TOP ACTIVATIONS
MAX = 3.961

bees chased her all around the garden . Jane was very
very loud . All of the other animals on the farm
, " It 's okay , Lily , it 's okay
, " It 's okay , Anna . Acc idents happen
spread them out all over the grass , so she could
" Don 't be scared , Amy . Everything will be
. So they ran around the house , trying to find
, " It 's okay , Lily . You 'll be
is okay to say sorry , but you also need to
, " It 's okay , Anna . It was an
they should forgive each other . Lily and Max hugged and
wanted to go back to the garden , but he was
're glad you 're okay , Anna . We love you
" Be careful , Mom . The oven is
, " It 's okay , my loves . Match ing
, " It 's okay , my loves . I am
You are being very stubborn , Anna and Ben . You
" It 's okay , sweet ies ," Mom said
her . " Don 't hurt the bug , Lily ,"
right into the middle of the road , and a car

MIN ACTIVATIONS
MIN = -4.227

joy as the yellow boat gl ided across the lake .
She smiled and gave Tim a hug . They were happy
mom my gave her a pops icle to taste . It
was a shiny rock that gl ittered in the sun .
and gave the sausage one final hug before he went home
and gave his jacket an extra tight hug .
him and gave him a special gift . From that day
So he hopped over to take a closer look .
window so he went to take a look . When he
the zip - line and z ipped around the room ,
it would give her a special power . One
. She put on her special swimming helmet so she wouldn
impressed with Mary and her special suit .
, so he went to take a look . He saw
. Mike always wore his special uniform every day . One
feeling very proud wearing her special suit . She will never
a zipper that she loved to play with . One day
her mum put on her special clothes and said to her
. He walked over to take a closer look . It
I will give you a magic pen that will make your

INTERVAL 1.914 - 3.961
CONTAINS 1.143%

snacks . One day , Lily 's mom asked her to
it . Tim my thought that maybe his
of your life ." Alice yelled even louder ,
and about to run away , but then she heard a
took the pig to the other side of the farm and

INTERVAL -0.133 - 1.914
CONTAINS 55.703%

to close their eyes and count to ten . When they
new toy . <|endoftext|> De ena was tired after a long
had . <|endoftext|> Once upon a time , there was a
But she knew that if she was ever curious
the closet , and even in the toy box . Finally

INTERVAL -2.180 - -0.133
CONTAINS 42.325%

, she had a great idea ! She pointed to the
un pack all of their things . One of the first
then stepped into the water . It felt cold and strange
," Lucy said , " I have a joke !"
Come on , let 's go ." He ran to the

INTERVAL -4.227 - -2.180
CONTAINS 0.829%

big , round sun . Every day it smiled down on
. So he decided to take her to the park and
The guard nodded and replied ,
. But I have a special offer for you . If
named Lily . She loved to pick flowers in the garden
Token bees
Token ID17002
Feature activation+1.43e+00

Pos logit contributions
 mess+4.458
 ruining+4.116
 wasting+4.046
 fighting+4.035
 wasteful+3.996
Neg logit contributions
iest-5.836
 oblig-5.291
br-5.279
 name-5.177
 farewell-5.079
Token chased
Token ID26172
Feature activation+2.11e+00

Pos logit contributions
 mess+3.174
 wasting+2.796
 wasteful+2.795
 ruining+2.743
 yourselves+2.675
Neg logit contributions
iest-2.041
 oblig-1.834
br-1.796
int-1.742
 armour-1.738
Token her
Token ID607
Feature activation+1.04e+00

Pos logit contributions
 mess+4.183
 wasting+3.721
 wasteful+3.616
 ruining+3.590
 fighting+3.383
Neg logit contributions
iest-3.573
 oblig-3.416
 farewell-3.268
shirt-3.197
int-3.126
Token all
Token ID477
Feature activation+2.09e+00

Pos logit contributions
 mess+2.062
 wasting+1.831
 wasteful+1.819
 ruining+1.781
 fighting+1.725
Neg logit contributions
iest-1.749
 armour-1.534
 oblig-1.527
 ti-1.525
anger-1.509
Token around
Token ID1088
Feature activation+1.51e+00

Pos logit contributions
 mess+4.823
 wasting+4.476
 wasteful+4.296
 ruining+4.275
 yourselves+4.122
Neg logit contributions
iest-3.053
br-2.492
 oblig-2.427
 farewell-2.373
shirt-2.335
Token the
Token ID262
Feature activation+3.96e+00

Pos logit contributions
 mess+2.953
 wasteful+2.584
 wasting+2.554
 ruining+2.457
 fighting+2.345
Neg logit contributions
iest-2.543
 oblig-2.366
 ti-2.235
br-2.231
 armour-2.182
Token garden
Token ID11376
Feature activation+1.95e+00

Pos logit contributions
 wasteful+7.354
 fighting+7.230
 wasting+7.160
 ruining+7.071
 mess+6.825
Neg logit contributions
iest-7.151
br-6.721
 name-6.528
 powers-6.337
 ti-6.295
Token.
Token ID13
Feature activation+1.36e+00

Pos logit contributions
 mess+4.317
 wasting+3.966
 wasteful+3.949
 ruining+3.822
 yourselves+3.727
Neg logit contributions
iest-2.709
 oblig-2.349
br-2.337
anger-2.321
 ti-2.316
Token Jane
Token ID12091
Feature activation+1.81e+00

Pos logit contributions
 mess+2.760
 wasting+2.393
 ruining+2.368
 wasteful+2.334
 fighting+2.262
Neg logit contributions
iest-2.144
 oblig-2.024
 ti-1.931
shirt-1.926
int-1.925
Token was
Token ID373
Feature activation+1.89e+00

Pos logit contributions
 mess+4.146
 wasting+3.765
 wasteful+3.741
 ruining+3.663
 yourselves+3.583
Neg logit contributions
iest-2.439
br-2.198
 oblig-2.185
 ti-2.116
 shone-2.114
Token very
Token ID845
Feature activation+1.92e+00

Pos logit contributions
 mess+3.368
 wasting+2.785
 wasteful+2.779
 ruining+2.662
 fighting+2.591
Neg logit contributions
iest-3.399
 oblig-3.261
br-3.200
 armour-3.141
 farewell-3.094
Token very
Token ID845
Feature activation+1.25e+00

Pos logit contributions
 mess+1.540
 wasting+1.289
 ruining+1.265
 wasteful+1.224
 yourselves+1.184
Neg logit contributions
iest-1.913
 armour-1.787
 oblig-1.780
br-1.776
 sail-1.748
Token loud
Token ID7812
Feature activation+4.12e-01

Pos logit contributions
 mess+2.187
 wasting+1.895
 ruining+1.866
 wasteful+1.776
 yourselves+1.775
Neg logit contributions
iest-2.303
br-2.138
 oblig-2.110
 sail-2.095
 medal-2.072
Token.
Token ID13
Feature activation+8.71e-01

Pos logit contributions
 mess+0.869
 wasting+0.770
 ruining+0.752
 wasteful+0.751
 fighting+0.731
Neg logit contributions
iest-0.627
 oblig-0.556
 armour-0.556
br-0.554
 ti-0.542
Token All
Token ID1439
Feature activation+7.69e-01

Pos logit contributions
 mess+1.936
 wasting+1.697
 ruining+1.674
 wasteful+1.663
 fighting+1.608
Neg logit contributions
iest-1.240
 oblig-1.143
br-1.138
 armour-1.121
anger-1.106
Token of
Token ID286
Feature activation+6.19e-01

Pos logit contributions
 mess+1.547
 wasting+1.343
 ruining+1.321
 wasteful+1.303
 fighting+1.271
Neg logit contributions
iest-1.304
 oblig-1.156
br-1.148
 armour-1.130
shirt-1.107
Token the
Token ID262
Feature activation+3.93e+00

Pos logit contributions
 mess+1.311
 wasting+1.137
 ruining+1.123
 wasteful+1.122
 fighting+1.089
Neg logit contributions
iest-0.959
 oblig-0.856
br-0.853
 armour-0.850
 ti-0.818
Token other
Token ID584
Feature activation+3.02e+00

Pos logit contributions
 yourselves+6.421
 mess+6.203
 wasteful+5.884
 wasting+5.866
 ruining+5.771
Neg logit contributions
iest-7.970
br-7.871
 powers-6.989
 oblig-6.957
 name-6.939
Token animals
Token ID4695
Feature activation+1.33e+00

Pos logit contributions
 mess+4.610
 wasteful+4.048
 ruining+4.036
 wasting+3.984
 yourselves+3.925
Neg logit contributions
iest-6.696
br-6.149
 powers-5.722
int-5.716
anger-5.710
Token on
Token ID319
Feature activation+1.12e+00

Pos logit contributions
 mess+2.862
 wasting+2.505
 wasteful+2.478
 ruining+2.471
 yourselves+2.424
Neg logit contributions
iest-2.013
 oblig-1.791
br-1.738
 sail-1.726
 armour-1.702
Token the
Token ID262
Feature activation+3.16e+00

Pos logit contributions
 mess+2.105
 wasting+1.802
 wasteful+1.793
 ruining+1.757
 fighting+1.686
Neg logit contributions
iest-1.978
 armour-1.837
br-1.819
 oblig-1.788
 medal-1.764
Token farm
Token ID5318
Feature activation+1.46e+00

Pos logit contributions
 mess+6.230
 wasting+6.004
 wasteful+5.904
 yourselves+5.808
 ruining+5.484
Neg logit contributions
iest-4.997
br-4.891
 armour-4.767
 sail-4.640
 oblig-4.636
Token,
Token ID11
Feature activation+1.76e-01

Pos logit contributions
iest+0.184
 oblig+0.168
 armour+0.167
br+0.164
shirt+0.162
Neg logit contributions
 mess-0.199
 wasting-0.172
 ruining-0.168
 wasteful-0.166
 fighting-0.166
Token "
Token ID366
Feature activation+2.10e+00

Pos logit contributions
 mess+0.370
 wasting+0.324
 ruining+0.319
 wasteful+0.315
 fighting+0.310
Neg logit contributions
iest-0.274
 oblig-0.249
 armour-0.244
br-0.243
 ti-0.239
TokenIt
Token ID1026
Feature activation+1.77e+00

Pos logit contributions
 mess+4.504
 ruining+3.937
 wasting+3.839
 fighting+3.780
 wasteful+3.710
Neg logit contributions
iest-3.323
br-3.084
shirt-2.957
 ti-2.936
tie-2.849
Token's
Token ID338
Feature activation+2.10e+00

Pos logit contributions
 mess+2.806
 wasting+2.404
 ruining+2.383
 wasteful+2.342
 yourselves+2.234
Neg logit contributions
iest-3.587
br-3.341
 powers-3.259
int-3.239
 oblig-3.229
Token okay
Token ID8788
Feature activation+1.61e+00

Pos logit contributions
 mess+3.493
 wasting+2.984
 ruining+2.926
 fighting+2.863
 wasteful+2.790
Neg logit contributions
iest-3.937
br-3.715
int-3.698
 name-3.680
 oblig-3.630
Token,
Token ID11
Feature activation+3.79e+00

Pos logit contributions
 mess+3.858
 wasting+3.512
 ruining+3.490
 wasteful+3.452
 fighting+3.310
Neg logit contributions
iest-2.012
br-1.734
 oblig-1.726
 ti-1.678
 powers-1.674
Token Lily
Token ID20037
Feature activation+2.23e+00

Pos logit contributions
 mess+6.436
 wasteful+6.295
 wasting+5.970
 ruining+5.761
 anth+5.456
Neg logit contributions
iest-6.912
 ti-6.770
 yes-6.738
 medal-6.610
br-6.519
Token,
Token ID11
Feature activation+2.19e+00

Pos logit contributions
 mess+5.609
 ruining+5.260
 wasting+5.240
 wasteful+5.149
 yourselves+4.931
Neg logit contributions
iest-2.477
br-2.091
 ti-2.015
 oblig-1.973
 name-1.968
Token it
Token ID340
Feature activation+1.54e+00

Pos logit contributions
 mess+3.703
 wasteful+3.141
 wasting+3.098
 ruining+3.029
 fighting+2.909
Neg logit contributions
iest-4.243
 ti-3.923
br-3.907
 yes-3.839
 medal-3.829
Token's
Token ID338
Feature activation+2.03e+00

Pos logit contributions
 mess+2.444
 wasting+2.116
 ruining+2.093
 wasteful+2.068
 yourselves+1.990
Neg logit contributions
iest-3.084
br-2.906
int-2.809
 oblig-2.776
 shone-2.769
Token okay
Token ID8788
Feature activation+1.17e+00

Pos logit contributions
 mess+3.273
 wasting+2.886
 ruining+2.830
 wasteful+2.749
 fighting+2.729
Neg logit contributions
iest-3.867
 name-3.617
br-3.597
 ti-3.580
 armour-3.573
Token,
Token ID11
Feature activation-4.30e-01

Pos logit contributions
 mess+0.769
 wasting+0.676
 ruining+0.667
 wasteful+0.657
 fighting+0.646
Neg logit contributions
iest-0.534
 oblig-0.480
br-0.471
 armour-0.466
 ti-0.462
Token "
Token ID366
Feature activation+1.64e+00

Pos logit contributions
iest+0.741
 oblig+0.663
 armour+0.661
br+0.643
shirt+0.639
Neg logit contributions
 mess-0.852
 wasting-0.749
 ruining-0.732
 fighting-0.724
 wasteful-0.717
TokenIt
Token ID1026
Feature activation+1.65e+00

Pos logit contributions
 mess+3.598
 ruining+3.193
 wasting+3.139
 fighting+3.062
 wasteful+3.029
Neg logit contributions
iest-2.515
br-2.231
 oblig-2.216
shirt-2.202
 ti-2.163
Token's
Token ID338
Feature activation+1.94e+00

Pos logit contributions
 mess+2.695
 wasting+2.327
 ruining+2.315
 wasteful+2.286
 yourselves+2.169
Neg logit contributions
iest-3.260
br-2.985
 shone-2.939
 name-2.931
 powers-2.930
Token okay
Token ID8788
Feature activation+1.55e+00

Pos logit contributions
 mess+3.207
 wasting+2.759
 ruining+2.695
 fighting+2.599
 wasteful+2.548
Neg logit contributions
iest-3.682
int-3.480
 name-3.464
br-3.414
 oblig-3.402
Token,
Token ID11
Feature activation+3.76e+00

Pos logit contributions
 mess+3.677
 wasting+3.341
 ruining+3.305
 wasteful+3.280
 fighting+3.160
Neg logit contributions
iest-2.004
 oblig-1.702
br-1.686
 ti-1.651
 powers-1.622
Token Anna
Token ID11735
Feature activation+1.81e+00

Pos logit contributions
 mess+6.479
 wasteful+6.457
 ruining+5.948
 wasting+5.885
 fighting+5.667
Neg logit contributions
iest-7.080
 yes-6.672
 ti-6.666
 medal-6.288
 name-6.241
Token.
Token ID13
Feature activation+6.48e-01

Pos logit contributions
 mess+4.432
 wasting+4.056
 ruining+4.047
 wasteful+3.963
 fighting+3.787
Neg logit contributions
iest-2.206
 ti-1.800
br-1.793
 oblig-1.787
 powers-1.717
Token Acc
Token ID6366
Feature activation+2.04e+00

Pos logit contributions
 mess+1.238
 wasting+1.056
 ruining+1.043
 wasteful+1.016
 fighting+1.008
Neg logit contributions
iest-1.141
 oblig-1.044
 armour-1.024
 ti-1.024
br-1.023
Tokenidents
Token ID3231
Feature activation+5.34e-01

Pos logit contributions
 mess+2.394
 wasting+2.161
 ruining+2.104
 wasteful+1.937
 fighting+1.741
Neg logit contributions
iest-4.781
int-4.707
anger-4.649
shirt-4.643
 name-4.623
Token happen
Token ID1645
Feature activation+1.47e+00

Pos logit contributions
 mess+1.134
 wasting+1.014
 ruining+0.992
 wasteful+0.985
 fighting+0.970
Neg logit contributions
iest-0.813
 oblig-0.711
br-0.710
 armour-0.686
 ti-0.686
Token spread
Token ID4104
Feature activation-9.11e-02

Pos logit contributions
 mess+1.834
 wasting+1.627
 ruining+1.598
 wasteful+1.585
 fighting+1.551
Neg logit contributions
iest-1.337
 oblig-1.248
 ti-1.224
 armour-1.222
br-1.218
Token them
Token ID606
Feature activation+7.51e-01

Pos logit contributions
iest+0.160
 oblig+0.146
 armour+0.144
br+0.143
 ti+0.141
Neg logit contributions
 mess-0.174
 wasting-0.150
 ruining-0.147
 wasteful-0.145
 fighting-0.144
Token out
Token ID503
Feature activation-2.91e-01

Pos logit contributions
 mess+1.549
 wasting+1.373
 wasteful+1.355
 ruining+1.336
 fighting+1.290
Neg logit contributions
iest-1.179
 armour-1.061
 oblig-1.061
br-1.051
 ti-1.035
Token all
Token ID477
Feature activation+8.58e-01

Pos logit contributions
iest+0.456
 oblig+0.416
 armour+0.407
br+0.403
shirt+0.399
Neg logit contributions
 mess-0.613
 wasting-0.536
 ruining-0.528
 fighting-0.518
 wasteful-0.515
Token over
Token ID625
Feature activation+7.33e-01

Pos logit contributions
 mess+1.684
 wasting+1.497
 wasteful+1.468
 ruining+1.467
 fighting+1.409
Neg logit contributions
iest-1.475
 oblig-1.297
br-1.273
 armour-1.271
shirt-1.266
Token the
Token ID262
Feature activation+3.70e+00

Pos logit contributions
 mess+1.484
 wasting+1.299
 wasteful+1.282
 ruining+1.275
 fighting+1.229
Neg logit contributions
iest-1.194
 oblig-1.087
 armour-1.074
 ti-1.052
br-1.042
Token grass
Token ID8701
Feature activation+1.16e+00

Pos logit contributions
 wasting+7.375
 wasteful+7.335
 mess+7.264
 ruining+7.240
 fighting+6.995
Neg logit contributions
 name-5.593
iest-5.406
br-5.227
 seas-5.156
 ti-5.141
Token,
Token ID11
Feature activation+2.84e+00

Pos logit contributions
 mess+2.496
 wasteful+2.201
 wasting+2.199
 ruining+2.162
 fighting+2.047
Neg logit contributions
iest-1.810
 armour-1.579
anger-1.570
 oblig-1.553
 ti-1.547
Token so
Token ID523
Feature activation+8.73e-01

Pos logit contributions
 mess+5.395
 wasteful+4.909
 yourselves+4.683
 wasting+4.566
 ruining+4.463
Neg logit contributions
iest-4.526
 ti-4.496
 armour-4.481
 shone-4.432
 sail-4.408
Token she
Token ID673
Feature activation+4.41e-01

Pos logit contributions
 mess+1.590
 wasting+1.350
 ruining+1.348
 wasteful+1.329
 fighting+1.295
Neg logit contributions
iest-1.634
 oblig-1.491
br-1.488
 armour-1.485
 ti-1.485
Token could
Token ID714
Feature activation+1.06e+00

Pos logit contributions
 mess+0.929
 wasting+0.818
 ruining+0.805
 wasteful+0.795
 fighting+0.784
Neg logit contributions
iest-0.678
 oblig-0.616
 armour-0.607
br-0.603
 ti-0.599
Token "
Token ID366
Feature activation+1.89e+00

Pos logit contributions
 mess+3.852
 wasting+3.468
 ruining+3.383
 wasteful+3.338
 fighting+3.193
Neg logit contributions
 oblig-2.298
iest-2.289
 ti-2.250
shirt-2.249
 name-2.239
TokenDon
Token ID3987
Feature activation+9.04e-01

Pos logit contributions
 mess+3.846
 ruining+3.351
 wasting+3.326
 fighting+3.229
 wasteful+3.197
Neg logit contributions
iest-3.191
shirt-3.013
br-2.916
 oblig-2.916
int-2.861
Token't
Token ID470
Feature activation+2.77e+00

Pos logit contributions
 mess+1.620
 wasting+1.383
 wasteful+1.349
 ruining+1.344
 fighting+1.306
Neg logit contributions
iest-1.721
 oblig-1.592
br-1.591
anger-1.532
 armour-1.497
Token be
Token ID307
Feature activation+2.34e+00

Pos logit contributions
 mess+4.098
 wasteful+3.831
 wasting+3.737
 ruining+3.432
 yourselves+3.181
Neg logit contributions
 sail-5.721
iest-5.586
 oblig-5.498
 name-5.308
 ti-5.289
Token scared
Token ID12008
Feature activation+2.81e+00

Pos logit contributions
 mess+3.413
 wasting+2.853
 ruining+2.754
 wasteful+2.689
 fighting+2.579
Neg logit contributions
iest-4.808
br-4.757
int-4.696
 oblig-4.542
 ti-4.539
Token,
Token ID11
Feature activation+3.68e+00

Pos logit contributions
 mess+7.005
 wasting+6.594
 wasteful+6.570
 ruining+6.366
 fighting+6.070
Neg logit contributions
iest-3.494
br-2.839
 oblig-2.710
 powers-2.621
 farewell-2.511
Token Amy
Token ID14235
Feature activation+2.19e+00

Pos logit contributions
 mess+6.057
 wasting+5.494
 wasteful+5.482
 ruining+5.379
 yourselves+5.136
Neg logit contributions
iest-7.504
 yes-7.304
br-6.946
 hi-6.800
 ti-6.794
Token.
Token ID13
Feature activation+8.85e-01

Pos logit contributions
 mess+5.042
 ruining+4.715
 wasting+4.648
 wasteful+4.530
 fighting+4.428
Neg logit contributions
iest-3.113
 ti-2.612
 oblig-2.594
br-2.517
 powers-2.459
Token Everything
Token ID11391
Feature activation+1.52e+00

Pos logit contributions
 mess+1.914
 wasting+1.653
 ruining+1.641
 wasteful+1.599
 fighting+1.572
Neg logit contributions
iest-1.325
 oblig-1.208
br-1.185
anger-1.178
int-1.173
Token will
Token ID481
Feature activation+1.23e+00

Pos logit contributions
 mess+3.144
 wasting+2.884
 ruining+2.820
 wasteful+2.816
 fighting+2.721
Neg logit contributions
iest-2.370
br-2.117
 powers-1.991
 shone-1.973
 oblig-1.958
Token be
Token ID307
Feature activation+2.10e+00

Pos logit contributions
 mess+2.606
 wasting+2.363
 wasteful+2.309
 ruining+2.287
 fighting+2.263
Neg logit contributions
iest-1.803
 oblig-1.635
br-1.610
 sail-1.594
 ti-1.532
Token.
Token ID13
Feature activation+2.73e-02

Pos logit contributions
 mess+2.827
 wasting+2.584
 wasteful+2.523
 ruining+2.517
 fighting+2.452
Neg logit contributions
iest-1.820
 armour-1.603
 ti-1.556
anger-1.526
br-1.513
Token So
Token ID1406
Feature activation+8.86e-01

Pos logit contributions
 mess+0.057
 wasting+0.050
 ruining+0.049
 wasteful+0.049
 fighting+0.048
Neg logit contributions
iest-0.043
 oblig-0.039
 armour-0.038
br-0.038
 ti-0.037
Token they
Token ID484
Feature activation+1.21e-01

Pos logit contributions
 mess+1.952
 wasting+1.721
 ruining+1.683
 wasteful+1.678
 fighting+1.623
Neg logit contributions
iest-1.326
 oblig-1.175
br-1.168
 armour-1.160
 sail-1.144
Token ran
Token ID4966
Feature activation+8.23e-01

Pos logit contributions
 mess+0.254
 wasting+0.223
 ruining+0.219
 wasteful+0.216
 fighting+0.214
Neg logit contributions
iest-0.188
 oblig-0.170
 armour-0.168
br-0.166
 ti-0.163
Token around
Token ID1088
Feature activation+3.81e-01

Pos logit contributions
 mess+1.744
 wasting+1.574
 wasteful+1.536
 ruining+1.516
 fighting+1.470
Neg logit contributions
iest-1.242
 armour-1.121
 oblig-1.117
br-1.108
anger-1.096
Token the
Token ID262
Feature activation+3.63e+00

Pos logit contributions
 mess+0.695
 wasting+0.599
 ruining+0.586
 wasteful+0.585
 fighting+0.564
Neg logit contributions
iest-0.691
 oblig-0.639
 armour-0.628
br-0.620
 ti-0.616
Token house
Token ID2156
Feature activation+1.35e+00

Pos logit contributions
 wasting+6.953
 wasteful+6.884
 ruining+6.858
 mess+6.752
 fighting+6.401
Neg logit contributions
 name-5.731
iest-5.418
 sail-5.416
 suit-5.409
anger-5.303
Token,
Token ID11
Feature activation+2.19e+00

Pos logit contributions
 mess+2.867
 wasting+2.582
 wasteful+2.577
 ruining+2.493
 yourselves+2.445
Neg logit contributions
iest-2.019
 oblig-1.803
 armour-1.764
 ti-1.754
anger-1.749
Token trying
Token ID2111
Feature activation+4.61e-01

