0.014
rated+0.013
 air+0.013
Neg logit contributions
ves-0.027
vern-0.027
 backup-0.025
ades-0.025
 mercy-0.024
Token doctor
Token ID6253
Feature activation+9.17e+00

Pos logit contributions
 around+0.572
 air+0.558
cy+0.526
 down+0.525
et+0.513
Neg logit contributions
ves-0.324
vern-0.320
ades-0.299
keys-0.259
 backup-0.237
Token was
Token ID373
Feature activation+1.82e+00

Pos logit contributions
vern+0.535
ves+0.513
ades+0.479
 backup+0.468
 mercy+0.457
Neg logit contributions
 around-0.494
cy-0.441
 air-0.428
et-0.426
 down-0.420
Token very
Token ID845
Feature activation-6.23e+00

Pos logit contributions
ves+0.123
vern+0.119
ades+0.114
keys+0.110
 backup+0.108
Neg logit contributions
 around-0.082
 down-0.068
 air-0.068
et-0.065
cy-0.062
Token nice
Token ID3621
Feature activation+1.62e+00

Pos logit contributions
 around+0.328
 down+0.287
 air+0.271
 alone+0.267
cy+0.257
Neg logit contributions
ves-0.384
vern-0.348
ades-0.345
keys-0.320
lor-0.318
Token and
Token ID290
Feature activation-1.62e+00

Pos logit contributions
ves+0.110
vern+0.109
ades+0.101
 mercy+0.099
 backup+0.098
Neg logit contributions
 around-0.068
cy-0.059
 air-0.059
 down-0.058
et-0.056
TokenWhat
Token ID2061
Feature activation+1.85e+00

Pos logit contributions
ves+0.147
vern+0.144
ades+0.127
 mercy+0.124
 backup+0.122
Neg logit contributions
 around-0.223
 air-0.206
cy-0.205
 down-0.202
et-0.200
Token happened
Token ID3022
Feature activation+2.25e+00

Pos logit contributions
ves+0.121
vern+0.119
ades+0.111
 backup+0.109
 mercy+0.108
Neg logit contributions
 around-0.081
cy-0.071
 air-0.071
 down-0.069
|-0.065
Token?"
Token ID1701
Feature activation-1.05e+00

Pos logit contributions
vern+0.117
ves+0.116
 mercy+0.107
ades+0.106
 backup+0.106
Neg logit contributions
 around-0.117
cy-0.113
 air-0.111
et-0.110
|-0.109
Token her
Token ID607
Feature activation+1.40e+00

Pos logit contributions
 around+0.060
 down+0.054
 air+0.053
cy+0.052
|+0.048
Neg logit contributions
vern-0.058
ves-0.057
ades-0.053
 mercy-0.051
keys-0.050
Token mom
Token ID1995
Feature activation+3.65e+00

Pos logit contributions
ves+0.058
vern+0.056
ades+0.050
keys+0.048
 backup+0.047
Neg logit contributions
 around-0.098
cy-0.091
 down-0.090
 air-0.090
et-0.086
Tokenmy
Token ID1820
Feature activation-9.04e+00

Pos logit contributions
ves+0.293
vern+0.291
 mercy+0.275
 forgiveness+0.273
ades+0.272
Neg logit contributions
 around-0.090
 air-0.079
cy-0.077
|-0.073
et-0.069
Token asked
Token ID1965
Feature activation+1.11e+00

Pos logit contributions
 around+0.460
 down+0.409
 air+0.394
cy+0.392
et+0.385
Neg logit contributions
vern-0.551
ves-0.540
ades-0.505
 backup-0.492
 mercy-0.479
Token.
Token ID13
Feature activation-4.90e-01

Pos logit contributions
ves+0.063
vern+0.062
 forgiveness+0.057
 mercy+0.057
ades+0.055
Neg logit contributions
 around-0.054
 air-0.052
cy-0.051
et-0.050
|-0.049
Token Lily
Token ID20037
Feature activation-5.43e+00