Pos logit contributions
 mess+4.089
 wasteful+3.665
 wasting+3.517
 yourselves+3.481
 ruining+3.365
Neg logit contributions
iest-3.437
 sail-3.429
 armour-3.395
 ti-3.384
 shone-3.319
Token to
Token ID284
Feature activation+1.21e+00

Pos logit contributions
 mess+1.074
 wasting+0.962
 ruining+0.944
 wasteful+0.942
 fighting+0.921
Neg logit contributions
iest-0.598
 oblig-0.532
 armour-0.526
br-0.518
 ti-0.508
Token find
Token ID1064
Feature activation-1.07e-01

Pos logit contributions
 mess+2.395
 wasting+2.130
 wasteful+2.121
 ruining+2.067
 fighting+2.033
Neg logit contributions
iest-1.928
 oblig-1.854
 sail-1.808
 armour-1.765
 ti-1.727
Token,
Token ID11
Feature activation-5.38e-01

Pos logit contributions
 mess+0.149
 wasting+0.131
 ruining+0.129
 wasteful+0.127
 fighting+0.126
Neg logit contributions
iest-0.110
 oblig-0.099
 armour-0.098
br-0.097
 ti-0.095
Token "
Token ID366
Feature activation+1.50e+00

Pos logit contributions
iest+0.941
 oblig+0.840
 armour+0.837
shirt+0.810
int+0.810
Neg logit contributions
 mess-1.049
 wasting-0.925
 ruining-0.905
 fighting-0.899
 wasteful-0.886
TokenIt
Token ID1026
Feature activation+1.32e+00

Pos logit contributions
 mess+3.211
 ruining+2.830
 wasting+2.795
 fighting+2.683
 wasteful+2.670
Neg logit contributions
iest-2.369
shirt-2.113
br-2.109
 oblig-2.104
 ti-2.041
Token's
Token ID338
Feature activation+1.68e+00

Pos logit contributions
 mess+1.985
 wasting+1.674
 ruining+1.656
 wasteful+1.631
 yourselves+1.501
Neg logit contributions
iest-2.796
br-2.585
 oblig-2.540
 powers-2.536
int-2.514
Token okay
Token ID8788
Feature activation+1.13e+00

Pos logit contributions
 mess+2.717
 wasting+2.297
 ruining+2.254
 fighting+2.172
 wasteful+2.126
Neg logit contributions
iest-3.314
br-3.090
 armour-3.086
int-3.084
 oblig-3.076
Token,
Token ID11
Feature activation+3.62e+00

Pos logit contributions
 mess+2.604
 wasting+2.343
 ruining+2.314
 wasteful+2.285
 fighting+2.215
Neg logit contributions
iest-1.526
 oblig-1.326
br-1.314
 ti-1.281
 armour-1.276
Token Lily
Token ID20037
Feature activation+2.11e+00

Pos logit contributions
 mess+6.093
 wasteful+5.775
 wasting+5.625
 ruining+5.434
 fighting+4.948
Neg logit contributions
 medal-6.622
 yes-6.501
iest-6.463
 ti-6.253
br-6.052
Token.
Token ID13
Feature activation+4.52e-01

Pos logit contributions
 mess+5.299
 ruining+4.928
 wasting+4.922
 wasteful+4.794
 yourselves+4.601
Neg logit contributions
iest-2.371
br-1.948
 ti-1.906
anger-1.870
 oblig-1.864
Token You
Token ID921
Feature activation+8.93e-01

Pos logit contributions
 mess+0.838
 wasting+0.714
 ruining+0.702
 wasteful+0.686
 fighting+0.678
Neg logit contributions
iest-0.823
 oblig-0.755
 armour-0.742
br-0.741
 ti-0.737
Token'll
Token ID1183
Feature activation+1.44e+00

Pos logit contributions
 mess+1.969
 wasting+1.727
 ruining+1.719
 wasteful+1.677
 fighting+1.635
Neg logit contributions
iest-1.299
 oblig-1.183
br-1.143
 armour-1.130
 sail-1.123
Token be
Token ID307
Feature activation+1.93e+00

Pos logit contributions
 mess+2.926
 wasting+2.651
 wasteful+2.602
 ruining+2.559
 fighting+2.477
Neg logit contributions
iest-2.206
 oblig-2.127
 sail-2.062
br-2.008
 name-2.004
Token is
Token ID318
Feature activation+1.29e+00

Pos logit contributions
 mess+1.925
 wasting+1.698
 ruining+1.673
 wasteful+1.657
 fighting+1.574
Neg logit contributions
iest-1.785
br-1.620
 oblig-1.599
 armour-1.563
 powers-1.562
Token okay
Token ID8788
Feature activation+8.70e-01

Pos logit contributions
 mess+2.033
 wasting+1.706
 ruining+1.669
 wasteful+1.623
 fighting+1.582
Neg logit contributions
iest-2.543
 oblig-2.411
br-2.398
 armour-2.391
 ti-2.361
Token to
Token ID284
Feature activation+1.36e+00

Pos logit contributions
 mess+1.963
 wasting+1.753
 ruining+1.725
 wasteful+1.716
 fighting+1.655
Neg logit contributions
iest-1.230
 oblig-1.080
br-1.067
 armour-1.030
 ti-1.023
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 mess+2.801
 wasting+2.551
 ruining+2.463
 wasteful+2.448
 fighting+2.322
Neg logit contributions
iest-1.998
 oblig-1.916
 sail-1.861
br-1.788
 medal-1.782
Token sorry
Token ID7926
Feature activation+1.13e+00

Pos logit contributions
iest+2.197
int+2.026
 armour+2.023
shirt+2.018
 oblig+2.006
Neg logit contributions
 mess-1.531
 wasting-1.263
 ruining-1.257
 fighting-1.252
 wasteful-1.215
Token,
Token ID11
Feature activation+3.60e+00

Pos logit contributions
 mess+2.525
 wasting+2.321
 ruining+2.276
 wasteful+2.237
 fighting+2.168
Neg logit contributions
iest-1.556
 oblig-1.348
br-1.341
 armour-1.312
 ti-1.301
Token but
Token ID475
Feature activation+1.11e+00

Pos logit contributions
 mess+6.095
 wasting+5.634
 wasteful+5.516
 ruining+5.468
 fighting+4.922
Neg logit contributions
iest-6.716
 yes-6.431
br-6.188
 sail-6.159
 ti-6.046
Token you
Token ID345
Feature activation+1.90e+00

Pos logit contributions
 mess+1.744
 wasting+1.435
 ruining+1.416
 wasteful+1.399
 fighting+1.312
Neg logit contributions
iest-2.269
 oblig-2.094
 sail-2.053
br-2.050
 ti-2.042
Token also
Token ID635
Feature activation+6.23e-01

Pos logit contributions
 mess+4.068
 ruining+3.664
 wasting+3.620
 yourselves+3.518
 wasteful+3.517
Neg logit contributions
iest-2.662
 oblig-2.529
 name-2.463
 sail-2.436
int-2.386
Token need
Token ID761
Feature activation-4.38e-01

Pos logit contributions
 mess+1.227
 wasting+1.068
 ruining+1.061
 wasteful+1.027
 fighting+1.019
Neg logit contributions
iest-1.019
 oblig-0.945
br-0.909
 armour-0.905
 ti-0.894
Token to
Token ID284
Feature activation+7.44e-01

Pos logit contributions
iest+0.661
 oblig+0.584
 armour+0.581
int+0.574
br+0.573
Neg logit contributions
 mess-0.966
 wasting-0.852
 ruining-0.837
 wasteful-0.827
 fighting-0.825
Token,
Token ID11
Feature activation-4.57e-01

Pos logit contributions
iest+0.897
 armour+0.825
 oblig+0.805
shirt+0.792
int+0.785
Neg logit contributions
 mess-1.061
 wasting-0.931
 ruining-0.911
 fighting-0.909
 wasteful-0.893
Token "
Token ID366
Feature activation+1.89e+00

Pos logit contributions
iest+0.790
 armour+0.708
 oblig+0.700
shirt+0.687
int+0.682
Neg logit contributions
 mess-0.903
 wasting-0.795
 ruining-0.778
 fighting-0.770
 wasteful-0.759
TokenIt
Token ID1026
Feature activation+1.39e+00

Pos logit contributions
 mess+4.177
 ruining+3.651
 wasting+3.585
 fighting+3.495
 wasteful+3.475
Neg logit contributions
iest-2.915
br-2.677
 ti-2.594
 oblig-2.570
shirt-2.556
Token's
Token ID338
Feature activation+1.48e+00

Pos logit contributions
 mess+2.214
 wasting+1.915
 ruining+1.903
 wasteful+1.881
 yourselves+1.766
Neg logit contributions
iest-2.802
br-2.589
int-2.542
 name-2.526
 powers-2.526
Token okay
Token ID8788
Feature activation+1.25e+00

Pos logit contributions
 mess+2.310
 wasting+1.939
 ruining+1.891
 fighting+1.837
 wasteful+1.817
Neg logit contributions
iest-2.969
 oblig-2.795
int-2.786
br-2.781
 armour-2.778
Token,
Token ID11
Feature activation+3.59e+00

Pos logit contributions
 mess+2.885
 wasting+2.590
 ruining+2.560
 wasteful+2.551
 fighting+2.452
Neg logit contributions
iest-1.673
 oblig-1.464
br-1.444
 ti-1.405
 powers-1.387
Token Anna
Token ID11735
Feature activation+2.05e+00

Pos logit contributions
 mess+6.424
 wasteful+6.136
 ruining+5.689
 wasting+5.621
 fighting+5.332
Neg logit contributions
iest-6.671
 yes-6.530
 ti-6.336
 medal-6.276
br-6.086
Token.
Token ID13
Feature activation+2.81e-01

Pos logit contributions
 mess+5.172
 ruining+4.761
 wasting+4.747
 wasteful+4.702
 yourselves+4.445
Neg logit contributions
iest-2.373
br-1.913
 oblig-1.905
 ti-1.900
 name-1.841
Token It
Token ID632
Feature activation+1.81e+00

Pos logit contributions
 mess+0.507
 wasting+0.432
 ruining+0.425
 wasteful+0.416
 fighting+0.412
Neg logit contributions
iest-0.522
 oblig-0.479
 armour-0.472
br-0.471
 ti-0.466
Token was
Token ID373
Feature activation+1.28e+00

Pos logit contributions
 mess+3.378
 wasting+2.982
 ruining+2.974
 wasteful+2.938
 yourselves+2.900
Neg logit contributions
iest-3.134
br-2.916
 shone-2.824
int-2.769
 oblig-2.746
Token an
Token ID281
Feature activation+9.57e-01

Pos logit contributions
 mess+2.785
 wasting+2.459
 ruining+2.420
 fighting+2.389
 wasteful+2.380
Neg logit contributions
iest-1.741
 armour-1.624
 ti-1.609
br-1.600
 oblig-1.565
Token they
Token ID484
Feature activation+1.57e+00

Pos logit contributions
 mess+4.241
 wasteful+3.705
 wasting+3.654
 ruining+3.626
 yourselves+3.561
Neg logit contributions
iest-3.428
 shone-3.073
br-3.067
 sail-2.992
 powers-2.974
Token should
Token ID815
Feature activation+1.41e+00

Pos logit contributions
 mess+3.365
 wasting+2.962
 ruining+2.952
 yourselves+2.893
 wasteful+2.864
Neg logit contributions
iest-2.346
 sail-2.060
 oblig-2.052
tie-1.996
 armour-1.988
Token forgive
Token ID20927
Feature activation+1.40e+00

Pos logit contributions
 mess+2.784
 wasting+2.480
 ruining+2.433
 wasteful+2.427
 fighting+2.305
Neg logit contributions
iest-2.270
 oblig-2.132
 sail-2.109
 medal-2.019
 ti-2.017
Token each
Token ID1123
Feature activation+5.11e-01

Pos logit contributions
 mess+2.380
 wasting+2.024
 wasteful+1.955
 ruining+1.954
 fighting+1.850
Neg logit contributions
iest-2.706
 oblig-2.484
br-2.483
 armour-2.460
shirt-2.450
Token other
Token ID584
Feature activation+1.25e+00

Pos logit contributions
 mess+0.751
 wasting+0.624
 ruining+0.615
 wasteful+0.599
 fighting+0.586
Neg logit contributions
iest-1.130
 oblig-1.041
 armour-1.019
br-1.017
shirt-1.013
Token.
Token ID13
Feature activation+3.59e+00

Pos logit contributions
 mess+2.502
 ruining+2.199
 wasting+2.195
 wasteful+2.128
 fighting+2.072
Neg logit contributions
iest-2.026
 oblig-1.781
shirt-1.758
br-1.750
 armour-1.739
Token Lily
Token ID20037
Feature activation+1.45e+00

Pos logit contributions
 mess+9.011
 wasting+8.364
 ruining+8.296
 wasteful+7.765
 yourselves+7.588
Neg logit contributions
 His-4.891
 farewell-4.029
shirt-3.998
anger-3.943
 name-3.919
Token and
Token ID290
Feature activation+2.12e+00

Pos logit contributions
 mess+3.062
 ruining+2.806
 wasting+2.774
 wasteful+2.704
 yourselves+2.628
Neg logit contributions
iest-2.086
 oblig-1.949
int-1.892
 medal-1.866
 ti-1.857
Token Max
Token ID5436
Feature activation+8.05e-01

Pos logit contributions
 mess+3.702
 wasting+3.246
 wasteful+3.201
 ruining+3.173
 yourselves+2.976
Neg logit contributions
iest-3.740
 oblig-3.696
 armour-3.672
 sail-3.643
 medal-3.636
Token hugged
Token ID41130
Feature activation+1.69e+00

Pos logit contributions
 mess+1.583
 wasting+1.378
 ruining+1.367
 wasteful+1.329
 fighting+1.297
Neg logit contributions
iest-1.326
 oblig-1.242
 armour-1.190
 ti-1.186
 sail-1.182
Token and
Token ID290
Feature activation+1.26e+00

Pos logit contributions
 mess+3.094
 wasting+2.795
 ruining+2.727
 wasteful+2.640
 yourselves+2.501
Neg logit contributions
iest-2.937
 armour-2.755
 farewell-2.752
 oblig-2.750
shirt-2.731
Token wanted
Token ID2227
Feature activation+4.77e-01

Pos logit contributions
 mess+1.347
 wasting+1.177
 ruining+1.152
 wasteful+1.129
 fighting+1.112
Neg logit contributions
iest-1.323
 armour-1.231
 oblig-1.231
 ti-1.209
br-1.199
Token to
Token ID284
Feature activation+4.71e-01

Pos logit contributions
 mess+1.113
 wasting+0.991
 ruining+0.975
 wasteful+0.967
 fighting+0.951
Neg logit contributions
iest-0.627
 oblig-0.562
 armour-0.553
br-0.541
shirt-0.530
Token go
Token ID467
Feature activation+7.26e-02

Pos logit contributions
 mess+1.046
 wasting+0.934
 ruining+0.917
 wasteful+0.912
 fighting+0.898
Neg logit contributions
iest-0.666
 oblig-0.612
 armour-0.585
br-0.579
 ti-0.574
Token back
Token ID736
Feature activation+1.83e-01

Pos logit contributions
 mess+0.152
 wasting+0.133
 ruining+0.131
 wasteful+0.129
 fighting+0.128
Neg logit contributions
iest-0.115
 oblig-0.104
 armour-0.102
br-0.101
 ti-0.099
Token to
Token ID284
Feature activation+7.23e-01

Pos logit contributions
 mess+0.399
 wasting+0.353
 ruining+0.347
 wasteful+0.343
 fighting+0.339
Neg logit contributions
iest-0.274
 oblig-0.246
 armour-0.242
br-0.239
 ti-0.235
Token the
Token ID262
Feature activation+3.58e+00

Pos logit contributions
 mess+1.567
 wasting+1.395
 wasteful+1.377
 ruining+1.367
 fighting+1.326
Neg logit contributions
iest-1.027
 oblig-0.964
 armour-0.945
 sail-0.912
br-0.901
Token garden
Token ID11376
Feature activation+1.37e+00

Pos logit contributions
 mess+7.002
 ruining+6.876
 wasting+6.745
 wasteful+6.615
 yourselves+6.447
Neg logit contributions
 name-5.425
 sail-5.281
iest-5.247
 ti-5.091
 seas-5.020
Token,
Token ID11
Feature activation+1.54e+00

Pos logit contributions
 mess+2.681
 wasting+2.390
 wasteful+2.364
 ruining+2.342
 yourselves+2.250
Neg logit contributions
iest-2.286
 armour-2.091
 oblig-2.062
 ti-2.019
 sail-2.010
Token but
Token ID475
Feature activation+1.03e+00

Pos logit contributions
 mess+2.262
 wasting+1.910
 wasteful+1.871
 ruining+1.836
 yourselves+1.737
Neg logit contributions
iest-3.190
 armour-3.097
 sail-3.070
 oblig-3.060
 ti-3.034
Token he
Token ID339
Feature activation+7.90e-01

Pos logit contributions
 mess+2.599
 wasting+2.318
 ruining+2.279
 wasteful+2.252
 fighting+2.207
Neg logit contributions
iest-1.192
 armour-1.035
 oblig-1.021
 medal-0.996
 sail-0.988
Token was
Token ID373
Feature activation+1.20e+00

Pos logit contributions
 mess+1.659
 wasting+1.465
 ruining+1.447
 wasteful+1.411
 fighting+1.397
Neg logit contributions
iest-1.243
 oblig-1.111
 armour-1.092
int-1.073
br-1.068
Token're
Token ID821
Feature activation+1.46e+00

Pos logit contributions
 mess+0.271
 wasting+0.238
 ruining+0.234
 wasteful+0.231
 fighting+0.228
Neg logit contributions
iest-0.204
 oblig-0.184
 armour-0.181
br-0.180
 ti-0.177
Token glad
Token ID9675
Feature activation+1.83e+00

Pos logit contributions
 mess+2.766
 wasting+2.307
 wasteful+2.296
 ruining+2.292
 fighting+2.125
Neg logit contributions
iest-2.534
 oblig-2.408
br-2.270
 armour-2.255
 sail-2.254
Token you
Token ID345
Feature activation-2.86e-01

Pos logit contributions
 mess+2.682
 wasteful+2.208
 wasting+2.123
 ruining+2.105
 fighting+1.928
Neg logit contributions
iest-4.091
 oblig-3.825
 ti-3.742
br-3.719
 medal-3.663
Token're
Token ID821
Feature activation+2.17e+00

Pos logit contributions
iest+0.494
 oblig+0.450
 armour+0.449
br+0.445
anger+0.436
Neg logit contributions
 mess-0.562
 wasting-0.487
 ruining-0.478
 wasteful-0.471
 fighting-0.470
Token okay
Token ID8788
Feature activation+1.92e+00

Pos logit contributions
 mess+3.964
 wasteful+3.488
 wasting+3.406
 ruining+3.326
 rats+2.996
Neg logit contributions
iest-3.888
 oblig-3.562
 sail-3.542
 name-3.440
 armour-3.395
Token,
Token ID11
Feature activation+3.57e+00

Pos logit contributions
 mess+4.708
 wasteful+4.275
 wasting+4.244
 ruining+4.205
 yourselves+3.873
Neg logit contributions
iest-2.343
 oblig-1.910
 ti-1.895
br-1.854
 armour-1.805
Token Anna
Token ID11735
Feature activation+1.64e+00

Pos logit contributions
 mess+6.026
 wasteful+5.666
 ruining+5.500
 wasting+5.398
 fighting+5.064
Neg logit contributions
iest-7.196
 yes-6.724
 medal-6.560
br-6.520
 ti-6.438
Token.
Token ID13
Feature activation+5.43e-01

Pos logit contributions
 mess+3.922
 ruining+3.596
 wasting+3.591
 wasteful+3.521
 fighting+3.369
Neg logit contributions
iest-2.109
 oblig-1.746
 ti-1.708
br-1.697
 powers-1.635
Token We
Token ID775
Feature activation+3.07e-02

Pos logit contributions
 mess+0.982
 wasting+0.830
 ruining+0.814
 wasteful+0.792
 fighting+0.784
Neg logit contributions
iest-1.022
 oblig-0.933
br-0.921
 armour-0.919
 ti-0.911
Token love
Token ID1842
Feature activation+1.85e+00

Pos logit contributions
 mess+0.063
 wasting+0.055
 ruining+0.054
 wasteful+0.053
 fighting+0.053
Neg logit contributions
iest-0.050
 oblig-0.045
 armour-0.045
br-0.044
 ti-0.044
Token you
Token ID345
Feature activation+1.88e+00

Pos logit contributions
 mess+2.634
 wasteful+2.094
 wasting+2.072
 ruining+2.019
 fighting+1.858
Neg logit contributions
iest-4.066
 oblig-3.921
 powers-3.812
 ti-3.762
 medal-3.739
Token
Token ID198
Feature activation+5.00e-01

Pos logit contributions
 mess+0.697
 wasting+0.591
 ruining+0.584
 wasteful+0.573
 fighting+0.565
Neg logit contributions
iest-0.747
 oblig-0.694
br-0.684
 armour-0.682
 ti-0.676
Token
Token ID198
Feature activation+1.84e+00

Pos logit contributions
 mess+1.117
 wasting+0.991
 ruining+0.985
 wasteful+0.971
 fighting+0.954
Neg logit contributions
iest-0.704
 oblig-0.643
br-0.623
 armour-0.614
 ti-0.611
Token"
Token ID1
Feature activation+7.64e-02

Pos logit contributions
 mess+3.813
 ruining+3.317
 wasteful+3.237
 wasting+3.229
 fighting+3.193
Neg logit contributions
iest-2.992
br-2.882
 oblig-2.796
 ti-2.770
shirt-2.654
TokenBe
Token ID3856
Feature activation+3.72e-01

Pos logit contributions
 mess+0.140
 wasting+0.120
 ruining+0.118
 wasteful+0.116
 fighting+0.115
Neg logit contributions
iest-0.141
 oblig-0.129
 armour-0.128
br-0.127
 ti-0.125
Token careful
Token ID8161
Feature activation+1.88e+00

Pos logit contributions
 mess+0.551
 wasting+0.456
 ruining+0.446
 wasteful+0.435
 fighting+0.432
Neg logit contributions
iest-0.810
 oblig-0.755
 armour-0.745
br-0.739
 ti-0.732
Token,
Token ID11
Feature activation+3.57e+00

Pos logit contributions
 mess+4.300
 wasting+3.949
 wasteful+3.944
 ruining+3.878
 fighting+3.682
Neg logit contributions
iest-2.639
 oblig-2.316
 ti-2.162
 powers-2.154
br-2.150
Token Mom
Token ID11254
Feature activation+2.11e+00

Pos logit contributions
 mess+6.325
 wasteful+5.982
 ruining+5.812
 wasting+5.741
 fighting+5.662
Neg logit contributions
iest-6.487
 ti-6.161
 yes-6.104
 name-6.075
br-5.895
Token.
Token ID13
Feature activation+7.06e-01

Pos logit contributions
 mess+4.773
 ruining+4.418
 wasting+4.401
 wasteful+4.342
 fighting+4.128
Neg logit contributions
iest-2.989
 oblig-2.604
 ti-2.522
int-2.498
br-2.495
Token The
Token ID383
Feature activation+1.51e+00

Pos logit contributions
 mess+1.528
 wasting+1.317
 ruining+1.310
 wasteful+1.281
 fighting+1.271
Neg logit contributions
iest-1.058
 oblig-0.970
br-0.942
 armour-0.942
 ti-0.931
Token oven
Token ID14361
Feature activation+1.24e+00

Pos logit contributions
 mess+2.348
 wasting+2.054
 ruining+2.033
 wasteful+1.981
 fighting+1.935
Neg logit contributions
iest-3.059
br-2.817
 oblig-2.782
anger-2.734
 name-2.728
Token is
Token ID318
Feature activation+1.98e+00

Pos logit contributions
 mess+2.570
 wasting+2.342
 ruining+2.300
 wasteful+2.242
 fighting+2.233
Neg logit contributions
iest-1.887
br-1.705
 oblig-1.665
anger-1.637
int-1.611
Token,
Token ID11
Feature activation+4.98e-01

Pos logit contributions
iest+1.825
 armour+1.738
 oblig+1.670
shirt+1.647
int+1.621
Neg logit contributions
 mess-1.985
 wasting-1.749
 fighting-1.727
 wasteful-1.676
 ruining-1.671
Token "
Token ID366
Feature activation+1.21e+00

Pos logit contributions
 mess+1.077
 wasting+0.940
 ruining+0.928
 wasteful+0.922
 fighting+0.898
Neg logit contributions
iest-0.735
 oblig-0.671
br-0.659
 armour-0.648
 ti-0.646
TokenIt
Token ID1026
Feature activation+1.38e+00

Pos logit contributions
 mess+2.478
 ruining+2.125
 wasting+2.116
 wasteful+2.049
 fighting+2.029
Neg logit contributions
iest-2.031
br-1.833
 oblig-1.806
shirt-1.792
 ti-1.759
Token's
Token ID338
Feature activation+1.32e+00

Pos logit contributions
 mess+2.216
 wasting+1.906
 ruining+1.881
 wasteful+1.861
 yourselves+1.749
Neg logit contributions
iest-2.809
br-2.593
 powers-2.532
 oblig-2.525
int-2.501
Token okay
Token ID8788
Feature activation+1.15e+00

Pos logit contributions
 mess+2.049
 wasting+1.716
 ruining+1.672
 fighting+1.614
 wasteful+1.612
Neg logit contributions
iest-2.695
 armour-2.521
br-2.510
 oblig-2.506
int-2.474
Token,
Token ID11
Feature activation+3.57e+00

Pos logit contributions
 mess+2.624
 wasting+2.358
 ruining+2.331
 wasteful+2.300
 fighting+2.224
Neg logit contributions
iest-1.577
 oblig-1.383
br-1.362
 powers-1.329
 ti-1.327
Token my
Token ID616
Feature activation-1.06e+00

Pos logit contributions
 mess+5.835
 wasteful+5.369
 wasting+5.341
 ruining+5.105
ivering+4.689
Neg logit contributions
iest-6.866
 yes-6.520
 medal-6.452
br-6.356
 ti-6.175
Token loves
Token ID10408
Feature activation+1.19e-01

Pos logit contributions
iest+1.917
 oblig+1.802
 armour+1.788
br+1.763
shirt+1.706
Neg logit contributions
 mess-2.120
 wasting-1.722
 fighting-1.711
 wasteful-1.698
 ruining-1.663
Token.
Token ID13
Feature activation+2.77e-02

Pos logit contributions
 mess+0.247
 wasting+0.217
 ruining+0.213
 wasteful+0.210
 fighting+0.208
Neg logit contributions
iest-0.190
 oblig-0.171
 armour-0.169
br-0.167
 ti-0.164
Token Match
Token ID13225
Feature activation-8.25e-01

Pos logit contributions
 mess+0.054
 wasting+0.047
 ruining+0.047
 wasteful+0.046
 fighting+0.045
Neg logit contributions
iest-0.047
 oblig-0.043
 armour-0.042
br-0.042
 ti-0.041
Tokening
Token ID278
Feature activation+1.10e-01

Pos logit contributions
iest+1.465
 oblig+1.410
 armour+1.404
int+1.348
 ti+1.347
Neg logit contributions
 mess-1.540
 wasting-1.326
 fighting-1.290
 ruining-1.284
 wasteful-1.277
Token,
Token ID11
Feature activation+5.66e-02

Pos logit contributions
iest+0.639
 armour+0.584
 oblig+0.581
shirt+0.565
br+0.561
Neg logit contributions
 mess-0.786
 wasting-0.689
 ruining-0.675
 fighting-0.670
 wasteful-0.665
Token "
Token ID366
Feature activation+1.34e+00

Pos logit contributions
 mess+0.118
 wasting+0.103
 ruining+0.101
 wasteful+0.100
 fighting+0.099
Neg logit contributions
iest-0.090
 oblig-0.081
 armour-0.080
br-0.079
 ti-0.078
TokenIt
Token ID1026
Feature activation+1.09e+00

Pos logit contributions
 mess+2.813
 ruining+2.448
 wasting+2.427
 fighting+2.339
 wasteful+2.336
Neg logit contributions
iest-2.201
br-1.966
 oblig-1.947
shirt-1.917
 ti-1.898
Token's
Token ID338
Feature activation+1.37e+00

Pos logit contributions
 mess+1.658
 wasting+1.400
 ruining+1.390
 wasteful+1.367
 fighting+1.288
Neg logit contributions
iest-2.290
br-2.107
 oblig-2.094
 powers-2.063
int-2.053
Token okay
Token ID8788
Feature activation+9.16e-01

Pos logit contributions
 mess+2.145
 wasting+1.788
 ruining+1.770
 fighting+1.713
 wasteful+1.684
Neg logit contributions
iest-2.803
 oblig-2.606
 armour-2.579
br-2.573
 name-2.570
Token,
Token ID11
Feature activation+3.57e+00

Pos logit contributions
 mess+2.072
 wasting+1.847
 ruining+1.823
 wasteful+1.805
 fighting+1.752
Neg logit contributions
iest-1.291
 oblig-1.135
br-1.116
 ti-1.087
 armour-1.084
Token my
Token ID616
Feature activation-3.77e-01

Pos logit contributions
 mess+6.135
 wasteful+5.841
 wasting+5.377
 ruining+5.309
 fighting+4.970
Neg logit contributions
iest-6.840
 yes-6.509
 medal-6.447
 ti-6.252
 goodbye-6.154
Token loves
Token ID10408
Feature activation+3.49e-01

Pos logit contributions
iest+0.667
 oblig+0.613
 armour+0.613
br+0.603
shirt+0.591
Neg logit contributions
 mess-0.732
 wasting-0.622
 ruining-0.604
 wasteful-0.604
 fighting-0.598
Token.
Token ID13
Feature activation-2.77e-01

Pos logit contributions
 mess+0.732
 wasting+0.648
 ruining+0.637
 wasteful+0.627
 fighting+0.620
Neg logit contributions
iest-0.547
 oblig-0.489
 armour-0.480
br-0.479
 ti-0.472
Token I
Token ID314
Feature activation-1.49e-01

Pos logit contributions
iest+0.489
 oblig+0.445
 armour+0.441
br+0.435
shirt+0.427
Neg logit contributions
 mess-0.522
 wasting-0.457
 ruining-0.447
 wasteful-0.443
 fighting-0.436
Token am
Token ID716
Feature activation+1.28e+00

Pos logit contributions
iest+0.198
 armour+0.174
 oblig+0.173
br+0.170
shirt+0.166
Neg logit contributions
 mess-0.352
 wasting-0.312
 ruining-0.307
 wasteful-0.305
 fighting-0.303
TokenYou
Token ID1639
Feature activation+1.27e+00

Pos logit contributions
 mess+3.509
 ruining+3.029
 wasting+3.012
 wasteful+2.913
 fighting+2.905
Neg logit contributions
iest-2.644
 oblig-2.410
shirt-2.398
br-2.341
 ti-2.262
Token are
Token ID389
Feature activation+1.98e+00

Pos logit contributions
 mess+2.734
 ruining+2.382
 wasting+2.369
 wasteful+2.318
 fighting+2.250
Neg logit contributions
iest-1.883
 oblig-1.689
 sail-1.672
br-1.653
 armour-1.652
Token being
Token ID852
Feature activation+1.20e+00

Pos logit contributions
 mess+3.371
 wasteful+2.670
 wasting+2.622
 ruining+2.575
 yourselves+2.542
Neg logit contributions
iest-3.686
 oblig-3.505
br-3.498
 medal-3.459
 armour-3.404
Token very
Token ID845
Feature activation+2.99e-01

Pos logit contributions
 mess+1.843
 wasting+1.481
 ruining+1.459
 wasteful+1.390
 fighting+1.382
Neg logit contributions
iest-2.505
 oblig-2.359
 armour-2.325
br-2.306
shirt-2.282
Token stubborn
Token ID24444
Feature activation+9.54e-01

Pos logit contributions
 mess+0.430
 wasting+0.351
 ruining+0.344
 wasteful+0.333
 fighting+0.332
Neg logit contributions
iest-0.668
 oblig-0.622
 armour-0.613
br-0.613
 ti-0.604
Token,
Token ID11
Feature activation+3.57e+00

Pos logit contributions
 mess+1.951
 wasting+1.744
 ruining+1.715
 wasteful+1.691
 fighting+1.635
Neg logit contributions
iest-1.540
 oblig-1.332
br-1.324
 armour-1.322
shirt-1.308
Token Anna
Token ID11735
Feature activation+1.61e+00

Pos logit contributions
 mess+6.436
 wasteful+6.049
 ruining+5.776
 wasting+5.711
 fighting+5.471
Neg logit contributions
iest-6.796
 medal-6.194
 yes-6.151
 ti-6.043
 farewell-5.851
Token and
Token ID290
Feature activation+1.08e+00

Pos logit contributions
 mess+3.423
 wasting+3.071
 ruining+3.068
 wasteful+3.012
 fighting+2.891
Neg logit contributions
iest-2.498
 ti-2.143
br-2.137
 oblig-2.133
 armour-2.090
Token Ben
Token ID3932
Feature activation+9.06e-01

Pos logit contributions
 mess+1.781
 ruining+1.463
 wasting+1.450
 wasteful+1.407
 fighting+1.395
Neg logit contributions
iest-2.183
 armour-1.993
 oblig-1.990
 ti-1.980
br-1.964
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
 mess+1.878
 wasting+1.671
 ruining+1.654
 wasteful+1.621
 fighting+1.583
Neg logit contributions
iest-1.414
 oblig-1.254
br-1.225
 ti-1.218
 armour-1.210
Token You
Token ID921
Feature activation+1.56e+00

Pos logit contributions
 mess+2.181
 wasting+1.786
 ruining+1.782
 wasteful+1.721
 fighting+1.689
Neg logit contributions
iest-1.983
 oblig-1.854
 armour-1.826
shirt-1.822
br-1.802
Token
Token ID198
Feature activation+2.21e+00

Pos logit contributions
 mess+1.963
 ruining+1.757
 wasting+1.756
 wasteful+1.728
 fighting+1.666
Neg logit contributions
iest-1.123
 oblig-1.030
br-1.002
 armour-0.974
 ti-0.972
Token"
Token ID1
Feature activation+8.00e-01

Pos logit contributions
 mess+4.846
 ruining+4.378
 wasting+4.267
 wasteful+4.221
 fighting+3.979
Neg logit contributions
iest-3.104
 oblig-2.969
br-2.944
 ti-2.940
 sail-2.883
TokenIt
Token ID1026
Feature activation+1.37e+00

Pos logit contributions
 mess+1.568
 wasting+1.336
 ruining+1.333
 wasteful+1.297
 fighting+1.278
Neg logit contributions
iest-1.373
 oblig-1.252
br-1.242
 ti-1.224
 armour-1.203
Token's
Token ID338
Feature activation+2.31e+00

Pos logit contributions
 mess+2.383
 wasting+2.125
 ruining+2.090
 wasteful+2.068
 yourselves+1.967
Neg logit contributions
iest-2.546
br-2.330
 shone-2.264
 oblig-2.261
 powers-2.255
Token okay
Token ID8788
Feature activation+1.64e+00

Pos logit contributions
 mess+3.837
 wasting+3.317
 ruining+3.230
 wasteful+3.105
 fighting+3.099
Neg logit contributions
iest-4.129
 name-4.044
 armour-4.035
int-3.987
br-3.978
Token,
Token ID11
Feature activation+3.56e+00

Pos logit contributions
 mess+3.872
 wasting+3.529
 ruining+3.509
 wasteful+3.458
 fighting+3.302
Neg logit contributions
iest-2.093
 oblig-1.830
br-1.756
 ti-1.735
 powers-1.725
Token sweet
Token ID6029
Feature activation+1.87e+00

Pos logit contributions
 mess+6.601
 wasteful+6.336
 ruining+5.906
 wasting+5.890
 fighting+5.522
Neg logit contributions
iest-6.301
 ti-5.927
 yes-5.888
 medal-5.738
 name-5.569
Tokenies
Token ID444
Feature activation+2.04e+00

Pos logit contributions
 mess+3.131
 ruining+3.004
 wasting+2.904
 wasteful+2.819
 fighting+2.711
Neg logit contributions
iest-3.833
 oblig-3.254
int-3.247
anger-3.243
br-3.211
Token,"
Token ID553
Feature activation+8.85e-01

Pos logit contributions
 mess+4.809
 ruining+4.443
 wasting+4.378
 wasteful+4.320
 fighting+4.113
Neg logit contributions
iest-2.696
 oblig-2.275
br-2.165
 ti-2.160
 sail-2.103
Token Mom
Token ID11254
Feature activation+4.98e-01

Pos logit contributions
 mess+1.611
 ruining+1.381
 wasting+1.368
 wasteful+1.350
 fighting+1.279
Neg logit contributions
iest-1.589
 oblig-1.511
 ti-1.467
 armour-1.440
 sail-1.431
Token said
Token ID531
Feature activation+6.49e-02

Pos logit contributions
 mess+0.906
 wasting+0.782
 ruining+0.774
 wasteful+0.756
 fighting+0.736
Neg logit contributions
iest-0.912
 oblig-0.847
br-0.820
int-0.819
 armour-0.816
Token her
Token ID607
Feature activation+5.78e-01

Pos logit contributions
 mess+1.009
 wasting+0.869
 wasteful+0.855
 ruining+0.851
 fighting+0.819
Neg logit contributions
iest-0.922
 oblig-0.854
 armour-0.835
br-0.828
 ti-0.818
Token.
Token ID13
Feature activation+1.42e+00

Pos logit contributions
 mess+1.109
 wasting+0.973
 wasteful+0.955
 ruining+0.955
 fighting+0.923
Neg logit contributions
iest-0.994
 oblig-0.903
 armour-0.892
 ti-0.880
br-0.878
Token "
Token ID366
Feature activation+1.25e+00

Pos logit contributions
 mess+3.050
 wasting+2.725
 ruining+2.690
 wasteful+2.632
 fighting+2.545
Neg logit contributions
iest-1.909
 ti-1.881
shirt-1.861
 oblig-1.850
anger-1.848
TokenDon
Token ID3987
Feature activation+8.67e-01

Pos logit contributions
 mess+2.426
 ruining+2.076
 wasting+2.073
 wasteful+2.007
 fighting+2.002
Neg logit contributions
iest-2.162
shirt-1.973
br-1.962
 oblig-1.946
 ti-1.914
Token't
Token ID470
Feature activation+2.16e+00

Pos logit contributions
 mess+1.532
 wasting+1.313
 ruining+1.278
 wasteful+1.276
 fighting+1.243
Neg logit contributions
iest-1.664
br-1.531
 oblig-1.527
anger-1.482
int-1.440
Token hurt
Token ID5938
Feature activation+3.56e+00

Pos logit contributions
 mess+3.215
 wasting+2.868
 wasteful+2.858
 ruining+2.686
 fighting+2.513
Neg logit contributions
iest-4.445
 sail-4.326
 oblig-4.324
 ti-4.119
 name-4.090
Token the
Token ID262
Feature activation+1.16e+00

Pos logit contributions
 mess+8.151
 wasteful+7.422
 wasting+7.352
 ruining+6.927
 fighting+6.570
Neg logit contributions
iest-4.877
 powers-4.261
 sail-4.234
 oblig-4.150
 medal-4.127
Token bug
Token ID5434
Feature activation+2.05e+00

Pos logit contributions
 mess+2.279
 wasting+2.074
 ruining+2.048
 wasteful+2.008
 fighting+1.982
Neg logit contributions
iest-1.926
 oblig-1.676
br-1.666
 ti-1.663
anger-1.663
Token,
Token ID11
Feature activation+1.70e+00

Pos logit contributions
 mess+4.575
 wasting+4.236
 ruining+4.142
 wasteful+4.119
 fighting+3.992
Neg logit contributions
iest-3.078
br-2.579
 oblig-2.479
 powers-2.373
 medal-2.354
Token Lily
Token ID20037
Feature activation+2.38e+00

Pos logit contributions
 mess+3.211
 wasting+2.804
 ruining+2.795
 wasteful+2.746
 fighting+2.690
Neg logit contributions
iest-2.898
 ti-2.626
br-2.612
 sail-2.595
 medal-2.546
Token,"
Token ID553
Feature activation+8.64e-01

Pos logit contributions
 mess+5.638
 ruining+5.351
 wasting+5.282
 wasteful+5.117
 fighting+4.998
Neg logit contributions
iest-3.179
 ti-2.594
 oblig-2.542
br-2.495
 sail-2.488
Token right
Token ID826
Feature activation-3.22e-01

Pos logit contributions
 mess+2.490
 wasting+2.243
 wasteful+2.180
 ruining+2.127
 fighting+2.079
Neg logit contributions
iest-2.023
 armour-1.858
br-1.839
 oblig-1.839
anger-1.817
Token into
Token ID656
Feature activation+8.92e-01

Pos logit contributions
iest+0.574
 oblig+0.531
br+0.515
 armour+0.512
 ti+0.507
Neg logit contributions
 mess-0.609
 wasting-0.521
 ruining-0.518
 wasteful-0.505
 fighting-0.502
Token the
Token ID262
Feature activation+2.73e+00

Pos logit contributions
 mess+1.793
 wasting+1.562
 wasteful+1.556
 ruining+1.538
 fighting+1.488
Neg logit contributions
iest-1.415
 armour-1.318
 oblig-1.308
br-1.251
 sail-1.249
Token middle
Token ID3504
Feature activation+1.61e+00

Pos logit contributions
 mess+5.485
 wasting+5.285
 ruining+5.182
 wasteful+4.988
 yourselves+4.901
Neg logit contributions
iest-3.881
 sail-3.804
 name-3.795
 armour-3.759
shirt-3.667
Token of
Token ID286
Feature activation+9.25e-01

Pos logit contributions
 mess+4.289
 wasteful+3.971
 wasting+3.967
 ruining+3.866
 yourselves+3.755
Neg logit contributions
iest-1.737
br-1.381
anger-1.310
 armour-1.302
 oblig-1.294
Token the
Token ID262
Feature activation+3.56e+00

Pos logit contributions
 mess+1.750
 wasteful+1.492
 wasting+1.486
 ruining+1.461
 fighting+1.413
Neg logit contributions
iest-1.607
 armour-1.502
 oblig-1.476
 sail-1.443
br-1.434
Token road
Token ID2975
Feature activation+1.76e+00

Pos logit contributions
 wasting+7.337
 wasteful+7.272
 ruining+7.183
 yourselves+7.135
 mess+7.127
Neg logit contributions
iest-4.987
br-4.958
 sail-4.816
 seas-4.596
 name-4.524
Token,
Token ID11
Feature activation+2.44e+00

Pos logit contributions
 mess+3.816
 wasting+3.444
 wasteful+3.424
 ruining+3.326
 yourselves+3.241
Neg logit contributions
iest-2.570
anger-2.249
 oblig-2.234
 armour-2.229
 sail-2.210
Token and
Token ID290
Feature activation+1.60e+00

Pos logit contributions
 mess+4.286
 wasteful+3.833
 wasting+3.642
 yourselves+3.600
 ruining+3.486
Neg logit contributions
 sail-4.098
iest-4.086
 armour-4.051
 ti-3.950
 shone-3.945
Token a
Token ID257
Feature activation+2.28e-01

Pos logit contributions
 mess+3.501
 wasting+3.076
 wasteful+3.006
 ruining+2.969
 yourselves+2.947
Neg logit contributions
iest-2.244
 armour-2.082
 sail-2.058
 oblig-2.052
 ti-2.005
Token car
Token ID1097
Feature activation-5.98e-01

Pos logit contributions
 mess+0.434
 wasting+0.378
 ruining+0.371
 wasteful+0.365
 fighting+0.361
Neg logit contributions
iest-0.396
 oblig-0.362
 armour-0.357
br-0.356
 ti-0.349
Token joy
Token ID8716
Feature activation-1.33e+00

Pos logit contributions
iest+2.654
anger+2.532
int+2.446
shirt+2.383
 oblig+2.346
Neg logit contributions
 mess-3.055
 wasting-2.627
 ruining-2.586
 fighting-2.553
 wasteful-2.469
Token as
Token ID355
Feature activation-1.60e+00

Pos logit contributions
iest+2.359
 oblig+2.253
shirt+2.173
br+2.169
 armour+2.167
Neg logit contributions
 mess-2.516
 fighting-2.151
 wasting-2.147
 ruining-2.125
 wasteful-1.985
Token the
Token ID262
Feature activation-1.68e+00

Pos logit contributions
int+3.237
shirt+3.237
iest+3.229
anger+3.135
 oblig+3.110
Neg logit contributions
 mess-2.532
 wasting-2.199
 fighting-2.126
 ruining-2.080
 wasteful-2.026
Token yellow
Token ID7872
Feature activation-3.04e+00

Pos logit contributions
iest+2.219
anger+2.130
shirt+2.095
int+2.065
br+2.050
Neg logit contributions
 mess-4.038
 wasting-3.484
 fighting-3.444
 ruining-3.364
 wasteful-3.297
Token boat
Token ID8848
Feature activation-1.82e+00

Pos logit contributions
shirt+4.569
 oblig+4.386
iest+4.278
br+4.263
 ti+4.255
Neg logit contributions
 mess-6.827
 fighting-5.737
 wasting-5.504
 ruining-5.154
 forth-5.149
Token gl
Token ID1278
Feature activation-4.23e+00

Pos logit contributions
iest+2.791
shirt+2.660
 oblig+2.611
 armour+2.569
int+2.542
Neg logit contributions
 mess-3.951
 fighting-3.401
 ruining-3.342
 wasting-3.329
 wasteful-3.154
Tokenided
Token ID1384
Feature activation-2.53e+00

Pos logit contributions
 armour+6.695
 ti+6.591
 mineral+6.500
 medal+6.459
 oblig+6.244
Neg logit contributions
 mess-8.733
 wasteful-7.685
 ruining-7.383
ivering-7.234
 yourselves-7.227
Token across
Token ID1973
Feature activation-1.08e+00

Pos logit contributions
 oblig+4.922
iest+4.914
int+4.689
 ti+4.572
br+4.523
Neg logit contributions
 mess-4.304
 fighting-3.666
 ruining-3.435
 forth-3.397
 wasting-3.261
Token the
Token ID262
Feature activation-5.07e-01

Pos logit contributions
iest+2.355
int+2.253
shirt+2.222
 oblig+2.216
anger+2.195
Neg logit contributions
 mess-1.621
 wasting-1.328
 ruining-1.304
 fighting-1.290
 wasteful-1.208
Token lake
Token ID13546
Feature activation-2.63e-01

Pos logit contributions
iest+0.818
 oblig+0.753
 armour+0.728
anger+0.719
br+0.716
Neg logit contributions
 mess-1.060
 wasting-0.903
 ruining-0.885
 fighting-0.875
 wasteful-0.871
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
iest+0.424
 oblig+0.387
 armour+0.379
br+0.376
shirt+0.371
Neg logit contributions
 mess-0.538
 wasting-0.467
 ruining-0.460
 fighting-0.453
 wasteful-0.448
Token She
Token ID1375
Feature activation-1.37e+00

Pos logit contributions
 mess+0.145
 wasting+0.126
 ruining+0.124
 wasteful+0.122
 fighting+0.121
Neg logit contributions
iest-0.128
 oblig-0.117
 armour-0.115
br-0.115
 ti-0.113
Token smiled
Token ID13541
Feature activation-9.02e-01

Pos logit contributions
iest+2.522
 oblig+2.242
 armour+2.238
anger+2.202
br+2.182
Neg logit contributions
 mess-2.675
 wasting-2.274
 fighting-2.195
 ruining-2.152
 wasteful-2.126
Token and
Token ID290
Feature activation-1.50e+00

Pos logit contributions
iest+1.970
 oblig+1.842
br+1.809
anger+1.798
shirt+1.781
Neg logit contributions
 mess-1.392
 wasting-1.128
 fighting-1.099
 ruining-1.079
 wasteful-1.054
Token gave
Token ID2921
Feature activation-3.78e-01

Pos logit contributions
iest+2.929
 armour+2.661
anger+2.628
 oblig+2.590
br+2.548
Neg logit contributions
 mess-2.729
 wasting-2.369
 fighting-2.289
 ruining-2.265
 wasteful-2.218
Token Tim
Token ID5045
Feature activation-7.91e-01

Pos logit contributions
iest+0.758
 oblig+0.701
br+0.694
 armour+0.691
int+0.678
Neg logit contributions
 mess-0.640
 wasting-0.538
 ruining-0.527
 fighting-0.522
 wasteful-0.517
Token a
Token ID257
Feature activation-4.18e+00

Pos logit contributions
iest+1.458
 oblig+1.347
br+1.341
 armour+1.309
anger+1.308
Neg logit contributions
 mess-1.446
 wasting-1.238
 ruining-1.184
 fighting-1.184
 wasteful-1.180
Token hug
Token ID16225
Feature activation-7.63e-01

Pos logit contributions
anced+9.798
iest+9.699
 armour+9.351
ests+9.264
ance+9.032
Neg logit contributions
 mess-8.027
 wasting-5.177
 fighting-4.917
 wasteful-4.788
 mistake-4.775
Token.
Token ID13
Feature activation+3.21e-01

Pos logit contributions
iest+1.301
 oblig+1.210
br+1.185
 armour+1.181
int+1.148
Neg logit contributions
 mess-1.482
 wasting-1.277
 fighting-1.251
 ruining-1.248
 wasteful-1.236
Token They
Token ID1119
Feature activation-9.16e-01

Pos logit contributions
 mess+0.657
 wasting+0.573
 ruining+0.564
 wasteful+0.558
 fighting+0.546
Neg logit contributions
iest-0.517
 oblig-0.471
 armour-0.463
br-0.463
 ti-0.454
Token were
Token ID547
Feature activation+9.40e-01

Pos logit contributions
iest+1.765
anger+1.602
br+1.595
 oblig+1.594
 armour+1.578
Neg logit contributions
 mess-1.634
 wasting-1.398
 ruining-1.340
 fighting-1.339
 wasteful-1.321
Token happy
Token ID3772
Feature activation+1.02e+00