Pos logit contributions
 around+0.026
cy+0.024
 air+0.024
et+0.023
 down+0.023
Neg logit contributions
ves-0.027
vern-0.027
ades-0.024
 mercy-0.024
 backup-0.024
Token told
Token ID1297
Feature activation+5.30e+00

Pos logit contributions
 around+0.278
cy+0.246
 down+0.245
 air+0.245
et+0.237
Neg logit contributions
vern-0.322
ves-0.321
ades-0.293
 backup-0.288
 mercy-0.286
Token her
Token ID607
Feature activation+1.40e+00

Pos logit contributions
ves+0.315
vern+0.311
ades+0.285
 mercy+0.277
keys+0.276
Neg logit contributions
 around-0.270
 air-0.241
cy-0.241
 down-0.238
et-0.231
Token the
Token ID262
Feature activation-4.04e+00

Pos logit contributions
ves+0.279
vern+0.272
ades+0.250
 mercy+0.247
 backup+0.244
Neg logit contributions
 around-0.234
cy-0.218
 air-0.208
 down-0.206
|-0.203
Token jungle
Token ID20712
Feature activation-1.10e+00

Pos logit contributions
 around+0.222
cy+0.219
|+0.214
et+0.211
 down+0.206
Neg logit contributions
ves-0.195
vern-0.179
keys-0.175
ades-0.172
 wife-0.169
Token.
Token ID13
Feature activation-3.43e-01

Pos logit contributions
 around+0.050
cy+0.045
 air+0.044
 down+0.044
et+0.043
Neg logit contributions
ves-0.070
vern-0.069
ades-0.064
 mercy-0.063
 backup-0.062
Token But
Token ID887
Feature activation-7.00e+00

Pos logit contributions
 around+0.018
rated+0.018
et+0.017
ening+0.017
cy+0.017
Neg logit contributions
ves-0.018
vern-0.017
ades-0.016
His-0.016
 backup-0.016
Token one
Token ID530
Feature activation+7.51e+00

Pos logit contributions
 around+0.385
cy+0.349
 air+0.346
 down+0.342
et+0.336
Neg logit contributions
ves-0.381
vern-0.381
ades-0.345
 mercy-0.335
 backup-0.333
Token day
Token ID1110
Feature activation-1.15e+01

Pos logit contributions
ves+0.597
vern+0.573
 forgiveness+0.544
keys+0.541
 mercy+0.540
Neg logit contributions
 around-0.197
 air-0.172
 down-0.166
cy-0.157
|-0.157
Token,
Token ID11
Feature activation+9.18e-01

Pos logit contributions
 around+0.447
 down+0.388
 air+0.372
cy+0.339
 through+0.327
Neg logit contributions
vern-0.883
ves-0.824
ades-0.795
 mercy-0.771
 backup-0.757
Token the
Token ID262
Feature activation-4.03e+00

Pos logit contributions
vern+0.067
ves+0.064
ades+0.060
 mercy+0.057
 backup+0.056
Neg logit contributions
 around-0.039
 down-0.034
 air-0.034
cy-0.032
et-0.029
Token music
Token ID2647
Feature activation+1.58e+00

Pos logit contributions
 around+0.218
cy+0.211
|+0.204
 down+0.196
amp+0.196
Neg logit contributions
ves-0.211
vern-0.196
keys-0.193
ades-0.186
 wife-0.184
Token was
Token ID373
Feature activation+1.87e+00

Pos logit contributions
vern+0.099
ves+0.098
ades+0.090
 mercy+0.089
 backup+0.089
Neg logit contributions
 around-0.074
 air-0.065
cy-0.065
 down-0.064
et-0.062
Token different
Token ID1180
Feature activation+1.52e+00

Pos logit contributions
ves+0.114
vern+0.113
ades+0.103
 mercy+0.102
 backup+0.101
Neg logit contributions
 around-0.086
cy-0.081
 air-0.078
 down-0.076
|-0.075