Pos logit contributions
 mess+1.666
 wasting+1.401
 wasteful+1.389
 ruining+1.374
 fighting+1.326
Neg logit contributions
iest-1.777
 oblig-1.640
 armour-1.631
 ti-1.611
br-1.587
Token mom
Token ID1995
Feature activation+1.70e+00

Pos logit contributions
iest+2.261
 oblig+2.112
br+2.106
 armour+2.061
int+2.043
Neg logit contributions
 mess-1.505
 wasting-1.160
 fighting-1.149
 ruining-1.125
 wasteful-1.105
Tokenmy
Token ID1820
Feature activation+3.70e-01

Pos logit contributions
 mess+2.188
 ruining+1.859
 wasting+1.854
 wasteful+1.802
 yourselves+1.783
Neg logit contributions
iest-4.030
int-3.784
 oblig-3.721
shirt-3.713
 shone-3.694
Token gave
Token ID2921
Feature activation+8.36e-01

Pos logit contributions
 mess+0.670
 wasting+0.577
 ruining+0.568
 wasteful+0.558
 fighting+0.545
Neg logit contributions
iest-0.683
 oblig-0.629
 armour-0.617
br-0.615
int-0.607
Token her
Token ID607
Feature activation-1.65e+00

Pos logit contributions
 mess+1.575
 wasting+1.369
 ruining+1.355
 wasteful+1.323
 fighting+1.291
Neg logit contributions
iest-1.482
 oblig-1.346
 armour-1.330
shirt-1.325
br-1.311
Token a
Token ID257
Feature activation-3.21e+00

Pos logit contributions
iest+2.707
br+2.546
 oblig+2.532
anger+2.435
 armour+2.402
Neg logit contributions
 mess-3.463
 wasting-3.114
 wasteful-2.946
 fighting-2.928
 ruining-2.907
Token pops
Token ID26384
Feature activation-4.15e+00

Pos logit contributions
iest+6.782
anced+6.581
 armour+6.281
int+6.253
 oblig+6.215
Neg logit contributions
 mess-6.277
 wasting-4.700
 wasteful-4.565
 fighting-4.490
 mistake-4.469
Tokenicle
Token ID1548
Feature activation-1.46e+00

Pos logit contributions
 oblig+7.492
br+6.976
 armour+6.904
 ti+6.829
iest+6.799
Neg logit contributions
 mess-8.718
 fighting-7.167
 ruining-6.854
 yourselves-6.792
 wasting-6.663
Token to
Token ID284
Feature activation-1.50e+00

Pos logit contributions
iest+2.727
 oblig+2.616
 armour+2.541
int+2.482
br+2.478
Neg logit contributions
 mess-2.686
 wasting-2.223
 ruining-2.200
 fighting-2.196
 wasteful-2.145
Token taste
Token ID6938
Feature activation-8.77e-01

Pos logit contributions
iest+2.635
anger+2.413
br+2.356
 armour+2.327
shirt+2.280
Neg logit contributions
 mess-3.035
 wasting-2.623
 ruining-2.566
 wasteful-2.498
 fighting-2.496
Token.
Token ID13
Feature activation+1.14e+00

Pos logit contributions
iest+1.630
 oblig+1.568
 armour+1.531
anger+1.508
int+1.498
Neg logit contributions
 mess-1.605
 wasting-1.357
 ruining-1.313
 wasteful-1.303
 fighting-1.282
Token It
Token ID632
Feature activation+6.40e-01

Pos logit contributions
 mess+2.182
 wasting+1.938
 ruining+1.916
 wasteful+1.866
 fighting+1.812
Neg logit contributions
iest-1.877
 ti-1.799
shirt-1.798
br-1.798
anger-1.784
Token was
Token ID373
Feature activation-1.31e+00

Pos logit contributions
iest+1.717
 oblig+1.629
 armour+1.566
int+1.543
anger+1.540
Neg logit contributions
 mess-2.088
 wasting-1.771
 ruining-1.760
 fighting-1.733
 wasteful-1.674
Token a
Token ID257
Feature activation-9.00e-01

Pos logit contributions
iest+2.123
 oblig+1.983
int+1.941
shirt+1.870
anger+1.862
Neg logit contributions
 mess-2.778
 wasting-2.456
 ruining-2.425
 fighting-2.358
 wasteful-2.295
Token shiny
Token ID22441
Feature activation-2.36e+00

Pos logit contributions
iest+1.398
 oblig+1.283
int+1.250
 armour+1.220
shirt+1.210
Neg logit contributions
 mess-1.979
 wasting-1.683
 ruining-1.655
 fighting-1.626
 wasteful-1.616
Token rock
Token ID3881
Feature activation-6.04e-01

Pos logit contributions
 oblig+3.676
iest+3.463
int+3.296
anced+3.295
shirt+3.135
Neg logit contributions
 mess-5.608
 ruining-4.371
 fighting-4.348
 wasting-4.343
 wasteful-4.192
Token that
Token ID326
Feature activation-1.08e+00

Pos logit contributions
iest+1.056
 oblig+0.999
 armour+0.963
int+0.947
br+0.942
Neg logit contributions
 mess-1.160
 wasting-0.993
 ruining-0.981
 fighting-0.965
 wasteful-0.938
Token gl
Token ID1278
Feature activation-4.14e+00

Pos logit contributions
iest+1.683
 oblig+1.579
int+1.557
br+1.535
anger+1.531
Neg logit contributions
 mess-2.289
 wasting-1.981
 ruining-1.950
 fighting-1.909
 wasteful-1.889
Tokenittered
Token ID36613
Feature activation-1.62e+00

Pos logit contributions
 medal+7.020
 oblig+6.968
 sail+6.875
iest+6.807
 armour+6.762
Neg logit contributions
 mess-8.090
 ruining-7.031
 wasteful-6.933
 yourselves-6.796
 wasting-6.647
Token in
Token ID287
Feature activation-2.15e-01

Pos logit contributions
 oblig+3.007
iest+2.895
br+2.726
int+2.723
anger+2.707
Neg logit contributions
 mess-3.002
 ruining-2.516
 wasting-2.509
 fighting-2.477
 wasteful-2.352
Token the
Token ID262
Feature activation-6.58e-01

Pos logit contributions
iest+0.420
 oblig+0.389
br+0.382
 armour+0.378
int+0.378
Neg logit contributions
 mess-0.373
 wasting-0.318
 ruining-0.311
 fighting-0.303
 wasteful-0.301
Token sun
Token ID4252
Feature activation-6.08e-01

Pos logit contributions
iest+1.112
 oblig+1.035
anger+0.988
br+0.986
 armour+0.983
Neg logit contributions
 mess-1.311
 wasting-1.114
 ruining-1.096
 wasteful-1.079
 fighting-1.067
Token.
Token ID13
Feature activation-1.94e-01

Pos logit contributions
iest+1.009
 oblig+0.943
 armour+0.917
br+0.905
shirt+0.892
Neg logit contributions
 mess-1.208
 wasting-1.035
 ruining-1.022
 fighting-1.013
 wasteful-0.978
Token and
Token ID290
Feature activation-1.46e+00

Pos logit contributions
iest+4.023
 oblig+3.828
shirt+3.731
anger+3.725
br+3.722
Neg logit contributions
 mess-2.661
 wasting-2.112
 fighting-2.084
 ruining-2.027
 wasteful-1.898
Token gave
Token ID2921
Feature activation-1.12e+00

Pos logit contributions
iest+2.614
anger+2.398
br+2.325
 oblig+2.314
 armour+2.269
Neg logit contributions
 mess-2.865
 wasting-2.503
 ruining-2.410
 fighting-2.370
 wasteful-2.317
Token the
Token ID262
Feature activation-1.59e-01

Pos logit contributions
iest+2.035
br+1.912
 oblig+1.900
anger+1.856
 ti+1.832
Neg logit contributions
 mess-2.090
 wasting-1.770
 ruining-1.714
 fighting-1.711
 wasteful-1.701
Token sausage
Token ID31889
Feature activation-2.30e+00

Pos logit contributions
iest+0.256
 oblig+0.233
 armour+0.229
br+0.228
anger+0.224
Neg logit contributions
 mess-0.328
 wasting-0.286
 ruining-0.280
 wasteful-0.276
 fighting-0.275
Token one
Token ID530
Feature activation-2.24e+00

Pos logit contributions
iest+4.302
br+4.045
 oblig+4.023
anger+4.006
int+3.905
Neg logit contributions
 mess-4.295
 wasting-3.670
 fighting-3.507
 ruining-3.450
 wasteful-3.416
Token final
Token ID2457
Feature activation-4.14e+00

Pos logit contributions
iest+4.351
 oblig+4.311
br+4.240
anger+4.191
anced+4.139
Neg logit contributions
 mess-3.955
 wasting-3.144
 wasteful-3.004
 fighting-2.988
 ruining-2.897
Token hug
Token ID16225
Feature activation-1.79e+00

Pos logit contributions
ests+7.799
iest+7.676
anger+7.514
 armour+7.412
 seas+7.357
Neg logit contributions
 mess-9.041
 fighting-6.715
 mistake-6.657
 ruining-6.568
 wasting-6.486
Token before
Token ID878
Feature activation-5.81e-01

Pos logit contributions
iest+3.250
 oblig+3.203
int+3.085
br+3.070
 armour+3.016
Neg logit contributions
 mess-3.211
 wasting-2.703
 fighting-2.682
 ruining-2.679
 wasteful-2.554
Token he
Token ID339
Feature activation-2.16e+00

Pos logit contributions
iest+0.969
 oblig+0.873
int+0.861
shirt+0.861
br+0.861
Neg logit contributions
 mess-1.184
 wasting-1.041
 ruining-1.020
 fighting-1.010
 wasteful-0.970
Token went
Token ID1816
Feature activation-1.71e+00

Pos logit contributions
iest+3.994
anger+3.652
 oblig+3.522
shirt+3.488
 armour+3.487
Neg logit contributions
 mess-4.266
 wasting-3.500
 ruining-3.414
 fighting-3.306
 wasteful-3.300
Token home
Token ID1363
Feature activation-2.96e-01

Pos logit contributions
iest+3.254
 oblig+2.903
int+2.903
br+2.814
 armour+2.797
Neg logit contributions
 mess-3.297
 ruining-2.695
 wasting-2.668
 fighting-2.636
 wasteful-2.449
Token and
Token ID290
Feature activation+3.09e-01

Pos logit contributions
iest+1.060
 oblig+0.977
 armour+0.963
br+0.957
int+0.946
Neg logit contributions
 mess-1.101
 wasting-0.962
 ruining-0.938
 fighting-0.937
 wasteful-0.897
Token gave
Token ID2921
Feature activation-7.16e-01

Pos logit contributions
 mess+0.604
 wasting+0.525
 ruining+0.516
 wasteful+0.510
 fighting+0.502
Neg logit contributions
iest-0.526
 oblig-0.478
 armour-0.475
br-0.468
 ti-0.463
Token his
Token ID465
Feature activation-2.93e+00

Pos logit contributions
iest+1.335
 oblig+1.240
br+1.233
int+1.209
 armour+1.202
Neg logit contributions
 mess-1.283
 wasting-1.088
 ruining-1.065
 fighting-1.063
 wasteful-1.043
Token jacket
Token ID15224
Feature activation-2.39e+00

Pos logit contributions
 oblig+5.624
br+5.602
iest+5.568
int+5.414
anger+5.313
Neg logit contributions
 mess-5.809
 fighting-4.597
 wasting-4.495
 ruining-4.221
 wasteful-4.162
Token an
Token ID281
Feature activation-2.25e+00

Pos logit contributions
iest+4.664
 oblig+4.533
br+4.317
int+4.307
 armour+4.098
Neg logit contributions
 mess-4.331
 fighting-3.481
 wasting-3.426
 ruining-3.389
 wasteful-3.297
Token extra
Token ID3131
Feature activation-4.13e+00

Pos logit contributions
iest+4.415
br+4.358
 oblig+4.342
anger+4.184
anced+4.029
Neg logit contributions
 mess-4.016
 wasting-3.158
 ruining-3.056
 wasteful-3.048
 fighting-3.025
Token tight
Token ID5381
Feature activation-2.44e+00

Pos logit contributions
 oblig+8.314
anced+8.087
iest+7.870
inosaur+7.657
anger+7.626
Neg logit contributions
 mess-9.047
 mistake-5.889
 fuss-5.885
 yourselves-5.701
 wasting-5.663
Token hug
Token ID16225
Feature activation-1.71e+00

Pos logit contributions
iest+4.475
 oblig+4.404
int+4.162
br+4.073
 armour+4.000
Neg logit contributions
 mess-4.988
 fighting-3.846
 ruining-3.823
 wasting-3.816
 wasteful-3.547
Token.
Token ID13
Feature activation-6.65e-01

Pos logit contributions
iest+3.074
 oblig+3.068
int+2.923
br+2.902
 armour+2.879
Neg logit contributions
 mess-3.081
 fighting-2.585
 wasting-2.583
 ruining-2.569
 wasteful-2.445
Token
Token ID198
Feature activation-7.33e-01

Pos logit contributions
iest+1.101
 oblig+0.970
br+0.960
 armour+0.944
 ti+0.937
Neg logit contributions
 mess-1.372
 wasting-1.197
 ruining-1.172
 fighting-1.170
 wasteful-1.149
Token
Token ID198
Feature activation+3.50e-01

Pos logit contributions
iest+1.250
 armour+1.125
 oblig+1.109
br+1.101
int+1.096
Neg logit contributions
 mess-1.446
 wasting-1.247
 fighting-1.217
 ruining-1.214
 wasteful-1.183
Token him
Token ID683
Feature activation+1.51e-01

Pos logit contributions
iest+0.567
br+0.505
 oblig+0.502
 armour+0.499
shirt+0.490
Neg logit contributions
 mess-0.781
 wasting-0.694
 ruining-0.676
 fighting-0.668
 wasteful-0.662
Token and
Token ID290
Feature activation-2.53e-01

Pos logit contributions
 mess+0.259
 wasting+0.220
 ruining+0.216
 wasteful+0.212
 fighting+0.209
Neg logit contributions
iest-0.293
 oblig-0.270
 armour-0.267
br-0.265
 ti-0.261
Token gave
Token ID2921
Feature activation-9.54e-01

Pos logit contributions
iest+0.447
 oblig+0.404
 armour+0.401
br+0.399
shirt+0.393
Neg logit contributions
 mess-0.484
 wasting-0.420
 ruining-0.410
 wasteful-0.403
 fighting-0.402
Token him
Token ID683
Feature activation-2.08e+00

Pos logit contributions
iest+1.432
br+1.325
 oblig+1.286
anger+1.276
 armour+1.272
Neg logit contributions
 mess-2.066
 wasting-1.822
 fighting-1.768
 ruining-1.754
 wasteful-1.735
Token a
Token ID257
Feature activation-3.70e+00

Pos logit contributions
iest+4.015
br+3.721
anger+3.698
 oblig+3.612
int+3.565
Neg logit contributions
 mess-3.733
 wasting-3.280
 wasteful-3.070
 fighting-3.051
 ruining-3.031
Token special
Token ID2041
Feature activation-4.13e+00

Pos logit contributions
anced+8.165
iest+8.161
 armour+7.771
int+7.634
anger+7.598
Neg logit contributions
 mess-6.921
 wasting-5.124
 wasteful-4.636
 fighting-4.539
 mistake-4.453
Token gift
Token ID6979
Feature activation-2.07e+00

Pos logit contributions
anced+7.331
int+7.077
iest+6.947
 armour+6.761
br+6.709
Neg logit contributions
 mess-9.939
 mistake-7.765
 wasting-7.200
 fighting-7.146
 ruining-6.692
Token.
Token ID13
Feature activation-6.69e-01

Pos logit contributions
iest+3.992
int+3.870
 oblig+3.847
 armour+3.762
br+3.762
Neg logit contributions
 mess-3.526
 wasting-2.926
 fighting-2.912
 ruining-2.885
 wasteful-2.725
Token From
Token ID3574
Feature activation+1.33e-02

Pos logit contributions
iest+1.069
 oblig+0.943
br+0.932
 armour+0.925
shirt+0.897
Neg logit contributions
 mess-1.404
 wasting-1.258
 fighting-1.212
 ruining-1.209
 wasteful-1.196
Token that
Token ID326
Feature activation-2.20e-01

Pos logit contributions
 mess+0.021
 wasting+0.017
 ruining+0.017
 wasteful+0.016
 fighting+0.016
Neg logit contributions
iest-0.028
 oblig-0.026
 armour-0.026
br-0.026
 ti-0.026
Token day
Token ID1110
Feature activation-1.73e+00

Pos logit contributions
iest+0.314
 oblig+0.284
 armour+0.280
br+0.277
int+0.273
Neg logit contributions
 mess-0.492
 wasting-0.434
 ruining-0.426
 fighting-0.420
 wasteful-0.419
Token So
Token ID1406
Feature activation-6.85e-01

Pos logit contributions
iest+1.892
 oblig+1.612
br+1.600
 armour+1.566
 ti+1.547
Neg logit contributions
 mess-2.420
 wasting-2.099
 fighting-2.073
 ruining-2.045
 wasteful-2.027
Token he
Token ID339
Feature activation-1.89e+00

Pos logit contributions
iest+1.003
 oblig+0.910
shirt+0.886
br+0.880
anger+0.876
Neg logit contributions
 mess-1.504
 wasting-1.330
 ruining-1.319
 fighting-1.299
 wasteful-1.283
Token hopped
Token ID45230
Feature activation-2.15e+00

Pos logit contributions
iest+3.588
 oblig+3.137
anger+3.108
br+2.963
shirt+2.942
Neg logit contributions
 mess-3.642
 wasting-3.063
 ruining-2.988
 fighting-2.960
 wasteful-2.874
Token over
Token ID625
Feature activation-2.19e+00

Pos logit contributions
iest+4.711
 oblig+4.395
br+4.339
 armour+4.310
 powers+4.292
Neg logit contributions
 mess-3.335
 wasting-2.687
 ruining-2.665
 fighting-2.646
 wasteful-2.346
Token to
Token ID284
Feature activation-2.27e+00

Pos logit contributions
iest+4.514
int+4.287
br+4.249
 oblig+4.215
anger+4.042
Neg logit contributions
 mess-3.767
 fighting-3.127
 wasting-3.071
 ruining-3.001
 rats-2.668
Token take
Token ID1011
Feature activation-4.12e+00

Pos logit contributions
iest+5.363
br+5.100
anger+4.927
int+4.790
shirt+4.764
Neg logit contributions
 mess-3.454
 wasting-2.791
 fighting-2.647
 ruining-2.612
 yourselves-2.380
Token a
Token ID257
Feature activation-2.58e+00

Pos logit contributions
iest+9.165
anger+8.635
ute+8.396
ane+8.392
uttered+8.311
Neg logit contributions
 mess-6.640
 wasting-5.333
 mice-5.249
 fighting-5.201
 ruining-5.129
Token closer
Token ID5699
Feature activation-2.71e+00

Pos logit contributions
iest+4.528
anced+4.488
ests+4.227
 armour+4.219
 oblig+4.146
Neg logit contributions
 mess-5.571
 wasting-4.338
 fighting-4.307
 ruining-4.206
 wasteful-3.967
Token look
Token ID804
Feature activation-1.29e+00

Pos logit contributions
iest+4.290
ests+3.907
anced+3.904
 armour+3.882
 oblig+3.826
Neg logit contributions
 mess-6.120
 fighting-4.727
 ruining-4.674
 wasting-4.637
 fuss-4.387
Token.
Token ID13
Feature activation-1.80e+00

Pos logit contributions
 oblig+2.312
iest+2.282
 armour+2.188
br+2.107
 ti+2.102
Neg logit contributions
 mess-2.415
 wasting-2.010
 fighting-1.961
 ruining-1.952
 wasteful-1.886
Token
Token ID198
Feature activation-6.52e-01

Pos logit contributions
iest+3.487
 oblig+2.908
br+2.875
 ti+2.834
 armour+2.832
Neg logit contributions
 mess-3.379
 wasting-2.952
 fighting-2.913
 ruining-2.804
 wasteful-2.731
Token window
Token ID4324
Feature activation-9.45e-01

Pos logit contributions
 mess+0.930
 wasting+0.788
 ruining+0.761
 wasteful+0.759
 fighting+0.728
Neg logit contributions
iest-1.530
 armour-1.452
 oblig-1.434
anger-1.418
br-1.417
Token so
Token ID523
Feature activation-9.73e-01

Pos logit contributions
iest+1.685
 oblig+1.557
 armour+1.521
br+1.514
shirt+1.505
Neg logit contributions
 mess-1.820
 wasting-1.528
 ruining-1.522
 fighting-1.503
 wasteful-1.438
Token he
Token ID339
Feature activation-1.50e+00

Pos logit contributions
iest+1.893
 oblig+1.765
shirt+1.733
anger+1.722
 armour+1.707
Neg logit contributions
 mess-1.727
 wasting-1.454
 wasteful-1.413
 ruining-1.410
 fighting-1.387
Token went
Token ID1816
Feature activation-1.05e+00

Pos logit contributions
iest+2.777
 oblig+2.484
anger+2.449
shirt+2.386
br+2.363
Neg logit contributions
 mess-2.940
 wasting-2.465
 ruining-2.404
 fighting-2.387
 wasteful-2.356
Token to
Token ID284
Feature activation-1.16e+00

Pos logit contributions
iest+1.803
 oblig+1.604
 armour+1.571
int+1.567
br+1.563
Neg logit contributions
 mess-2.181
 wasting-1.854
 ruining-1.845
 fighting-1.807
 wasteful-1.725
Token take
Token ID1011
Feature activation-4.11e+00

Pos logit contributions
iest+2.090
br+1.859
anger+1.795
int+1.771
 armour+1.768
Neg logit contributions
 mess-2.372
 wasting-2.027
 ruining-1.983
 fighting-1.956
 wasteful-1.859
Token a
Token ID257
Feature activation-2.28e+00

Pos logit contributions
iest+9.328
anger+8.801
uttered+8.735
ided+8.341
ittered+8.340
Neg logit contributions
 mess-6.848
 ruining-5.515
 fighting-5.505
 yourselves-5.382
 wasting-5.377
Token look
Token ID804
Feature activation-1.72e+00

Pos logit contributions
iest+4.138
anced+3.968
 armour+3.695
 oblig+3.684
ment+3.656
Neg logit contributions
 mess-4.764
 wasting-3.775
 fighting-3.771
 ruining-3.729
 wasteful-3.444
Token.
Token ID13
Feature activation-1.93e+00

Pos logit contributions
 oblig+3.135
iest+3.044
 armour+2.895
br+2.864
anger+2.844
Neg logit contributions
 mess-3.225
 wasting-2.684
 fighting-2.621
 ruining-2.608
 wasteful-2.515
Token When
Token ID1649
Feature activation-1.20e+00

Pos logit contributions
iest+3.619
 oblig+2.972
br+2.920
 medal+2.891
 armour+2.850
Neg logit contributions
 mess-3.827
 wasting-3.359
 fighting-3.277
 ruining-3.207
 wasteful-3.130
Token he
Token ID339
Feature activation-2.25e+00

Pos logit contributions
iest+1.744
int+1.583
shirt+1.552
 oblig+1.528
anger+1.520
Neg logit contributions
 mess-2.719
 wasting-2.443
 ruining-2.394
 fighting-2.363
 wasteful-2.293
Token the
Token ID262
Feature activation-1.15e+00

Pos logit contributions
iest+0.912
 oblig+0.838
int+0.828
 armour+0.825
br+0.824
Neg logit contributions
 mess-0.718
 wasting-0.601
 ruining-0.590
 fighting-0.575
 wasteful-0.562
Token zip
Token ID19974
Feature activation+1.09e-01

Pos logit contributions
iest+1.696
 oblig+1.641
int+1.554
 armour+1.526
br+1.467
Neg logit contributions
 mess-2.641
 ruining-2.235
 wasting-2.232
 fighting-2.182
 wasteful-2.129
Token-
Token ID12
Feature activation-1.79e+00

Pos logit contributions
 mess+0.186
 wasting+0.159
 ruining+0.155
 wasteful+0.153
 fighting+0.151
Neg logit contributions
iest-0.211
 oblig-0.195
 armour-0.192
br-0.191
 ti-0.188
Tokenline
Token ID1370
Feature activation-3.02e-01

Pos logit contributions
iest+2.618
 oblig+2.469
 armour+2.402
 ti+2.313
 powers+2.302
Neg logit contributions
 mess-3.778
 wasting-3.287
 wasteful-3.241
 fighting-3.191
 ruining-3.183
Token and
Token ID290
Feature activation-3.97e-01

Pos logit contributions
iest+0.586
 oblig+0.542
 armour+0.536
br+0.535
 ti+0.525
Neg logit contributions
 mess-0.517
 wasting-0.438
 ruining-0.429
 fighting-0.422
 wasteful-0.416
Token z
Token ID1976
Feature activation-4.10e+00

Pos logit contributions
iest+0.653
 oblig+0.589
 armour+0.579
br+0.575
int+0.569
Neg logit contributions
 mess-0.816
 wasting-0.709
 ruining-0.700
 fighting-0.687
 wasteful-0.678
Tokenipped
Token ID3949
Feature activation-6.27e-01

Pos logit contributions
iest+6.271
 armour+6.248
 outer+6.077
shirt+6.019
 sail+5.959
Neg logit contributions
 mess-8.888
 yourselves-8.375
 fighting-8.271
 wasting-8.012
 ruining-7.999
Token around
Token ID1088
Feature activation-2.48e-01

Pos logit contributions
iest+1.167
 oblig+1.073
int+1.050
 armour+1.049
br+1.041
Neg logit contributions
 mess-1.158
 wasting-0.962
 ruining-0.959
 fighting-0.945
 wasteful-0.909
Token the
Token ID262
Feature activation-2.95e-01

Pos logit contributions
iest+0.436
 oblig+0.397
 armour+0.393
br+0.390
int+0.388
Neg logit contributions
 mess-0.478
 wasting-0.412
 ruining-0.407
 fighting-0.399
 wasteful-0.392
Token room
Token ID2119
Feature activation+1.48e-01

Pos logit contributions
iest+0.636
 oblig+0.596
 armour+0.581
br+0.577
int+0.575
Neg logit contributions
 mess-0.466
 wasting-0.379
 ruining-0.372
 fighting-0.361
 wasteful-0.359
Token,
Token ID11
Feature activation+1.06e+00

Pos logit contributions
 mess+0.311
 wasting+0.273
 ruining+0.268
 wasteful+0.265
 fighting+0.262
Neg logit contributions
iest-0.232
 oblig-0.209
 armour-0.205
br-0.204
 ti-0.201
Token it
Token ID340
Feature activation-1.38e+00

Pos logit contributions
iest+1.464
 oblig+1.290
anger+1.264
int+1.262
br+1.256
Neg logit contributions
 mess-1.904
 wasting-1.655
 ruining-1.627
 fighting-1.587
 wasteful-1.574
Token would
Token ID561
Feature activation-1.02e+00

Pos logit contributions
iest+2.225
 oblig+2.083
 armour+2.066
int+2.013
shirt+1.946
Neg logit contributions
 mess-2.918
 wasting-2.445
 ruining-2.431
 fighting-2.349
 wasteful-2.346
Token give
Token ID1577
Feature activation+6.29e-01

Pos logit contributions
iest+1.511
int+1.337
 oblig+1.314
 armour+1.313
anger+1.312
Neg logit contributions
 mess-2.291
 wasting-1.970
 ruining-1.961
 fighting-1.892
 wasteful-1.880
Token her
Token ID607
Feature activation-2.38e+00

Pos logit contributions
 mess+1.191
 wasting+1.043
 ruining+1.023
 wasteful+1.011
 fighting+0.988
Neg logit contributions
iest-1.111
 oblig-1.013
 armour-1.000
br-0.998
 ti-0.984
Token a
Token ID257
Feature activation-3.52e+00

Pos logit contributions
iest+4.350
 oblig+4.215
int+4.090
br+3.940
 armour+3.924
Neg logit contributions
 mess-4.790
 wasting-3.825
 ruining-3.749
 fighting-3.749
 wasteful-3.559
Token special
Token ID2041
Feature activation-4.10e+00

Pos logit contributions
iest+7.397
anced+7.287
ests+6.820
int+6.804
ment+6.789
Neg logit contributions
 mess-7.386
 wasting-4.979
 ruining-4.917
 mistake-4.779
 fighting-4.778
Token power
Token ID1176
Feature activation-1.74e+00

Pos logit contributions
anced+7.475
iest+7.434
 armour+7.386
 oblig+7.157
int+7.062
Neg logit contributions
 mess-9.880
 mistake-7.183
 fighting-6.631
 ruining-6.558
 floor-6.488
Token.
Token ID13
Feature activation+2.09e-01

Pos logit contributions
iest+2.976
 oblig+2.882
int+2.831
 armour+2.829
shirt+2.679
Neg logit contributions
 mess-3.477
 wasting-2.808
 ruining-2.795
 fighting-2.739
 wasteful-2.690
Token
Token ID198
Feature activation-2.96e-01

Pos logit contributions
 mess+0.451
 wasting+0.398
 ruining+0.392
 wasteful+0.386
 fighting+0.382
Neg logit contributions
iest-0.313
 oblig-0.283
 armour-0.278
br-0.276
 ti-0.270
Token
Token ID198
Feature activation+6.45e-01

Pos logit contributions
iest+0.471
 armour+0.424
 oblig+0.423
br+0.415
 ti+0.410
Neg logit contributions
 mess-0.607
 wasting-0.529
 ruining-0.517
 fighting-0.512
 wasteful-0.509
TokenOne
Token ID3198
Feature activation-1.52e+00

Pos logit contributions
 mess+1.267
 wasting+1.102
 ruining+1.090
 wasteful+1.073
 fighting+1.054
Neg logit contributions
iest-1.105
br-1.016
 oblig-1.013
 armour-0.997
shirt-0.985
Token.
Token ID13
Feature activation-1.85e-03

Pos logit contributions
 mess+0.089
 wasting+0.078
 ruining+0.076
 wasteful+0.075
 fighting+0.075
Neg logit contributions
iest-0.066
 oblig-0.060
 armour-0.059
br-0.059
 ti-0.058
Token She
Token ID1375
Feature activation-1.63e+00

Pos logit contributions
iest+0.004
 oblig+0.004
 armour+0.004
br+0.003
 ti+0.003
Neg logit contributions
 mess-0.003
 wasting-0.002
 ruining-0.002
 wasteful-0.002
 fighting-0.002
Token put
Token ID1234
Feature activation-2.76e+00

Pos logit contributions
iest+2.848
 oblig+2.583
anger+2.535
br+2.534
 armour+2.450
Neg logit contributions
 mess-3.333
 wasting-2.786
 fighting-2.762
 ruining-2.695
 wasteful-2.640
Token on
Token ID319
Feature activation-1.05e+00

Pos logit contributions
 oblig+5.221
iest+5.094
anger+4.948
 powers+4.840
br+4.830
Neg logit contributions
 mess-4.858
 wasting-4.304
 forth-4.164
 ruining-4.121
 fighting-4.112
Token her
Token ID607
Feature activation-3.48e+00

Pos logit contributions
iest+2.299
 oblig+2.114
int+2.067
br+2.048
anger+2.041
Neg logit contributions
 mess-1.673
 wasting-1.379
 ruining-1.349
 fighting-1.313
 wasteful-1.222
Token special
Token ID2041
Feature activation-4.09e+00

Pos logit contributions
iest+6.734
 oblig+6.359
anger+6.330
br+6.276
int+6.049
Neg logit contributions
 mess-7.124
 ruining-5.737
 fighting-5.701
 wasting-5.598
 yourselves-5.383
Token swimming
Token ID14899
Feature activation-3.70e+00

Pos logit contributions
iest+7.594
 oblig+7.223
anced+7.211
anger+7.117
int+7.071
Neg logit contributions
 mess-9.332
 ruining-7.049
 fighting-7.023
 mistake-6.632
 yourselves-6.626
Token helmet
Token ID14335
Feature activation-7.97e-01

Pos logit contributions
 oblig+7.323
iest+7.292
int+6.624
br+6.552
dot+6.490
Neg logit contributions
 mess-7.152
 ruining-5.393
 fighting-5.337
 yourselves-5.267
 floor-5.244
Token so
Token ID523
Feature activation-1.12e+00

Pos logit contributions
iest+1.709
 oblig+1.626
br+1.560
 armour+1.546
int+1.538
Neg logit contributions
 mess-1.204
 wasting-0.991
 ruining-0.979
 fighting-0.970
 wasteful-0.915
Token she
Token ID673
Feature activation-1.61e+00

Pos logit contributions
iest+2.281
 oblig+2.172
 armour+2.142
int+2.129
shirt+2.098
Neg logit contributions
 mess-1.780
 wasting-1.511
 ruining-1.451
 wasteful-1.444
 fighting-1.420
Token wouldn
Token ID3636
Feature activation-9.88e-01

Pos logit contributions
iest+2.670
 oblig+2.497
br+2.357
 armour+2.331
anger+2.322
Neg logit contributions
 mess-3.323
 wasting-2.821
 fighting-2.762
 ruining-2.747
 wasteful-2.707
Token impressed
Token ID12617
Feature activation+4.40e-01

Pos logit contributions
 mess+0.557
 wasting+0.478
 ruining+0.471
 wasteful+0.461
 fighting+0.455
Neg logit contributions
iest-0.574
 oblig-0.527
 armour-0.516
br-0.516
 ti-0.508
Token with
Token ID351
Feature activation-1.04e-01

Pos logit contributions
 mess+0.842
 wasting+0.730
 ruining+0.715
 wasteful+0.711
 fighting+0.690
Neg logit contributions
iest-0.781
 oblig-0.703
br-0.693
 armour-0.691
 ti-0.681
Token Mary
Token ID5335
Feature activation-7.73e-02

Pos logit contributions
iest+0.199
 oblig+0.183
 armour+0.181
br+0.180
 ti+0.178
Neg logit contributions
 mess-0.181
 wasting-0.155
 ruining-0.152
 wasteful-0.148
 fighting-0.148
Token and
Token ID290
Feature activation+2.25e-02

Pos logit contributions
iest+0.147
 oblig+0.135
 armour+0.134
br+0.133
 ti+0.131
Neg logit contributions
 mess-0.136
 wasting-0.116
 ruining-0.113
 wasteful-0.111
 fighting-0.110
Token her
Token ID607
Feature activation-2.98e+00

Pos logit contributions
 mess+0.042
 wasting+0.037
 ruining+0.036
 wasteful+0.035
 fighting+0.035
Neg logit contributions
iest-0.040
 oblig-0.037
 armour-0.036
br-0.036
 ti-0.035
Token special
Token ID2041
Feature activation-4.06e+00

Pos logit contributions
iest+5.599
br+5.491
int+5.489
anger+5.233
 oblig+5.220
Neg logit contributions
 mess-6.261
 fighting-4.912
 wasting-4.760
 ruining-4.718
 mistake-4.404
Token suit
Token ID6050
Feature activation-1.06e+00

Pos logit contributions
br+6.962
int+6.869
 oblig+6.816
anced+6.767
tie+6.611
Neg logit contributions
 mess-10.222
 mistake-7.648
 fighting-7.393
 fuss-7.136
 floor-7.009
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
iest+1.814
 oblig+1.711
 armour+1.690
int+1.658
shirt+1.642
Neg logit contributions
 mess-2.048
 wasting-1.725
 ruining-1.709
 fighting-1.692
 wasteful-1.640
Token
Token ID220
Feature activation+8.49e-02

Pos logit contributions
 mess+0.225
 wasting+0.198
 ruining+0.195
 wasteful+0.193
 fighting+0.191
Neg logit contributions
iest-0.157
 oblig-0.142
 armour-0.139
br-0.138
 ti-0.135
Token
Token ID198
Feature activation-1.16e-01

Pos logit contributions
 mess+0.182
 wasting+0.160
 ruining+0.157
 wasteful+0.155
 fighting+0.154
Neg logit contributions
iest-0.129
 oblig-0.116
 armour-0.114
br-0.113
 ti-0.111
Token
Token ID198
Feature activation+3.16e-01

Pos logit contributions
iest+0.180
 oblig+0.161
 armour+0.160
br+0.158
 ti+0.155
Neg logit contributions
 mess-0.244
 wasting-0.215
 ruining-0.210
 wasteful-0.207
 fighting-0.207
Token,
Token ID11
Feature activation-2.27e-01

Pos logit contributions
iest+0.263
 oblig+0.244
br+0.238
 armour+0.238
 ti+0.234
Neg logit contributions
 mess-0.238
 wasting-0.202
 ruining-0.197
 fighting-0.193
 wasteful-0.193
Token so
Token ID523
Feature activation-1.28e-01

Pos logit contributions
iest+0.546
 oblig+0.511
br+0.502
 armour+0.501
anger+0.497
Neg logit contributions
 mess-0.290
 wasting-0.233
 ruining-0.226
 fighting-0.218
 wasteful-0.217
Token he
Token ID339
Feature activation-1.45e+00

Pos logit contributions
iest+0.153
 oblig+0.134
br+0.131
 armour+0.130
anger+0.127
Neg logit contributions
 mess-0.316
 wasting-0.284
 ruining-0.279
 wasteful-0.275
 fighting-0.275
Token went
Token ID1816
Feature activation-1.38e+00

Pos logit contributions
iest+3.010
anger+2.652
 oblig+2.639
br+2.599
shirt+2.499
Neg logit contributions
 mess-2.489
 wasting-2.077
 ruining-2.045
 fighting-2.032
 wasteful-1.978
Token to
Token ID284
Feature activation-1.37e+00

Pos logit contributions
iest+2.592
br+2.337
 oblig+2.331
 armour+2.322
int+2.301
Neg logit contributions
 mess-2.588
 wasting-2.201
 ruining-2.188
 fighting-2.155
 wasteful-2.026
Token take
Token ID1011
Feature activation-4.05e+00

Pos logit contributions
iest+2.570
br+2.355
anger+2.223
int+2.211
 ti+2.201
Neg logit contributions
 mess-2.682
 wasting-2.308
 fighting-2.263
 ruining-2.237
 wasteful-2.074
Token a
Token ID257
Feature activation-2.33e+00

Pos logit contributions
iest+9.429
ests+8.819
anger+8.774
 ti+8.607
ute+8.498
Neg logit contributions
 mess-6.308
 fighting-5.334
 wasting-5.067
 ruining-5.026
 both-4.646
Token look
Token ID804
Feature activation-1.23e+00

Pos logit contributions
iest+4.046
anced+3.912
 oblig+3.718
 armour+3.678
ests+3.624
Neg logit contributions
 mess-4.963
 fighting-4.018
 wasting-3.972
 ruining-3.869
 wasteful-3.634
Token.
Token ID13
Feature activation-9.90e-01

Pos logit contributions
iest+2.107
 oblig+2.102
 armour+1.979
br+1.974
 ti+1.948
Neg logit contributions
 mess-2.347
 wasting-1.982
 fighting-1.937
 ruining-1.927
 wasteful-1.880
Token He
Token ID679
Feature activation-1.27e+00

Pos logit contributions
iest+1.585
br+1.381
 oblig+1.365
 armour+1.323
 ti+1.322
Neg logit contributions
 mess-2.114
 wasting-1.868
 fighting-1.833
 ruining-1.814
 wasteful-1.770
Token saw
Token ID2497
Feature activation-1.01e+00

Pos logit contributions
iest+2.524
br+2.236
 oblig+2.235
anger+2.214
 armour+2.128
Neg logit contributions
 mess-2.304
 wasting-1.927
 fighting-1.875
 ruining-1.867
 wasteful-1.823
Token.
Token ID13
Feature activation-2.28e+00

Pos logit contributions
iest+3.182
br+3.078
 oblig+3.077
 ti+2.986
 armour+2.985
Neg logit contributions
 mess-2.522
 wasting-2.102
 fighting-2.071
 ruining-1.948
 wasteful-1.924
Token Mike
Token ID4995
Feature activation-9.06e-01

Pos logit contributions
iest+3.849
 oblig+3.659
int+3.557
br+3.553
 powers+3.435
Neg logit contributions
 mess-4.704
 fighting-4.224
 ruining-4.073
 wasting-4.071
 yourselves-3.880
Token always
Token ID1464
Feature activation-1.24e+00

Pos logit contributions
iest+1.478
 oblig+1.380
br+1.343
anger+1.329
 armour+1.327
Neg logit contributions
 mess-1.868
 wasting-1.620
 fighting-1.585
 ruining-1.562
 wasteful-1.550
Token wore
Token ID12408
Feature activation-2.35e+00

Pos logit contributions
iest+2.128
anger+2.016
 oblig+1.981
 armour+1.980
br+1.944
Neg logit contributions
 mess-2.438
 wasting-2.122
 ruining-2.091
 fighting-2.073
 wasteful-2.034
Token his
Token ID465
Feature activation-3.47e+00

Pos logit contributions
iest+4.037
anger+3.726
int+3.655
 oblig+3.641
uttered+3.333
Neg logit contributions
 mess-4.986
 ruining-4.320
 wasting-4.305
 fighting-4.236
 yourselves-3.967
Token special
Token ID2041
Feature activation-4.03e+00

Pos logit contributions
iest+7.213
 oblig+6.765
int+6.739
anger+6.679
ided+6.539
Neg logit contributions
 mess-6.676
 ruining-5.250
 fighting-5.215
 wasting-4.977
 wasteful-4.617
Token uniform
Token ID8187
Feature activation-1.61e+00

Pos logit contributions
iest+7.411
 oblig+7.063
anced+6.918
uttered+6.857
int+6.848
Neg logit contributions
 mess-9.358
 ruining-6.970
 fighting-6.968
 floor-6.763
 mistake-6.690
Token every
Token ID790
Feature activation-2.63e+00

Pos logit contributions
iest+3.362
 oblig+3.280
br+3.114
int+3.110
 armour+3.001
Neg logit contributions
 mess-2.518
 wasting-2.073
 ruining-2.065
 fighting-2.050
 wasteful-1.945
Token day
Token ID1110
Feature activation-1.51e+00

Pos logit contributions
iest+4.962
int+4.823
anger+4.769
 oblig+4.715
anced+4.714
Neg logit contributions
 mess-4.908
 fighting-4.028
 wasting-3.979
 ruining-3.930
 wasteful-3.641
Token.
Token ID13
Feature activation-1.92e+00

Pos logit contributions
iest+2.836
 oblig+2.674
int+2.591
 armour+2.553
anger+2.538
Neg logit contributions
 mess-2.662
 fighting-2.328
 wasting-2.327
 ruining-2.300
 wasteful-2.126
Token One
Token ID1881
Feature activation-2.34e+00

Pos logit contributions
iest+3.536
 oblig+3.157
int+3.147
br+3.115
 armour+3.083
Neg logit contributions
 mess-3.621
 wasting-3.097
 fighting-3.092
 ruining-2.990
 yourselves-2.943
Token feeling
Token ID4203
Feature activation-1.21e+00

Pos logit contributions
 mess+1.054
 wasting+0.919
 ruining+0.904
 wasteful+0.903
 fighting+0.874
Neg logit contributions
iest-0.948
 oblig-0.880
 armour-0.853
br-0.846
 ti-0.845
Token very
Token ID845
Feature activation-7.25e-01

Pos logit contributions
iest+2.576
anger+2.472
int+2.408
 armour+2.400
 oblig+2.380
Neg logit contributions
 mess-1.882
 wasting-1.592
 wasteful-1.520
 ruining-1.511
 fighting-1.460
Token proud
Token ID6613
Feature activation-4.77e-01

Pos logit contributions
iest+1.478
 armour+1.368
anger+1.360
br+1.359
 oblig+1.358
Neg logit contributions
 mess-1.206
 wasting-1.013
 ruining-0.975
 wasteful-0.974
 fighting-0.948
Token wearing
Token ID5762
Feature activation-1.71e+00

Pos logit contributions
iest+0.766
 oblig+0.710
 armour+0.693
br+0.685
int+0.680
Neg logit contributions
 mess-0.979
 wasting-0.852
 ruining-0.835
 fighting-0.823
 wasteful-0.813
Token her
Token ID607
Feature activation-3.29e+00

Pos logit contributions
iest+3.614
int+3.445
 oblig+3.374
anger+3.354
br+3.239
Neg logit contributions
 mess-2.821
 wasting-2.264
 ruining-2.253
 fighting-2.118
 wasteful-2.100
Token special
Token ID2041
Feature activation-4.03e+00

Pos logit contributions
iest+6.448
anced+6.096
br+6.096
anger+6.057
 oblig+6.056
Neg logit contributions
 mess-6.753
 ruining-5.160
 fighting-5.157
 wasting-5.090
 wasteful-4.689
Token suit
Token ID6050
Feature activation-9.44e-01

Pos logit contributions
iest+6.788
anced+6.787
uttered+6.712
br+6.635
 oblig+6.606
Neg logit contributions
 mess-10.037
 mistake-7.515
 fighting-7.311
 ruining-7.191
 wasting-6.840
Token.
Token ID13
Feature activation-5.40e-01

Pos logit contributions
iest+1.704
 oblig+1.607
 armour+1.566
br+1.550
int+1.540
Neg logit contributions
 mess-1.743
 wasting-1.460
 ruining-1.446
 fighting-1.421
 wasteful-1.385
Token She
Token ID1375
Feature activation-8.72e-01

Pos logit contributions
iest+0.934
 armour+0.829
 oblig+0.825
br+0.821
int+0.802
Neg logit contributions
 mess-1.051
 wasting-0.927
 ruining-0.895
 fighting-0.887
 wasteful-0.885
Token will
Token ID481
Feature activation-1.07e+00

Pos logit contributions
iest+1.677
anger+1.509
 oblig+1.505
 armour+1.504
br+1.498
Neg logit contributions
 mess-1.582
 wasting-1.330
 ruining-1.287
 fighting-1.258
 wasteful-1.256
Token never
Token ID1239
Feature activation+4.94e-01

Pos logit contributions
iest+2.621
int+2.460
shirt+2.450
anger+2.444
 armour+2.442
Neg logit contributions
 mess-1.292
 wasting-1.016
 ruining-0.985
 fighting-0.925
 wasteful-0.896
Token a
Token ID257
Feature activation-1.39e+00

Pos logit contributions
iest+3.605
 oblig+3.591
int+3.418
anger+3.314
 armour+3.168
Neg logit contributions
 mess-3.617
 wasting-3.180
 ruining-3.046
 fighting-2.985
 yourselves-2.891
Token zipper
Token ID48992
Feature activation-1.07e+00

Pos logit contributions
iest+2.262
 oblig+2.110
int+1.985
anced+1.921
anger+1.914
Neg logit contributions
 mess-3.071
 wasting-2.520
 ruining-2.497
 fighting-2.480
 wasteful-2.389
Token that
Token ID326
Feature activation-1.64e+00

Pos logit contributions
iest+1.792
 oblig+1.750
 armour+1.648
int+1.616
br+1.591
Neg logit contributions
 mess-2.127
 wasting-1.840
 ruining-1.814
 fighting-1.808
 wasteful-1.707
Token she
Token ID673
Feature activation-2.23e+00

Pos logit contributions
iest+3.601
int+3.551
 oblig+3.506
 armour+3.467
br+3.296
Neg logit contributions
 mess-2.428
 wasting-1.932
 ruining-1.906
 wasteful-1.828
 fighting-1.825
Token loved
Token ID6151
Feature activation-1.21e+00

Pos logit contributions
iest+4.133
 oblig+3.977
anger+3.829
int+3.736
br+3.732
Neg logit contributions
 mess-4.203
 wasting-3.580
 ruining-3.493
 wasteful-3.429
 fighting-3.352
Token to
Token ID284
Feature activation-4.02e+00

Pos logit contributions
iest+2.236
 oblig+2.128
int+2.110
br+1.992
 armour+1.988
Neg logit contributions
 mess-2.281
 wasting-1.949
 ruining-1.947
 fighting-1.925
 wasteful-1.824
Token play
Token ID711
Feature activation-1.65e+00

Pos logit contributions
iest+7.805
anger+7.197
br+7.164
 oblig+7.012
ment+6.816
Neg logit contributions
 mess-8.529
 forth-6.641
 wasting-6.413
 ruining-6.407
 fighting-6.389
Token with
Token ID351
Feature activation-5.33e-01

Pos logit contributions
iest+3.468
 oblig+3.329
int+3.275
anced+3.150
 armour+3.112
Neg logit contributions
 mess-2.720
 ruining-2.238
 fighting-2.189
 wasting-2.152
 yourselves-2.019
Token.
Token ID13
Feature activation+4.14e-01

Pos logit contributions
iest+0.902
 oblig+0.843
 armour+0.808
int+0.806
br+0.804
Neg logit contributions
 mess-1.060
 wasting-0.916
 ruining-0.902
 fighting-0.887
 wasteful-0.880
Token One
Token ID1881
Feature activation-1.58e+00

Pos logit contributions
 mess+0.897
 wasting+0.798
 ruining+0.788
 wasteful+0.775
 fighting+0.762
Neg logit contributions
iest-0.616
 oblig-0.557
 armour-0.550
br-0.547
 ti-0.543
Token day
Token ID1110
Feature activation-7.32e-01

Pos logit contributions
iest+2.627
 oblig+2.612
 armour+2.558
anger+2.518
br+2.509
Neg logit contributions
 mess-3.182
 wasting-2.652
 fighting-2.569
 wasteful-2.537
 ruining-2.511
Token her
Token ID607
Feature activation-1.78e+00

Pos logit contributions
iest+1.156
 armour+1.092
 oblig+1.077
int+1.052
anger+1.033
Neg logit contributions
 mess-1.170
 wasting-0.991
 ruining-0.971
 fighting-0.965
 wasteful-0.953
Token mum
Token ID25682
Feature activation-1.62e-01

Pos logit contributions
iest+3.967
 armour+3.777
 oblig+3.735
br+3.699
shirt+3.656
Neg logit contributions
 mess-2.841
 wasting-2.193
 fighting-2.189
 ruining-2.069
 wasteful-2.014
Token put
Token ID1234
Feature activation-1.31e+00

Pos logit contributions
iest+0.241
 oblig+0.217
 armour+0.215
br+0.211
anger+0.208
Neg logit contributions
 mess-0.350
 wasting-0.309
 ruining-0.302
 wasteful-0.299
 fighting-0.297
Token on
Token ID319
Feature activation-2.20e-01

Pos logit contributions
iest+2.344
 oblig+2.182
 armour+2.129
anger+2.116
br+2.109
Neg logit contributions
 mess-2.461
 wasting-2.162
 ruining-2.080
 fighting-2.061
 wasteful-2.045
Token her
Token ID607
Feature activation-3.17e+00

Pos logit contributions
iest+0.394
 oblig+0.358
 armour+0.353
br+0.350
int+0.345
Neg logit contributions
 mess-0.418
 wasting-0.362
 ruining-0.353
 wasteful-0.346
 fighting-0.345
Token special
Token ID2041
Feature activation-4.01e+00

Pos logit contributions
iest+6.584
 oblig+5.904
br+5.885
anger+5.852
anced+5.832
Neg logit contributions
 mess-6.120
 wasting-4.992
 fighting-4.863
 ruining-4.795
 wasteful-4.590
Token clothes
Token ID8242
Feature activation-7.23e-01

Pos logit contributions
iest+8.123
anced+7.634
uttered+7.485
 oblig+7.448
int+7.301
Neg logit contributions
 mess-8.743
 ruining-6.438
 fighting-6.278
 wasting-6.198
 floor-6.081
Token and
Token ID290
Feature activation-5.82e-01

Pos logit contributions
iest+1.419
 oblig+1.335
 armour+1.310
br+1.297
int+1.277
Neg logit contributions
 mess-1.222
 wasting-1.029
 ruining-1.003
 fighting-1.000
 wasteful-0.976
Token said
Token ID531
Feature activation-1.55e+00

Pos logit contributions
iest+1.008
 oblig+0.919
 armour+0.907
br+0.897
anger+0.895
Neg logit contributions
 mess-1.137
 wasting-0.981
 ruining-0.952
 wasteful-0.939
 fighting-0.935
Token to
Token ID284
Feature activation+4.09e-01

Pos logit contributions
iest+2.815
 armour+2.718
int+2.646
 oblig+2.589
shirt+2.572
Neg logit contributions
 mess-2.845
 wasting-2.473
 fighting-2.420
 ruining-2.379
 wasteful-2.365
Token her
Token ID607
Feature activation-1.97e+00

Pos logit contributions
 mess+0.731
 wasting+0.628
 ruining+0.617
 wasteful+0.607
 fighting+0.600
Neg logit contributions
iest-0.764
 oblig-0.710
 armour-0.694
br-0.688
 ti-0.688
Token.
Token ID13
Feature activation-1.08e+00

Pos logit contributions
iest+0.074
 oblig+0.068
 armour+0.067
br+0.066
 ti+0.065
Neg logit contributions
 mess-0.091
 wasting-0.080
 ruining-0.078
 wasteful-0.077
 fighting-0.077
Token He
Token ID679
Feature activation-1.02e+00

Pos logit contributions
iest+1.618
 oblig+1.376
br+1.364
 armour+1.313
 ti+1.306
Neg logit contributions
 mess-2.401
 wasting-2.169
 fighting-2.104
 ruining-2.098
 wasteful-2.077
Token walked
Token ID6807
Feature activation-1.49e+00

Pos logit contributions
iest+1.910
 oblig+1.694
anger+1.685
br+1.662
 armour+1.638
Neg logit contributions
 mess-1.921
 wasting-1.631
 fighting-1.599
 ruining-1.589
 wasteful-1.548
Token over
Token ID625
Feature activation-1.67e+00

Pos logit contributions
iest+2.835
br+2.586
 oblig+2.586
anger+2.483
int+2.482
Neg logit contributions
 mess-2.665
 fighting-2.265
 ruining-2.243
 wasting-2.243
 wasteful-2.109
Token to
Token ID284
Feature activation-2.18e+00

Pos logit contributions
iest+3.162
int+2.907
 oblig+2.896
br+2.863
anger+2.797
Neg logit contributions
 mess-3.028
 fighting-2.621
 wasting-2.559
 ruining-2.525
 wasteful-2.332
Token take
Token ID1011
Feature activation-4.01e+00

Pos logit contributions
iest+4.693
br+4.579
anger+4.340
int+4.223
 armour+4.214
Neg logit contributions
 mess-3.560
 wasting-3.025
 fighting-2.964
 ruining-2.856
 yourselves-2.685
Token a
Token ID257
Feature activation-2.49e+00

Pos logit contributions
iest+9.396
ests+8.906
anger+8.717
ipop+8.560
int+8.540
Neg logit contributions
 mess-6.062
 fighting-4.796
 wasting-4.571
 ruining-4.539
 yourselves-4.396
Token closer
Token ID5699
Feature activation-2.43e+00

Pos logit contributions
iest+4.168
anced+4.092
ests+3.971
 armour+3.884
 oblig+3.835
Neg logit contributions
 mess-5.498
 fighting-4.390
 wasting-4.323
 ruining-4.203
 wasteful-3.973
Token look
Token ID804
Feature activation-9.68e-01

Pos logit contributions
iest+3.706
 armour+3.379
 oblig+3.332
ests+3.283
anced+3.265
Neg logit contributions
 mess-5.511
 fighting-4.438
 ruining-4.328
 wasting-4.286
 forth-4.016
Token.
Token ID13
Feature activation-1.30e+00

Pos logit contributions
iest+1.820
 oblig+1.776
 armour+1.704
br+1.667
int+1.656
Neg logit contributions
 mess-1.720
 wasting-1.428
 ruining-1.396
 fighting-1.389
 wasteful-1.351
Token It
Token ID632
Feature activation-8.78e-01

Pos logit contributions
iest+2.164
 oblig+1.830
br+1.829
 armour+1.789
 ti+1.777
Neg logit contributions
 mess-2.691
 wasting-2.430
 fighting-2.370
 ruining-2.343
 wasteful-2.294
Token I
Token ID314
Feature activation-1.59e+00

Pos logit contributions
 mess+0.880
 wasting+0.750
 ruining+0.734
 wasteful+0.724
 fighting+0.711
Neg logit contributions
iest-1.012
 oblig-0.932
 armour-0.920
br-0.919
 ti-0.908
Token will
Token ID481
Feature activation-1.24e+00

Pos logit contributions
iest+2.880
 armour+2.765
shirt+2.682
anger+2.662
br+2.632
Neg logit contributions
 mess-3.056
 wasting-2.490
 wasteful-2.434
 fighting-2.427
 ruining-2.405
Token give
Token ID1577
Feature activation+1.07e+00

Pos logit contributions
iest+2.194
shirt+2.003
 armour+1.994
anger+1.975
int+1.969
Neg logit contributions
 mess-2.432
 wasting-2.093
 ruining-2.069
 fighting-2.024
 wasteful-1.944
Token you
Token ID345
Feature activation-1.26e+00

Pos logit contributions
 mess+1.762
 wasting+1.473
 ruining+1.442
 wasteful+1.408
 fighting+1.363
Neg logit contributions
iest-2.183
 oblig-2.022
shirt-1.980
 armour-1.975
br-1.961
Token a
Token ID257
Feature activation-3.64e+00

Pos logit contributions
iest+2.360
 oblig+2.195
anger+2.169
br+2.145
int+2.126
Neg logit contributions
 mess-2.251
 wasting-1.931
 wasteful-1.861
 ruining-1.855
 fighting-1.817
Token magic
Token ID5536
Feature activation-4.00e+00

Pos logit contributions
iest+7.582
anced+7.291
ittered+6.972
int+6.912
ment+6.852
Neg logit contributions
 mess-7.641
 mistake-5.496
 wasteful-5.267
 wasting-5.218
 fighting-5.154
Token pen
Token ID3112
Feature activation-6.59e-01

Pos logit contributions
 oblig+6.696
anced+6.647
uttered+6.609
rolled+6.333
ittered+6.328
Neg logit contributions
 mess-10.021
 mistake-7.203
 fighting-6.944
 ruining-6.868
 wasteful-6.766
Token that
Token ID326
Feature activation-9.11e-02

Pos logit contributions
iest+1.225
 oblig+1.144
 armour+1.125
int+1.114
br+1.102
Neg logit contributions
 mess-1.175
 wasting-0.986
 ruining-0.971
 fighting-0.946
 wasteful-0.946
Token will
Token ID481
Feature activation+1.78e-01

Pos logit contributions
iest+0.157
 oblig+0.144
 armour+0.142
br+0.140
 ti+0.138
Neg logit contributions
 mess-0.176
 wasting-0.153
 ruining-0.150
 wasteful-0.148
 fighting-0.146
Token make
Token ID787
Feature activation+1.12e+00

Pos logit contributions
 mess+0.368
 wasting+0.323
 ruining+0.317
 wasteful+0.314
 fighting+0.311
Neg logit contributions
iest-0.283
 oblig-0.256
 armour-0.251
br-0.250
 ti-0.246
Token your
Token ID534
Feature activation-6.66e-01

Pos logit contributions
 mess+1.427
 wasting+1.175
 ruining+1.154
 wasteful+1.137
 fighting+1.087
Neg logit contributions
iest-2.639
 oblig-2.459
br-2.446
 armour-2.409
 powers-2.385
Token snacks
Token ID28487
Feature activation+3.70e-01

Pos logit contributions
iest+0.594
 oblig+0.553
 armour+0.542
br+0.533
anger+0.531
Neg logit contributions
 mess-0.602
 wasting-0.508
 ruining-0.498
 fighting-0.486
 wasteful-0.485
Token.
Token ID13
Feature activation+1.15e+00

Pos logit contributions
 mess+0.794
 wasting+0.700
 ruining+0.688
 wasteful+0.681
 fighting+0.671
Neg logit contributions
iest-0.568
 oblig-0.504
 armour-0.497
br-0.496
 ti-0.489
Token One
Token ID1881
Feature activation+7.99e-02

Pos logit contributions
 mess+2.808
 wasting+2.532
 ruining+2.528
 wasteful+2.485
 fighting+2.394
Neg logit contributions
iest-1.343
shirt-1.239
 oblig-1.233
 ti-1.228
 armour-1.220
Token day
Token ID1110
Feature activation-1.05e+00

Pos logit contributions
 mess+0.184
 wasting+0.163
 ruining+0.161
 wasteful+0.159
 fighting+0.157
Neg logit contributions
iest-0.111
 oblig-0.098
 armour-0.097
br-0.096
 ti-0.094
Token,
Token ID11
Feature activation+9.00e-01

Pos logit contributions
iest+1.888
 armour+1.791
 oblig+1.746
shirt+1.703
int+1.700
Neg logit contributions
 mess-1.986
 wasting-1.728
 fighting-1.706
 ruining-1.687
 wasteful-1.617
Token Lily
Token ID20037
Feature activation+2.10e+00

Pos logit contributions
 mess+1.523
 wasting+1.287
 ruining+1.267
 wasteful+1.262
 fighting+1.203
Neg logit contributions
iest-1.771
 ti-1.631
 oblig-1.628
br-1.623
 armour-1.598
Token's
Token ID338
Feature activation+2.37e-01

Pos logit contributions
 mess+4.239
 ruining+4.042
 wasteful+3.989
 wasting+3.972
 yourselves+3.841
Neg logit contributions
iest-3.053
 shone-2.870
int-2.856
 ti-2.844
shirt-2.833
Token mom
Token ID1995
Feature activation+2.01e+00

Pos logit contributions
 mess+0.394
 wasting+0.335
 ruining+0.328
 wasteful+0.323
 fighting+0.317
Neg logit contributions
iest-0.475
 oblig-0.438
 armour-0.434
br-0.430
 ti-0.426
Token asked
Token ID1965
Feature activation+4.03e-01

Pos logit contributions
 mess+4.236
 ruining+3.912
 yourselves+3.874
 wasteful+3.866
 wasting+3.810
Neg logit contributions
iest-2.976
 oblig-2.711
 shone-2.686
int-2.660
shirt-2.556
Token her
Token ID607
Feature activation+7.37e-02

Pos logit contributions
 mess+0.732
 wasting+0.627
 ruining+0.617
 wasteful+0.607
 fighting+0.595
Neg logit contributions
iest-0.743
 oblig-0.688
 armour-0.672
br-0.669
shirt-0.664
Token to
Token ID284
Feature activation-5.78e-01

Pos logit contributions
 mess+0.165
 wasting+0.146
 ruining+0.144
 wasteful+0.142
 fighting+0.141
Neg logit contributions
iest-0.106
 oblig-0.095
 armour-0.094
br-0.093
 ti-0.091
Token it
Token ID340
Feature activation+2.70e-01

Pos logit contributions
iest+2.055
 oblig+1.971
int+1.922
br+1.899
 armour+1.843
Neg logit contributions
 mess-2.129
 wasting-1.810
 ruining-1.802
 fighting-1.767
 wasteful-1.712
Token.
Token ID13
Feature activation+3.83e-01

Pos logit contributions
 mess+0.569
 wasting+0.501
 ruining+0.492
 wasteful+0.488
 fighting+0.479
Neg logit contributions
iest-0.422
 oblig-0.375
 armour-0.372
br-0.368
 ti-0.362
Token
Token ID220
Feature activation+1.11e-01

Pos logit contributions
 mess+0.860
 wasting+0.764
 ruining+0.753
 wasteful+0.742
 fighting+0.729
Neg logit contributions
iest-0.538
 oblig-0.484
 armour-0.477
br-0.471
shirt-0.467
Token
Token ID198
Feature activation+2.58e-01

Pos logit contributions
 mess+0.238
 wasting+0.209
 ruining+0.206
 wasteful+0.203
 fighting+0.201
Neg logit contributions
iest-0.167
 oblig-0.150
 armour-0.148
br-0.146
 ti-0.144
Token
Token ID198
Feature activation+6.92e-01

Pos logit contributions
 mess+0.563
 wasting+0.499
 ruining+0.491
 wasteful+0.484
 fighting+0.478
Neg logit contributions
iest-0.382
 oblig-0.342
 armour-0.335
br-0.334
shirt-0.328
TokenTim
Token ID14967
Feature activation+2.25e+00

Pos logit contributions
 mess+1.204
 wasting+1.040
 ruining+1.020
 wasteful+0.991
 fighting+0.976
Neg logit contributions
iest-1.328
br-1.218
shirt-1.214
 armour-1.213
 oblig-1.209
Tokenmy
Token ID1820
Feature activation+1.43e+00

Pos logit contributions
 mess+3.001
 wasting+2.807
 ruining+2.702
 wasteful+2.688
 yourselves+2.578
Neg logit contributions
iest-4.967
int-4.875
ah-4.811
shirt-4.806
 armour-4.778
Token thought
Token ID1807
Feature activation-9.12e-01

Pos logit contributions
 mess+2.858
 wasting+2.565
 ruining+2.536
 wasteful+2.512
 yourselves+2.411
Neg logit contributions
iest-2.178
int-2.147
 armour-2.141
 oblig-2.091
 sail-2.058
Token that
Token ID326
Feature activation+5.71e-01

Pos logit contributions
iest+1.738
 oblig+1.626
int+1.579
 armour+1.568
br+1.565
Neg logit contributions
 mess-1.682
 wasting-1.416
 ruining-1.384
 fighting-1.361
 wasteful-1.342
Token maybe
Token ID3863
Feature activation-1.03e+00

Pos logit contributions
 mess+1.292
 wasting+1.152
 ruining+1.141
 wasteful+1.133
 fighting+1.108
Neg logit contributions
iest-0.796
 oblig-0.691
 armour-0.687
br-0.686
 ti-0.676
Token his
Token ID465
Feature activation-5.32e-02

Pos logit contributions
iest+1.704
int+1.589
 oblig+1.587
br+1.540
shirt+1.537
Neg logit contributions
 mess-2.102
 wasting-1.846
 ruining-1.813
 fighting-1.793
 wasteful-1.746
Token of
Token ID286
Feature activation+1.29e+00

Pos logit contributions
 mess+2.434
 wasting+2.188
 ruining+2.164
 wasteful+2.136
 fighting+2.108
Neg logit contributions
iest-1.254
br-1.030
 oblig-1.016
 armour-0.976
shirt-0.972
Token your
Token ID534
Feature activation+8.02e-01

Pos logit contributions
 mess+2.307
 wasting+1.951
 wasteful+1.925
 ruining+1.924
 fighting+1.847
Neg logit contributions
iest-2.384
 oblig-2.166
 armour-2.163
 powers-2.133
br-2.120
Token life
Token ID1204
Feature activation+1.13e+00

Pos logit contributions
 mess+1.593
 wasting+1.424
 ruining+1.394
 wasteful+1.377
 fighting+1.348
Neg logit contributions
iest-1.295
 oblig-1.193
 armour-1.187
 ti-1.152
br-1.146
Token."
Token ID526
Feature activation+1.34e+00

Pos logit contributions
 mess+2.038
 wasting+1.802
 ruining+1.762
 wasteful+1.742
 fighting+1.692
Neg logit contributions
iest-2.117
 oblig-1.871
br-1.869
 armour-1.854
 ti-1.837
Token
Token ID198
Feature activation+7.02e-01

Pos logit contributions
 mess+3.136
 wasting+2.843
 ruining+2.828
 wasteful+2.804
 fighting+2.716
Neg logit contributions
iest-1.694
 oblig-1.627
 armour-1.564
shirt-1.537
 ti-1.526
Token
Token ID198
Feature activation+1.93e+00

Pos logit contributions
 mess+1.591
 wasting+1.428
 ruining+1.416
 wasteful+1.395
 fighting+1.373
Neg logit contributions
iest-0.965
 oblig-0.886
br-0.861
 armour-0.847
 ti-0.834
TokenAlice
Token ID44484
Feature activation+2.74e-01

Pos logit contributions
 mess+3.748
 wasting+3.344
 ruining+3.324
 fighting+3.249
 wasteful+3.182
Neg logit contributions
iest-3.362
br-3.267
 oblig-3.170
shirt-3.133
 farewell-3.072
Token yelled
Token ID22760
Feature activation-8.83e-02

Pos logit contributions
 mess+0.570
 wasting+0.501
 ruining+0.493
 wasteful+0.485
 fighting+0.478
Neg logit contributions
iest-0.430
 oblig-0.391
 armour-0.383
br-0.380
 ti-0.375
Token even
Token ID772
Feature activation+1.68e+00

Pos logit contributions
iest+0.147
 oblig+0.132
 armour+0.131
br+0.130
 ti+0.127
Neg logit contributions
 mess-0.178
 wasting-0.155
 ruining-0.153
 fighting-0.150
 wasteful-0.150
Token louder
Token ID27089
Feature activation+1.85e-01

Pos logit contributions
 mess+2.710
 wasting+2.353
 ruining+2.323
 yourselves+2.230
 wasteful+2.193
Neg logit contributions
iest-3.331
 oblig-3.117
 armour-3.109
int-3.049
shirt-3.045
Token,
Token ID11
Feature activation+1.52e+00

Pos logit contributions
 mess+0.365
 wasting+0.317
 ruining+0.311
 wasteful+0.307
 fighting+0.303
Neg logit contributions
iest-0.316
 oblig-0.287
 armour-0.283
br-0.281
 ti-0.276
Token and
Token ID290
Feature activation+9.32e-01

Pos logit contributions
 mess+3.630
 wasteful+3.257
 wasting+3.212
 ruining+3.160
 fighting+2.970
Neg logit contributions
iest-2.571
br-2.220
 armour-2.211
 ti-2.143
anger-2.134
Token about
Token ID546
Feature activation+4.07e-01

Pos logit contributions
 mess+1.909
 wasting+1.658
 wasteful+1.617
 ruining+1.616
 fighting+1.570
Neg logit contributions
iest-1.458
 oblig-1.344
 armour-1.330
 ti-1.302
 sail-1.287
Token to
Token ID284
Feature activation-4.01e-01

Pos logit contributions
 mess+0.766
 wasting+0.661
 ruining+0.646
 wasteful+0.645
 fighting+0.626
Neg logit contributions
iest-0.715
 oblig-0.656
 armour-0.649
br-0.639
 ti-0.637
Token run
Token ID1057
Feature activation+3.03e-01

Pos logit contributions
iest+0.671
br+0.596
 oblig+0.592
 armour+0.591
shirt+0.583
Neg logit contributions
 mess-0.818
 wasting-0.712
 ruining-0.703
 fighting-0.685
 wasteful-0.680
Token away
Token ID1497
Feature activation+8.71e-01

Pos logit contributions
 mess+0.561
 wasting+0.487
 ruining+0.474
 wasteful+0.470
 fighting+0.461
Neg logit contributions
iest-0.549
 oblig-0.501
 armour-0.497
br-0.493
 ti-0.485
Token,
Token ID11
Feature activation+1.92e+00

Pos logit contributions
 mess+1.900
 wasting+1.692
 wasteful+1.674
 ruining+1.646
 fighting+1.607
Neg logit contributions
iest-1.289
 oblig-1.134
 armour-1.115
br-1.110
 ti-1.107
Token but
Token ID475
Feature activation+7.13e-01

Pos logit contributions
 mess+3.043
 wasteful+2.647
 wasting+2.557
 ruining+2.415
 yourselves+2.349
Neg logit contributions
iest-3.715
 ti-3.580
 armour-3.552
 sail-3.546
 oblig-3.524
Token then
Token ID788
Feature activation-4.92e-01

Pos logit contributions
 mess+1.255
 wasting+1.047
 ruining+1.023
 wasteful+1.013
 fighting+0.987
Neg logit contributions
iest-1.373
 oblig-1.261
 armour-1.250
 ti-1.237
br-1.229
Token she
Token ID673
Feature activation-6.40e-01

Pos logit contributions
iest+1.021
 oblig+0.942
 armour+0.931
shirt+0.923
br+0.922
Neg logit contributions
 mess-0.791
 wasting-0.667
 ruining-0.650
 fighting-0.635
 wasteful-0.633
Token heard
Token ID2982
Feature activation-1.66e+00

Pos logit contributions
iest+1.213
 oblig+1.101
anger+1.075
 armour+1.075
br+1.072
Neg logit contributions
 mess-1.169
 wasting-0.982
 ruining-0.965
 fighting-0.953
 wasteful-0.945
Token a
Token ID257
Feature activation-4.07e-01

Pos logit contributions
iest+2.883
 oblig+2.573
int+2.548
 armour+2.497
anger+2.497
Neg logit contributions
 mess-3.351
 wasting-2.924
 ruining-2.855
 fighting-2.853
 wasteful-2.763
Token took
Token ID1718
Feature activation-3.75e-01

Pos logit contributions
 mess+0.050
 wasting+0.043
 ruining+0.043
 wasteful+0.042
 fighting+0.042
Neg logit contributions
iest-0.038
 oblig-0.034
 armour-0.033
br-0.033
 ti-0.033
Token the
Token ID262
Feature activation+2.19e-01

Pos logit contributions
iest+0.723
 oblig+0.659
 armour+0.652
br+0.651
 ti+0.648
Neg logit contributions
 mess-0.655
 wasting-0.560
 ruining-0.548
 fighting-0.541
 wasteful-0.538
Token pig
Token ID12967
Feature activation+6.30e-01

Pos logit contributions
 mess+0.440
 wasting+0.385
 ruining+0.379
 wasteful+0.373
 fighting+0.369
Neg logit contributions
iest-0.368
 oblig-0.332
 armour-0.328
br-0.326
 ti-0.320
Token to
Token ID284
Feature activation-3.41e-01

Pos logit contributions
 mess+1.365
 wasting+1.216
 ruining+1.196
 wasteful+1.185
 fighting+1.151
Neg logit contributions
iest-0.927
 oblig-0.830
 armour-0.829
br-0.807
shirt-0.802
Token the
Token ID262
Feature activation+1.78e+00

Pos logit contributions
iest+0.617
br+0.551
 armour+0.546
 oblig+0.546
int+0.542
Neg logit contributions
 mess-0.652
 wasting-0.564
 ruining-0.552
 fighting-0.541
 wasteful-0.539
Token other
Token ID584
Feature activation+2.11e+00

Pos logit contributions
 mess+3.213
 wasting+2.861
 ruining+2.804
 fighting+2.741
 wasteful+2.723
Neg logit contributions
iest-3.051
 armour-2.999
 sail-2.959
 oblig-2.924
 medal-2.871
Token side
Token ID1735
Feature activation+6.94e-01

Pos logit contributions
 mess+3.864
 wasting+3.431
 ruining+3.407
 wasteful+3.397
 fighting+3.262
Neg logit contributions
iest-3.945
 armour-3.585
 oblig-3.534
 sail-3.510
br-3.458
Token of
Token ID286
Feature activation+5.42e-01

Pos logit contributions
 mess+1.683
 wasting+1.511
 ruining+1.495
 wasteful+1.476
 fighting+1.440
Neg logit contributions
iest-0.879
 oblig-0.765
 armour-0.743
shirt-0.726
br-0.721
Token the
Token ID262
Feature activation+2.02e+00

Pos logit contributions
 mess+0.965
 wasting+0.823
 ruining+0.808
 wasteful+0.805
 fighting+0.781
Neg logit contributions
iest-1.014
 oblig-0.941
 armour-0.936
br-0.918
 ti-0.902
Token farm
Token ID5318
Feature activation+8.27e-01

Pos logit contributions
 mess+3.736
 wasting+3.440
 ruining+3.424
 wasteful+3.323
 fighting+3.312
Neg logit contributions
iest-3.354
 armour-3.306
br-3.300
 sail-3.263
 oblig-3.234
Token and
Token ID290
Feature activation+1.02e+00

Pos logit contributions
 mess+1.812
 wasting+1.615
 ruining+1.598
 wasteful+1.583
 fighting+1.527
Neg logit contributions
iest-1.183
 oblig-1.073
 armour-1.054
 ti-1.022
 sail-1.018
Token to
Token ID284
Feature activation-4.66e-01

Pos logit contributions
 mess+0.336
 wasting+0.292
 ruining+0.287
 wasteful+0.283
 fighting+0.280
Neg logit contributions
iest-0.284
 oblig-0.258
 armour-0.254
br-0.253
 ti-0.249
Token close
Token ID1969
Feature activation+5.71e-01

Pos logit contributions
iest+0.739
br+0.651
 armour+0.648
 oblig+0.644
anger+0.641
Neg logit contributions
 mess-0.980
 wasting-0.858
 ruining-0.847
 fighting-0.829
 wasteful-0.822
Token their
Token ID511
Feature activation+4.88e-01

Pos logit contributions
 mess+1.042
 wasting+0.902
 ruining+0.878
 wasteful+0.872
 fighting+0.847
Neg logit contributions
iest-1.045
 oblig-0.957
 armour-0.950
br-0.927
 ti-0.926
Token eyes
Token ID2951
Feature activation+3.62e-01

Pos logit contributions
 mess+0.923
 wasting+0.816
 ruining+0.791
 wasteful+0.787
 fighting+0.769
Neg logit contributions
iest-0.842
 oblig-0.775
 armour-0.774
br-0.756
shirt-0.753
Token and
Token ID290
Feature activation+2.66e-01

Pos logit contributions
 mess+0.625
 wasting+0.537
 ruining+0.526
 wasteful+0.517
 fighting+0.508
Neg logit contributions
iest-0.695
 oblig-0.636
 armour-0.631
br-0.628
 ti-0.619
Token count
Token ID954
Feature activation-4.91e-02

Pos logit contributions
 mess+0.538
 wasting+0.471
 ruining+0.462
 wasteful+0.456
 fighting+0.450
Neg logit contributions
iest-0.432
 oblig-0.395
 armour-0.388
br-0.383
 ti-0.379
Token to
Token ID284
Feature activation+5.40e-01

Pos logit contributions
iest+0.086
 oblig+0.079
 armour+0.077
br+0.077
 ti+0.076
Neg logit contributions
 mess-0.093
 wasting-0.081
 ruining-0.079
 wasteful-0.078
 fighting-0.078
Token ten
Token ID3478
Feature activation+1.18e+00

Pos logit contributions
 mess+1.026
 wasting+0.888
 ruining+0.868
 wasteful+0.863
 fighting+0.842
Neg logit contributions
iest-0.940
 oblig-0.872
 armour-0.853
br-0.841
 ti-0.833
Token.
Token ID13
Feature activation-1.88e-01

Pos logit contributions
 mess+2.514
 wasting+2.268
 wasteful+2.239
 ruining+2.222
 fighting+2.140
Neg logit contributions
iest-1.796
br-1.603
 armour-1.584
 oblig-1.582
 ti-1.527
Token When
Token ID1649
Feature activation+4.91e-01

Pos logit contributions
iest+0.305
 oblig+0.272
 armour+0.271
br+0.266
 ti+0.262
Neg logit contributions
 mess-0.388
 wasting-0.339
 ruining-0.333
 fighting-0.330
 wasteful-0.328
Token they
Token ID484
Feature activation-6.80e-01

Pos logit contributions
 mess+0.818
 wasting+0.692
 ruining+0.673
 wasteful+0.671
 fighting+0.645
Neg logit contributions
iest-0.978
 oblig-0.908
br-0.893
 armour-0.888
 ti-0.879
Token new
Token ID649
Feature activation-1.36e+00

Pos logit contributions
iest+2.036
br+1.854
 oblig+1.839
int+1.794
anger+1.793
Neg logit contributions
 mess-2.287
 wasting-1.907
 ruining-1.865
 fighting-1.846
 wasteful-1.832
Token toy
Token ID13373
Feature activation+2.32e-01

Pos logit contributions
iest+2.279
 oblig+2.092
br+2.091
int+2.076
anger+2.007
Neg logit contributions
 mess-2.846
 wasting-2.338
 fighting-2.313
 ruining-2.298
 wasteful-2.228
Token.
Token ID13
Feature activation+1.65e-01

Pos logit contributions
 mess+0.472
 wasting+0.415
 ruining+0.407
 wasteful+0.402
 fighting+0.396
Neg logit contributions
iest-0.376
 oblig-0.339
 armour-0.336
br-0.332
 ti-0.327
Token<|endoftext|>
Token ID50256
Feature activation-9.22e-01

Pos logit contributions
 mess+0.351
 wasting+0.309
 ruining+0.304
 wasteful+0.300
 fighting+0.297
Neg logit contributions
iest-0.251
 oblig-0.227
 armour-0.224
br-0.222
 ti-0.218
TokenDe
Token ID5005
Feature activation-5.58e-01

Pos logit contributions
iest+1.587
 oblig+1.442
 armour+1.440
int+1.404
shirt+1.398
Neg logit contributions
 mess-1.800
 wasting-1.547
 fighting-1.520
 ruining-1.500
 wasteful-1.449
Tokenena
Token ID8107
Feature activation+3.23e-01

Pos logit contributions
iest+0.900
 oblig+0.825
 armour+0.813
br+0.805
 ti+0.800
Neg logit contributions
 mess-1.128
 wasting-0.980
 ruining-0.962
 wasteful-0.960
 fighting-0.947
Token was
Token ID373
Feature activation+9.41e-01

Pos logit contributions
 mess+0.603
 wasting+0.523
 ruining+0.515
 wasteful+0.506
 fighting+0.499
Neg logit contributions
iest-0.575
 oblig-0.525
 armour-0.518
br-0.515
 ti-0.510
Token tired
Token ID10032
Feature activation+8.55e-01

Pos logit contributions
 mess+1.813
 wasting+1.558
 ruining+1.547
 wasteful+1.542
 fighting+1.474
Neg logit contributions
iest-1.575
 armour-1.473
 oblig-1.472
int-1.433
 ti-1.423
Token after
Token ID706
Feature activation+1.38e-01

Pos logit contributions
 mess+1.658
 wasting+1.474
 ruining+1.453
 wasteful+1.452
 fighting+1.407
Neg logit contributions
iest-1.455
 oblig-1.289
br-1.285
 armour-1.282
 ti-1.259
Token a
Token ID257
Feature activation-1.22e+00

Pos logit contributions
 mess+0.252
 wasting+0.217
 ruining+0.212
 wasteful+0.209
 fighting+0.207
Neg logit contributions
iest-0.254
 oblig-0.233
 armour-0.230
br-0.228
 ti-0.225
Token long
Token ID890
Feature activation-7.64e-01

Pos logit contributions
iest+1.961
 armour+1.751
 oblig+1.715
anced+1.712
int+1.690
Neg logit contributions
 mess-2.642
 wasting-2.228
 ruining-2.178
 fighting-2.163
 wasteful-2.124
Token had
Token ID550
Feature activation-4.15e-02

Pos logit contributions
iest+0.050
 oblig+0.045
 armour+0.045
br+0.045
shirt+0.044
Neg logit contributions
 mess-0.060
 wasting-0.052
 ruining-0.051
 wasteful-0.051
 fighting-0.050
Token.
Token ID13
Feature activation-2.19e-01

Pos logit contributions
iest+0.069
 oblig+0.063
 armour+0.062
br+0.062
 ti+0.061
Neg logit contributions
 mess-0.083
 wasting-0.072
 ruining-0.071
 wasteful-0.070
 fighting-0.069
Token<|endoftext|>
Token ID50256
Feature activation-1.55e+00

Pos logit contributions
iest+0.406
 oblig+0.367
 armour+0.364
br+0.362
 ti+0.354
Neg logit contributions
 mess-0.397
 wasting-0.345
 ruining-0.336
 wasteful-0.331
 fighting-0.331
TokenOnce
Token ID7454
Feature activation+7.01e-02

Pos logit contributions
iest+2.902
 armour+2.674
 oblig+2.644
int+2.634
shirt+2.630
Neg logit contributions
 mess-2.793
 wasting-2.379
 fighting-2.377
 ruining-2.271
 yourselves-2.188
Token upon
Token ID2402
Feature activation-9.06e-01

Pos logit contributions
 mess+0.142
 wasting+0.124
 ruining+0.122
 wasteful+0.120
 fighting+0.119
Neg logit contributions
iest-0.114
 oblig-0.104
 armour-0.102
br-0.101
 ti-0.099
Token a
Token ID257
Feature activation+1.05e+00

Pos logit contributions
iest+1.320
 oblig+1.182
anger+1.179
br+1.144
int+1.137
Neg logit contributions
 mess-2.024
 wasting-1.808
 ruining-1.738
 fighting-1.727
 wasteful-1.708
Token time
Token ID640
Feature activation+2.59e-01

Pos logit contributions
 mess+2.449
 wasting+2.250
 ruining+2.231
 wasteful+2.203
 fighting+2.163
Neg logit contributions
iest-1.311
 oblig-1.191
br-1.185
 armour-1.169
int-1.163
Token,
Token ID11
Feature activation+9.27e-01

Pos logit contributions
 mess+0.555
 wasting+0.489
 ruining+0.480
 wasteful+0.477
 fighting+0.467
Neg logit contributions
iest-0.393
 oblig-0.352
br-0.346
 armour-0.344
 ti-0.338
Token there
Token ID612
Feature activation-5.44e-01

Pos logit contributions
 mess+1.850
 wasting+1.595
 ruining+1.589
 wasteful+1.571
 fighting+1.501
Neg logit contributions
iest-1.558
br-1.390
 oblig-1.371
 armour-1.365
 ti-1.365
Token was
Token ID373
Feature activation+4.73e-02

Pos logit contributions
iest+0.861
 oblig+0.805
 armour+0.800
br+0.778
shirt+0.773
Neg logit contributions
 mess-1.128
 wasting-0.977
 ruining-0.956
 fighting-0.955
 wasteful-0.930
Token a
Token ID257
Feature activation+9.87e-02

Pos logit contributions
 mess+0.115
 wasting+0.102
 ruining+0.101
 wasteful+0.100
 fighting+0.099
Neg logit contributions
iest-0.059
 oblig-0.051
 armour-0.050
br-0.050
 ti-0.049
Token
Token ID198
Feature activation-8.54e-01

Pos logit contributions
iest+0.130
 oblig+0.118
 armour+0.117
br+0.116
 ti+0.114
Neg logit contributions
 mess-0.132
 wasting-0.114
 ruining-0.112
 wasteful-0.110
 fighting-0.109
Token
Token ID198
Feature activation+1.70e-01

Pos logit contributions
iest+1.360
 armour+1.211
br+1.183
 oblig+1.164
 ti+1.160
Neg logit contributions
 mess-1.801
 wasting-1.588
 fighting-1.535
 wasteful-1.524
 ruining-1.523
TokenBut
Token ID1537
Feature activation+7.04e-01

Pos logit contributions
 mess+0.286
 wasting+0.241
 ruining+0.237
 wasteful+0.232
 fighting+0.229
Neg logit contributions
iest-0.341
 oblig-0.316
 armour-0.311
br-0.310
 ti-0.305
Token she
Token ID673
Feature activation-6.60e-02

Pos logit contributions
 mess+1.161
 wasting+0.967
 ruining+0.946
 wasteful+0.940
 fighting+0.901
Neg logit contributions
iest-1.428
 oblig-1.323
 armour-1.304
 ti-1.292
br-1.288
Token knew
Token ID2993
Feature activation-2.31e-01

Pos logit contributions
iest+0.120
 oblig+0.109
 armour+0.108
br+0.108
shirt+0.106
Neg logit contributions
 mess-0.123
 wasting-0.105
 ruining-0.103
 wasteful-0.102
 fighting-0.101
Token that
Token ID326
Feature activation+4.65e-01

Pos logit contributions
iest+0.459
 oblig+0.426
 armour+0.421
br+0.418
shirt+0.413
Neg logit contributions
 mess-0.388
 wasting-0.332
 ruining-0.323
 wasteful-0.316
 fighting-0.315
Token if
Token ID611
Feature activation+1.70e-01

Pos logit contributions
 mess+0.848
 wasting+0.728
 ruining+0.716
 wasteful+0.710
 fighting+0.692
Neg logit contributions
iest-0.854
 oblig-0.775
 armour-0.768
br-0.763
 ti-0.758
Token she
Token ID673
Feature activation-1.69e+00

Pos logit contributions
 mess+0.294
 wasting+0.250
 ruining+0.245
 wasteful+0.241
 fighting+0.238
Neg logit contributions
iest-0.330
 oblig-0.304
 armour-0.300
br-0.298
 ti-0.294
Token was
Token ID373
Feature activation+9.71e-02

Pos logit contributions
iest+3.072
 armour+2.878
br+2.852
anger+2.836
 oblig+2.830
Neg logit contributions
 mess-3.165
 wasting-2.688
 ruining-2.613
 fighting-2.601
 wasteful-2.535
Token ever
Token ID1683
Feature activation+8.94e-01

Pos logit contributions
 mess+0.166
 wasting+0.141
 ruining+0.139
 wasteful+0.136
 fighting+0.135
Neg logit contributions
iest-0.189
 oblig-0.174
 armour-0.172
br-0.171
 ti-0.169
Token curious
Token ID11040
Feature activation-3.10e-01

Pos logit contributions
 mess+1.552
 wasting+1.328
 ruining+1.311
 wasteful+1.308
 fighting+1.254
Neg logit contributions
iest-1.704
 oblig-1.564
 armour-1.514
br-1.502
 ti-1.497
Token the
Token ID262
Feature activation+8.28e-01

Pos logit contributions
 mess+2.275
 wasting+1.993
 wasteful+1.990
 ruining+1.954
 fighting+1.879
Neg logit contributions
iest-2.071
 armour-1.896
 ti-1.862
 oblig-1.862
br-1.811
Token closet
Token ID21615
Feature activation+1.48e+00

Pos logit contributions
 mess+1.406
 wasting+1.243
 ruining+1.213
 wasteful+1.207
 fighting+1.195
Neg logit contributions
iest-1.565
 armour-1.471
 ti-1.451
 oblig-1.438
shirt-1.435
Token,
Token ID11
Feature activation+1.20e+00

Pos logit contributions
 mess+3.318
 wasting+3.002
 wasteful+2.981
 ruining+2.908
 fighting+2.770
Neg logit contributions
iest-2.111
anger-1.881
br-1.802
 ti-1.800
 oblig-1.782
Token and
Token ID290
Feature activation+1.10e+00

Pos logit contributions
 mess+2.246
 wasteful+1.932
 wasting+1.910
 ruining+1.871
 fighting+1.787
Neg logit contributions
iest-2.065
 armour-1.969
 ti-1.939
 oblig-1.900
 sail-1.886
Token even
Token ID772
Feature activation+1.50e-01

Pos logit contributions
 mess+2.213
 wasting+1.917
 ruining+1.889
 wasteful+1.869
 fighting+1.824
Neg logit contributions
iest-1.803
 ti-1.638
 oblig-1.636
 armour-1.631
br-1.598
Token in
Token ID287
Feature activation+8.75e-01

Pos logit contributions
 mess+0.299
 wasting+0.260
 ruining+0.256
 wasteful+0.252
 fighting+0.250
Neg logit contributions
iest-0.249
 oblig-0.227
 armour-0.224
br-0.222
 ti-0.218
Token the
Token ID262
Feature activation+6.06e-01

Pos logit contributions
 mess+1.649
 wasting+1.430
 wasteful+1.412
 ruining+1.407
 fighting+1.362
Neg logit contributions
iest-1.537
 armour-1.389
 oblig-1.386
 ti-1.375
br-1.360
Token toy
Token ID13373
Feature activation+3.57e-01

Pos logit contributions
 mess+1.022
 wasting+0.893
 ruining+0.870
 wasteful+0.861
 fighting+0.852
Neg logit contributions
iest-1.169
 armour-1.083
 oblig-1.073
 ti-1.071
shirt-1.059
Token box
Token ID3091
Feature activation+8.37e-02

Pos logit contributions
 mess+0.744
 wasting+0.656
 ruining+0.644
 wasteful+0.639
 fighting+0.626
Neg logit contributions
iest-0.565
 oblig-0.505
 armour-0.500
br-0.496
anger-0.489
Token.
Token ID13
Feature activation+1.70e+00

Pos logit contributions
 mess+0.175
 wasting+0.154
 ruining+0.151
 wasteful+0.149
 fighting+0.148
Neg logit contributions
iest-0.131
 oblig-0.118
 armour-0.116
br-0.115
 ti-0.113
Token Finally
Token ID9461
Feature activation+1.57e-01

Pos logit contributions
 mess+3.441
 ruining+3.023
 wasting+3.018
 wasteful+2.875
 fighting+2.807
Neg logit contributions
iest-2.597
anger-2.548
shirt-2.523
br-2.494
 oblig-2.493
Token,
Token ID11
Feature activation-9.85e-01

Pos logit contributions
iest+2.139
shirt+2.017
 oblig+2.006
 armour+2.005
int+1.936
Neg logit contributions
 mess-2.217
 wasting-1.922
 fighting-1.879
 ruining-1.864
 wasteful-1.793
Token she
Token ID673
Feature activation+4.62e-02

Pos logit contributions
iest+1.935
 oblig+1.824
 armour+1.815
shirt+1.793
int+1.772
Neg logit contributions
 mess-1.632
 wasting-1.431
 ruining-1.364
 fighting-1.353
 wasteful-1.310
Token had
Token ID550
Feature activation-5.11e-01

Pos logit contributions
 mess+0.092
 wasting+0.080
 ruining+0.078
 wasteful+0.077
 fighting+0.077
Neg logit contributions
iest-0.078
 oblig-0.070
 armour-0.069
br-0.069
 ti-0.068
Token a
Token ID257
Feature activation-8.24e-01

Pos logit contributions
iest+0.691
 oblig+0.595
 armour+0.587
br+0.577
shirt+0.577
Neg logit contributions
 mess-1.205
 wasting-1.075
 ruining-1.059
 fighting-1.041
 wasteful-1.039
Token great
Token ID1049
Feature activation-1.13e+00

Pos logit contributions
iest+1.587
 oblig+1.422
 armour+1.409
shirt+1.409
int+1.408
Neg logit contributions
 mess-1.533
 wasting-1.256
 ruining-1.238
 fighting-1.219
 wasteful-1.217
Token idea
Token ID2126
Feature activation-1.15e+00

Pos logit contributions
iest+1.751
 oblig+1.529
shirt+1.523
br+1.520
 armour+1.516
Neg logit contributions
 mess-2.607
 wasting-2.140
 fighting-2.131
 ruining-2.113
 wasteful-2.075
Token!
Token ID0
Feature activation-9.67e-01

Pos logit contributions
iest+2.030
 armour+1.890
 oblig+1.874
int+1.835
br+1.829
Neg logit contributions
 mess-2.206
 wasting-1.893
 ruining-1.887
 fighting-1.876
 wasteful-1.748
Token She
Token ID1375
Feature activation-6.99e-01

Pos logit contributions
iest+2.317
 oblig+2.136
 armour+2.113
br+2.097
 ti+2.065
Neg logit contributions
 mess-1.241
 wasting-1.028
 fighting-0.968
 ruining-0.960
 wasteful-0.949
Token pointed
Token ID6235
Feature activation-5.00e-01

Pos logit contributions
iest+1.263
 oblig+1.129
 armour+1.111
anger+1.109
br+1.105
Neg logit contributions
 mess-1.345
 wasting-1.137
 ruining-1.106
 fighting-1.098
 wasteful-1.092
Token to
Token ID284
Feature activation-6.18e-01

Pos logit contributions
iest+0.830
 oblig+0.751
br+0.742
 armour+0.726
int+0.720
Neg logit contributions
 mess-1.010
 wasting-0.878
 ruining-0.863
 fighting-0.859
 wasteful-0.846
Token the
Token ID262
Feature activation+1.74e+00

Pos logit contributions
iest+1.038
 oblig+0.927
br+0.924
 armour+0.917
int+0.916
Neg logit contributions
 mess-1.243
 wasting-1.095
 ruining-1.060
 fighting-1.054
 wasteful-1.039
Token un
Token ID555
Feature activation-5.76e-01

Pos logit contributions
iest+2.326
br+2.069
anger+2.061
int+2.055
 armour+2.013
Neg logit contributions
 mess-2.711
 wasting-2.380
 ruining-2.358
 fighting-2.338
 wasteful-2.175
Tokenpack
Token ID8002
Feature activation-9.58e-01

Pos logit contributions
iest+0.937
br+0.836
 oblig+0.834
 armour+0.832
 ti+0.815
Neg logit contributions
 mess-1.179
 wasting-1.029
 ruining-1.018
 fighting-1.005
 wasteful-0.987
Token all
Token ID477
Feature activation-4.26e-02

Pos logit contributions
iest+1.846
 oblig+1.772
br+1.731
int+1.708
 armour+1.703
Neg logit contributions
 mess-1.683
 wasting-1.398
 ruining-1.362
 fighting-1.359
 wasteful-1.321
Token of
Token ID286
Feature activation+7.35e-01

Pos logit contributions
iest+0.070
 oblig+0.064
 armour+0.063
br+0.062
 ti+0.061
Neg logit contributions
 mess-0.086
 wasting-0.075
 ruining-0.074
 wasteful-0.072
 fighting-0.072
Token their
Token ID511
Feature activation-2.54e-01

Pos logit contributions
 mess+1.389
 wasting+1.200
 wasteful+1.191
 ruining+1.185
 fighting+1.139
Neg logit contributions
iest-1.299
 oblig-1.176
 armour-1.172
 ti-1.133
 sail-1.129
Token things
Token ID1243
Feature activation-1.53e-01

Pos logit contributions
iest+0.514
 oblig+0.478
br+0.470
 armour+0.469
 ti+0.461
Neg logit contributions
 mess-0.425
 wasting-0.353
 ruining-0.346
 fighting-0.340
 wasteful-0.337
Token.
Token ID13
Feature activation+1.20e-01

Pos logit contributions
iest+0.266
 oblig+0.245
 armour+0.241
br+0.239
int+0.235
Neg logit contributions
 mess-0.294
 wasting-0.255
 ruining-0.250
 fighting-0.245
 wasteful-0.245
Token One
Token ID1881
Feature activation-1.25e+00

Pos logit contributions
 mess+0.247
 wasting+0.216
 ruining+0.213
 wasteful+0.210
 fighting+0.208
Neg logit contributions
iest-0.190
 oblig-0.172
 armour-0.170
br-0.168
 ti-0.165
Token of
Token ID286
Feature activation-3.48e-01

Pos logit contributions
iest+1.927
 oblig+1.895
 armour+1.881
br+1.833
 ti+1.820
Neg logit contributions
 mess-2.646
 wasting-2.257
 fighting-2.201
 wasteful-2.163
 ruining-2.157
Token the
Token ID262
Feature activation+2.93e-01

Pos logit contributions
iest+0.685
 oblig+0.634
br+0.629
 armour+0.627
anger+0.625
Neg logit contributions
 mess-0.588
 wasting-0.505
 ruining-0.490
 fighting-0.483
 wasteful-0.476
Token first
Token ID717
Feature activation-1.53e+00

Pos logit contributions
 mess+0.494
 wasting+0.422
 ruining+0.413
 wasteful+0.408
 fighting+0.398
Neg logit contributions
iest-0.583
 oblig-0.534
 armour-0.529
br-0.525
 ti-0.520
Token then
Token ID788
Feature activation-1.20e+00

Pos logit contributions
iest+0.429
 oblig+0.393
br+0.386
 armour+0.384
anger+0.380
Neg logit contributions
 mess-0.423
 wasting-0.365
 ruining-0.357
 fighting-0.350
 wasteful-0.348
Token stepped
Token ID10764
Feature activation-2.25e+00

Pos logit contributions
iest+1.969
 oblig+1.759
br+1.740
anger+1.737
 armour+1.700
Neg logit contributions
 mess-2.520
 wasting-2.199
 fighting-2.136
 ruining-2.130
 wasteful-2.095
Token into
Token ID656
Feature activation-1.02e+00

Pos logit contributions
iest+4.565
 oblig+4.218
br+4.113
 powers+4.083
 medal+3.988
Neg logit contributions
 mess-3.884
 wasting-3.335
 fighting-3.281
 ruining-3.245
 wasteful-3.006
Token the
Token ID262
Feature activation-1.11e-01

Pos logit contributions
iest+2.202
br+2.050
int+2.037
anger+2.016
 oblig+2.004
Neg logit contributions
 mess-1.642
 wasting-1.379
 ruining-1.326
 fighting-1.324
 wasteful-1.247
Token water
Token ID1660
Feature activation-3.75e-01

Pos logit contributions
iest+0.183
 oblig+0.166
 armour+0.162
br+0.162
 ti+0.159
Neg logit contributions
 mess-0.226
 wasting-0.196
 ruining-0.193
 wasteful-0.190
 fighting-0.189
Token.
Token ID13
Feature activation-1.73e+00

Pos logit contributions
iest+0.654
 oblig+0.605
 armour+0.592
br+0.590
int+0.578
Neg logit contributions
 mess-0.721
 wasting-0.621
 ruining-0.608
 fighting-0.602
 wasteful-0.592
Token It
Token ID632
Feature activation-8.69e-01

Pos logit contributions
iest+3.106
 oblig+2.577
br+2.575
 ti+2.497
 armour+2.482
Neg logit contributions
 mess-3.496
 wasting-3.121
 fighting-3.030
 ruining-2.984
 wasteful-2.976
Token felt
Token ID2936
Feature activation-1.49e+00

Pos logit contributions
iest+1.399
 oblig+1.303
 armour+1.273
anger+1.266
shirt+1.243
Neg logit contributions
 mess-1.802
 wasting-1.536
 ruining-1.513
 fighting-1.493
 wasteful-1.480
Token cold
Token ID4692
Feature activation-5.92e-02

Pos logit contributions
iest+3.248
anger+3.142
 oblig+3.079
int+3.044
 armour+3.027
Neg logit contributions
 mess-2.291
 wasting-1.951
 ruining-1.881
 wasteful-1.855
 fighting-1.793
Token and
Token ID290
Feature activation+4.08e-01

Pos logit contributions
iest+0.116
 oblig+0.108
 armour+0.106
br+0.106
 ti+0.104
Neg logit contributions
 mess-0.100
 wasting-0.085
 ruining-0.083
 wasteful-0.081
 fighting-0.081
Token strange
Token ID6283
Feature activation-9.48e-01

Pos logit contributions
 mess+0.699
 wasting+0.597
 ruining+0.583
 wasteful+0.574
 fighting+0.567
Neg logit contributions
iest-0.786
 oblig-0.721
 armour-0.716
br-0.707
 ti-0.704
Token,"
Token ID553
Feature activation+3.77e-01

Pos logit contributions
 mess+1.084
 wasting+0.957
 ruining+0.945
 wasteful+0.935
 fighting+0.913
Neg logit contributions
iest-0.796
 oblig-0.709
br-0.693
 armour-0.692
 ti-0.684
Token Lucy
Token ID22162
Feature activation-7.21e-02

Pos logit contributions
 mess+0.658
 wasting+0.563
 ruining+0.555
 wasteful+0.545
 fighting+0.535
Neg logit contributions
iest-0.724
 oblig-0.666
 armour-0.654
br-0.649
 ti-0.648
Token said
Token ID531
Feature activation-1.29e+00

Pos logit contributions
iest+0.139
 oblig+0.128
 armour+0.127
br+0.126
 ti+0.124
Neg logit contributions
 mess-0.125
 wasting-0.106
 ruining-0.104
 wasteful-0.102
 fighting-0.101
Token,
Token ID11
Feature activation-4.97e-01

Pos logit contributions
iest+2.308
 armour+2.160
br+2.134
 oblig+2.047
anger+2.044
Neg logit contributions
 mess-2.430
 wasting-2.081
 fighting-2.066
 ruining-2.030
 wasteful-1.983
Token "
Token ID366
Feature activation-2.78e-01

Pos logit contributions
iest+0.859
 oblig+0.761
br+0.757
 armour+0.755
anger+0.744
Neg logit contributions
 mess-0.985
 wasting-0.867
 ruining-0.844
 fighting-0.840
 wasteful-0.821
TokenI
Token ID40
Feature activation-1.01e+00

Pos logit contributions
iest+0.530
 oblig+0.488
 armour+0.485
br+0.481
anger+0.474
Neg logit contributions
 mess-0.483
 wasting-0.414
 ruining-0.403
 wasteful-0.397
 fighting-0.394
Token have
Token ID423
Feature activation+1.60e-01

Pos logit contributions
iest+1.911
 armour+1.790
anger+1.734
br+1.726
 oblig+1.724
Neg logit contributions
 mess-1.844
 wasting-1.528
 fighting-1.486
 wasteful-1.486
 ruining-1.481
Token a
Token ID257
Feature activation-1.30e+00

Pos logit contributions
 mess+0.368
 wasting+0.327
 ruining+0.322
 wasteful+0.318
 fighting+0.315
Neg logit contributions
iest-0.219
 oblig-0.195
 armour-0.191
br-0.190
 ti-0.186
Token joke
Token ID9707
Feature activation-3.63e-01

Pos logit contributions
iest+2.342
 oblig+2.062
int+2.044
 armour+2.027
anced+2.013
Neg logit contributions
 mess-2.679
 wasting-2.193
 ruining-2.151
 fighting-2.145
 wasteful-2.120
Token!"
Token ID2474
Feature activation-2.40e-01

Pos logit contributions
iest+0.664
 oblig+0.616
 armour+0.611
br+0.597
int+0.596
Neg logit contributions
 mess-0.657
 wasting-0.560
 ruining-0.551
 wasteful-0.540
 fighting-0.539
Token
Token ID220
Feature activation+4.69e-01

Pos logit contributions
iest+0.423
 oblig+0.382
 armour+0.380
br+0.378
 ti+0.368
Neg logit contributions
 mess-0.459
 wasting-0.398
 ruining-0.388
 fighting-0.383
 wasteful-0.381
Token Come
Token ID7911
Feature activation-1.54e+00

Pos logit contributions
iest+0.548
 oblig+0.489
br+0.481
 armour+0.480
anger+0.470
Neg logit contributions
 mess-0.660
 wasting-0.582
 ruining-0.567
 fighting-0.562
 wasteful-0.560
Token on
Token ID319
Feature activation+1.64e-02

Pos logit contributions
iest+3.130
br+2.748
 powers+2.721
 armour+2.720
 oblig+2.709
Neg logit contributions
 mess-2.627
 fighting-2.300
 wasting-2.253
 ruining-2.245
 wasteful-2.020
Token,
Token ID11
Feature activation-2.64e-01

Pos logit contributions
 mess+0.034
 wasting+0.030
 ruining+0.029
 wasteful+0.029
 fighting+0.029
Neg logit contributions
iest-0.026
 oblig-0.024
 armour-0.023
br-0.023
 ti-0.023
Token let
Token ID1309
Feature activation+2.63e-01

Pos logit contributions
iest+0.533
 oblig+0.488
 armour+0.484
br+0.481
int+0.476
Neg logit contributions
 mess-0.436
 wasting-0.367
 ruining-0.358
 fighting-0.350
 wasteful-0.350
Token's
Token ID338
Feature activation-1.21e-01

Pos logit contributions
 mess+0.332
 wasting+0.267
 ruining+0.259
 wasteful+0.252
 fighting+0.246
Neg logit contributions
iest-0.634
 oblig-0.594
 armour-0.587
br-0.585
shirt-0.579
Token go
Token ID467
Feature activation-1.53e+00

Pos logit contributions
iest+0.177
 oblig+0.158
br+0.155
 armour+0.155
shirt+0.151
Neg logit contributions
 mess-0.268
 wasting-0.235
 ruining-0.232
 wasteful-0.228
 fighting-0.227
Token."
Token ID526
Feature activation+2.61e-01

Pos logit contributions
iest+2.959
 armour+2.751
br+2.735
 oblig+2.699
 ti+2.662
Neg logit contributions
 mess-2.685
 wasting-2.198
 fighting-2.161
 ruining-2.159
 yourselves-2.001
Token He
Token ID679
Feature activation-1.45e+00

Pos logit contributions
 mess+0.522
 wasting+0.454
 ruining+0.448
 wasteful+0.441
 fighting+0.433
Neg logit contributions
iest-0.434
 oblig-0.399
 armour-0.391
br-0.386
 ti-0.383
Token ran
Token ID4966
Feature activation-8.30e-01

Pos logit contributions
iest+2.720
 oblig+2.357
br+2.309
 armour+2.295
anger+2.289
Neg logit contributions
 mess-2.843
 wasting-2.415
 ruining-2.311
 fighting-2.310
 wasteful-2.255
Token to
Token ID284
Feature activation-5.47e-01

Pos logit contributions
iest+1.457
 oblig+1.298
br+1.289
 armour+1.273
int+1.267
Neg logit contributions
 mess-1.637
 ruining-1.395
 wasting-1.391
 fighting-1.386
 wasteful-1.333
Token the
Token ID262
Feature activation-4.20e-02

Pos logit contributions
iest+1.120
br+1.034
 armour+1.008
int+1.007
 oblig+1.002
Neg logit contributions
 mess-0.927
 wasting-0.777
 ruining-0.755
 fighting-0.747
 wasteful-0.727
Token big
Token ID1263
Feature activation+3.59e-01

Pos logit contributions
 mess+0.235
 wasting+0.201
 ruining+0.197
 wasteful+0.193
 fighting+0.191
Neg logit contributions
iest-0.255
 oblig-0.235
 armour-0.232
br-0.231
 ti-0.228
Token,
Token ID11
Feature activation-1.32e-01

Pos logit contributions
 mess+0.731
 wasting+0.645
 ruining+0.635
 wasteful+0.626
 fighting+0.616
Neg logit contributions
iest-0.576
 oblig-0.521
 armour-0.517
br-0.511
 ti-0.503
Token round
Token ID2835
Feature activation-1.20e+00

Pos logit contributions
iest+0.224
 oblig+0.204
 armour+0.200
br+0.198
shirt+0.196
Neg logit contributions
 mess-0.260
 wasting-0.226
 ruining-0.221
 wasteful-0.218
 fighting-0.216
Token sun
Token ID4252
Feature activation-4.24e-01

Pos logit contributions
iest+2.261
 oblig+2.161
 armour+2.034
br+2.028
shirt+2.007
Neg logit contributions
 mess-2.230
 wasting-1.825
 fighting-1.777
 ruining-1.749
 wasteful-1.744
Token.
Token ID13
Feature activation-1.40e+00

Pos logit contributions
iest+0.731
 oblig+0.681
 armour+0.663
br+0.655
shirt+0.647
Neg logit contributions
 mess-0.819
 wasting-0.707
 ruining-0.693
 fighting-0.686
 wasteful-0.668
Token Every
Token ID3887
Feature activation-2.86e+00

Pos logit contributions
iest+2.388
 oblig+2.093
int+2.068
anger+2.050
 armour+2.019
Neg logit contributions
 mess-2.801
 wasting-2.532
 ruining-2.468
 fighting-2.449
 wasteful-2.350
Token day
Token ID1110
Feature activation-2.29e+00

Pos logit contributions
iest+5.474
 armour+5.372
 oblig+5.364
 ti+5.233
anger+5.180
Neg logit contributions
 mess-5.287
 wasting-4.127
 fighting-4.075
 wasteful-3.922
 ruining-3.871
Token it
Token ID340
Feature activation-6.29e-01

Pos logit contributions
int+4.588
 oblig+4.480
iest+4.398
anger+4.343
 armour+4.302
Neg logit contributions
 mess-3.692
 wasting-3.211
 fighting-3.202
 ruining-3.099
 wasteful-2.935
Token smiled
Token ID13541
Feature activation-9.11e-01

Pos logit contributions
iest+0.944
 oblig+0.864
 armour+0.854
anger+0.829
shirt+0.821
Neg logit contributions
 mess-1.379
 wasting-1.188
 ruining-1.163
 wasteful-1.154
 fighting-1.142
Token down
Token ID866
Feature activation-1.14e+00

Pos logit contributions
iest+2.006
 oblig+1.938
br+1.861
anger+1.844
shirt+1.843
Neg logit contributions
 mess-1.343
 wasting-1.086
 ruining-1.039
 fighting-1.025
 wasteful-1.016
Token on
Token ID319
Feature activation-5.66e-01

Pos logit contributions
iest+2.118
 oblig+2.018
shirt+1.939
br+1.937
 ti+1.934
Neg logit contributions
 mess-2.058
 wasting-1.793
 fighting-1.750
 ruining-1.739
 wasteful-1.672
Token.
Token ID13
Feature activation-1.27e-01

Pos logit contributions
iest+0.071
 oblig+0.064
 armour+0.063
br+0.063
 ti+0.061
Neg logit contributions
 mess-0.092
 wasting-0.081
 ruining-0.079
 wasteful-0.078
 fighting-0.078
Token So
Token ID1406
Feature activation+2.60e-01

Pos logit contributions
iest+0.195
 oblig+0.173
 armour+0.171
br+0.171
 ti+0.166
Neg logit contributions
 mess-0.270
 wasting-0.238
 ruining-0.233
 wasteful-0.230
 fighting-0.229
Token he
Token ID339
Feature activation-8.83e-01

Pos logit contributions
 mess+0.596
 wasting+0.529
 ruining+0.521
 wasteful+0.516
 fighting+0.509
Neg logit contributions
iest-0.359
 oblig-0.318
 armour-0.313
br-0.308
 ti-0.303
Token decided
Token ID3066
Feature activation-8.98e-01

Pos logit contributions
iest+1.561
 oblig+1.399
 armour+1.390
anger+1.379
br+1.369
Neg logit contributions
 mess-1.707
 wasting-1.459
 ruining-1.422
 fighting-1.403
 wasteful-1.396
Token to
Token ID284
Feature activation-6.51e-01

Pos logit contributions
iest+1.425
 oblig+1.274
int+1.266
br+1.254
 armour+1.253
Neg logit contributions
 mess-1.912
 wasting-1.676
 ruining-1.651
 fighting-1.632
 wasteful-1.599
Token take
Token ID1011
Feature activation-3.04e+00

Pos logit contributions
iest+1.028
 armour+0.913
br+0.909
 oblig+0.905
shirt+0.890
Neg logit contributions
 mess-1.372
 wasting-1.198
 ruining-1.178
 fighting-1.159
 wasteful-1.139
Token her
Token ID607
Feature activation-1.68e+00

Pos logit contributions
iest+6.161
anger+5.963
int+5.810
 ti+5.754
uttered+5.717
Neg logit contributions
 mess-5.188
 wasting-4.223
 fighting-4.142
 ruining-4.090
 yourselves-3.932
Token to
Token ID284
Feature activation-8.51e-01

Pos logit contributions
iest+2.936
br+2.729
 oblig+2.703
int+2.693
 armour+2.627
Neg logit contributions
 mess-3.356
 wasting-2.851
 fighting-2.826
 ruining-2.796
 wasteful-2.662
Token the
Token ID262
Feature activation-8.98e-02

Pos logit contributions
iest+1.670
br+1.521
int+1.519
anger+1.497
 armour+1.486
Neg logit contributions
 mess-1.527
 wasting-1.304
 ruining-1.263
 fighting-1.236
 wasteful-1.204
Token park
Token ID3952
Feature activation-3.83e-01

Pos logit contributions
iest+0.175
 oblig+0.161
 armour+0.159
br+0.158
int+0.156
Neg logit contributions
 mess-0.155
 wasting-0.132
 ruining-0.129
 wasteful-0.126
 fighting-0.125
Token and
Token ID290
Feature activation-6.14e-01

Pos logit contributions
iest+0.692
 oblig+0.633
br+0.626
 armour+0.621
int+0.613
Neg logit contributions
 mess-0.713
 wasting-0.611
 ruining-0.599
 fighting-0.590
 wasteful-0.584
Token
Token ID26391
Feature activation+5.93e-01

Pos logit contributions
iest+1.466
 armour+1.332
br+1.307
 oblig+1.292
 ti+1.288
Neg logit contributions
 mess-1.811
 wasting-1.566
 wasteful-1.556
 ruining-1.543
 fighting-1.514
Token
Token ID198
Feature activation-7.68e-01

Pos logit contributions
 mess+1.248
 wasting+1.098
 ruining+1.082
 wasteful+1.073
 fighting+1.044
Neg logit contributions
iest-0.912
 oblig-0.843
br-0.823
 armour-0.823
 ti-0.808
Token
Token ID198
Feature activation+8.07e-02

Pos logit contributions
iest+1.312
 armour+1.187
 oblig+1.149
br+1.146
int+1.140
Neg logit contributions
 mess-1.506
 wasting-1.316
 ruining-1.272
 fighting-1.266
 wasteful-1.255
TokenThe
Token ID464
Feature activation-1.20e+00

Pos logit contributions
 mess+0.143
 wasting+0.122
 ruining+0.120
 wasteful+0.118
 fighting+0.117
Neg logit contributions
iest-0.153
 oblig-0.141
 armour-0.139
br-0.138
 ti-0.136
Token guard
Token ID4860
Feature activation-4.47e-01

Pos logit contributions
iest+2.183
 oblig+1.989
int+1.988
br+1.980
shirt+1.958
Neg logit contributions
 mess-2.308
 wasting-1.934
 ruining-1.898
 fighting-1.859
 wasteful-1.846
Token nodded
Token ID14464
Feature activation-2.19e+00

Pos logit contributions
iest+0.736
 oblig+0.667
 armour+0.660
br+0.653
shirt+0.643
Neg logit contributions
 mess-0.898
 wasting-0.777
 ruining-0.761
 fighting-0.754
 wasteful-0.751
Token and
Token ID290
Feature activation-8.08e-01

Pos logit contributions
iest+5.089
anger+4.843
br+4.822
int+4.628
 oblig+4.626
Neg logit contributions
 mess-3.111
 fighting-2.594
 wasting-2.535
 ruining-2.473
 wasteful-2.238
Token replied
Token ID8712
Feature activation-1.98e+00

Pos logit contributions
iest+1.548
 armour+1.397
 oblig+1.392
br+1.392
anger+1.377
Neg logit contributions
 mess-1.426
 wasting-1.224
 ruining-1.187
 fighting-1.174
 wasteful-1.166
Token,
Token ID11
Feature activation-7.12e-01

Pos logit contributions
iest+3.792
 armour+3.571
shirt+3.553
 oblig+3.487
int+3.467
Neg logit contributions
 mess-3.406
 fighting-2.971
 wasting-2.955
 ruining-2.898
 wasteful-2.864
Token
Token ID6184
Feature activation-2.31e+00

Pos logit contributions
iest+1.246
 armour+1.097
 oblig+1.095
shirt+1.074
br+1.073
Neg logit contributions
 mess-1.388
 wasting-1.220
 ruining-1.191
 fighting-1.189
 wasteful-1.159
Token
Token ID95
Feature activation-1.51e+00

Pos logit contributions
iest+3.743
 armour+3.169
 shone+3.116
shirt+3.033
 oblig+3.004
Neg logit contributions
 mess-4.997
 ruining-4.494
 wasteful-4.453
 wasting-4.452
 yourselves-4.361
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
iest+1.148
 oblig+1.083
 armour+1.065
br+1.030
 ti+1.027
Neg logit contributions
 mess-1.149
 wasting-0.977
 ruining-0.954
 wasteful-0.944
 fighting-0.931
Token But
Token ID887
Feature activation-2.96e-01

Pos logit contributions
iest+1.893
 oblig+1.681
 armour+1.665
br+1.628
 medal+1.615
Neg logit contributions
 mess-1.979
 wasting-1.808
 wasteful-1.750
 ruining-1.741
 fighting-1.722
Token I
Token ID314
Feature activation-2.26e-01

Pos logit contributions
iest+0.617
 oblig+0.575
 armour+0.569
br+0.563
shirt+0.559
Neg logit contributions
 mess-0.466
 wasting-0.395
 ruining-0.384
 wasteful-0.377
 fighting-0.375
Token have
Token ID423
Feature activation-6.61e-01

Pos logit contributions
iest+0.414
 armour+0.378
 oblig+0.377
br+0.372
shirt+0.367
Neg logit contributions
 mess-0.419
 wasting-0.360
 ruining-0.350
 wasteful-0.348
 fighting-0.343
Token a
Token ID257
Feature activation-1.74e+00

Pos logit contributions
iest+1.111
 oblig+1.005
 armour+0.987
br+0.976
anger+0.972
Neg logit contributions
 mess-1.337
 wasting-1.168
 ruining-1.138
 wasteful-1.135
 fighting-1.120
Token special
Token ID2041
Feature activation-2.66e+00

Pos logit contributions
iest+3.192
 armour+2.867
anced+2.835
 oblig+2.812
int+2.753
Neg logit contributions
 mess-3.636
 wasting-2.873
 wasteful-2.840
 fighting-2.816
 ruining-2.775
Token offer
Token ID2897
Feature activation-9.14e-01

Pos logit contributions
iest+4.681
 armour+4.499
anced+4.338
 oblig+4.290
int+4.211
Neg logit contributions
 mess-5.886
 fighting-4.512
 wasting-4.457
 wasteful-4.454
 mistake-4.339
Token for
Token ID329
Feature activation-5.38e-01

Pos logit contributions
iest+1.686
 oblig+1.581
 armour+1.566
br+1.552
int+1.541
Neg logit contributions
 mess-1.627
 wasting-1.387
 ruining-1.353
 fighting-1.343
 wasteful-1.333
Token you
Token ID345
Feature activation+3.38e-02

Pos logit contributions
iest+1.201
 oblig+1.112
 armour+1.108
br+1.100
int+1.092
Neg logit contributions
 mess-0.778
 wasting-0.656
 ruining-0.635
 fighting-0.620
 wasteful-0.618
Token.
Token ID13
Feature activation-9.75e-01

Pos logit contributions
 mess+0.065
 wasting+0.057
 ruining+0.056
 wasteful+0.055
 fighting+0.054
Neg logit contributions
iest-0.058
 oblig-0.053
 armour-0.052
br-0.052
 ti-0.051
Token If
Token ID1002
Feature activation-4.14e-01

Pos logit contributions
iest+1.802
 oblig+1.606
 armour+1.587
br+1.559
anger+1.545
Neg logit contributions
 mess-1.752
 wasting-1.594
 ruining-1.529
 wasteful-1.527
 fighting-1.510
Token named
Token ID3706
Feature activation+1.47e+00

Pos logit contributions
 mess+0.788
 wasting+0.697
 ruining+0.688
 wasteful+0.681
 fighting+0.670
Neg logit contributions
iest-0.488
 oblig-0.436
 armour-0.427
br-0.424
 ti-0.420
Token Lily
Token ID20037
Feature activation-1.76e-02

Pos logit contributions
 mess+2.274
 wasting+1.843
 ruining+1.826
 wasteful+1.820
 fighting+1.720
Neg logit contributions
iest-3.105
 oblig-2.970
 ti-2.948
br-2.899
shirt-2.876
Token.
Token ID13
Feature activation+9.87e-01

Pos logit contributions
iest+0.028
 oblig+0.025
 armour+0.025
br+0.025
 ti+0.024
Neg logit contributions
 mess-0.037
 wasting-0.032
 ruining-0.032
 wasteful-0.031
 fighting-0.031
Token She
Token ID1375
Feature activation-1.20e+00

Pos logit contributions
 mess+1.697
 wasting+1.458
 ruining+1.434
 wasteful+1.412
 fighting+1.363
Neg logit contributions
iest-1.881
 ti-1.768
 oblig-1.758
shirt-1.748
br-1.738
Token loved
Token ID6151
Feature activation+4.36e-01

Pos logit contributions
iest+2.162
anger+1.955
 oblig+1.949
 armour+1.926
int+1.868
Neg logit contributions
 mess-2.385
 wasting-2.029
 ruining-1.966
 fighting-1.945
 wasteful-1.922
Token to
Token ID284
Feature activation-2.74e+00

Pos logit contributions
 mess+0.990
 wasting+0.875
 ruining+0.863
 wasteful+0.861
 fighting+0.843
Neg logit contributions
iest-0.593
 oblig-0.534
 armour-0.528
br-0.519
 ti-0.510
Token pick
Token ID2298
Feature activation-5.84e-01

Pos logit contributions
iest+5.720
anger+5.236
int+5.008
uttered+4.986
 armour+4.932
Neg logit contributions
 mess-5.135
 wasting-4.334
 ruining-4.126
 fighting-4.084
 wasteful-3.735
Token flowers
Token ID12734
Feature activation+4.49e-01

Pos logit contributions
iest+1.114
 oblig+1.058
 armour+1.027
br+1.004
 ti+0.997
Neg logit contributions
 mess-1.030
 wasting-0.869
 ruining-0.837
 fighting-0.829
 wasteful-0.829
Token in
Token ID287
Feature activation+4.22e-01

Pos logit contributions
 mess+0.861
 wasting+0.743
 ruining+0.730
 wasteful+0.725
 fighting+0.707
Neg logit contributions
iest-0.791
 oblig-0.712
br-0.709
 armour-0.702
 ti-0.694
Token the
Token ID262
Feature activation+1.26e-01

Pos logit contributions
 mess+0.755
 wasting+0.646
 ruining+0.637
 wasteful+0.632
 fighting+0.615
Neg logit contributions
iest-0.790
 oblig-0.726
 armour-0.718
br-0.710
 ti-0.707
Token garden
Token ID11376
Feature activation+8.20e-01

Pos logit contributions
 mess+0.218
 wasting+0.186
 ruining+0.182
 wasteful+0.178
 fighting+0.176
Neg logit contributions
iest-0.246
 oblig-0.227
 armour-0.224
br-0.223
 ti-0.220