TOP ACTIVATIONS
MAX = 2.195

Where Primary | Select - Exp and Property B ounds |
get worse ." "… Alright ." Ste
Del Sur featuring Coach ( Surv iv or T oc ant
card ) R attle Snake : La N m
) ( K ath leen Flynn )
customers might need to be dial ed back . In a
addition of crisp high - definition graphics and Wii Motion Plus
Oh my …. How bad is it ?」
streaming five videos of high definition video a day .
mon ologue given by Jimmy Kimmel concerning his newborn son .
and spread them near the sunk en fireplace . After that
Chart ered Institute of Personnel and Development " Overall ,
7 . Dw ark adh ish Temple Address
May 5 ). The most recent example of the wrong ness
up but I would still recommend we sign him for up
chain . M ounds of tail ings from mineral
secession ist bloc after the recent surge of popular mobil isation
federal reviews of whether health plans in the ACA market places
Temple Address : Sector 20 , J Road ,
priority . But …. " Ah ."

MIN ACTIVATIONS
MIN = -2.116

// The previous board | ---------------- ------------- recursive without ind irection
by clicking the box . Invalid email address . Please re
by clicking the box . Invalid email address . Please re
by clicking the box . Invalid email address . Please re
that 's had a story patch . That 's obviously not
SI military was under the command of General Alfred o Gu
under Zh uk ov 's command .[ 31 ] This front
handed Libya over to a patch work of tribal and Al
by clicking the box . Invalid email address . Please re
to learn more about social justice from atheists who shared their
if you 're really f **** d . Let
vm ash ship yard at Sever od v insk , which
series Natural World episode " Snow Leopard Beyond the Myth
bronze and steel have been collected in tribute to some of
which are probably easy to fix , but it just takes
bow in person but their collected correspondence contains no letter saying
This is explained here . * mod eline * * vim
month is to try and collect the Cur ric ulum Vit
show you a way to fix it by spending less than
't . They need a * lot * more populism -

INTERVAL 1.117 - 2.195
CONTAINS 0.236%

memo either . In the recent UN report investigating Protective Edge
43 in the 2014 National Draft , Mc Govern made his
Knowledge Fund , a venture capital fund of $ 50 million
it was the Caps who struck first when Alex O ve
projected costs for power from natural gas supplied power plants ,

INTERVAL 0.039 - 1.117
CONTAINS 43.214%

and found the private route was faster . Their
fit their locker room and culture , and they 're desperately
border of the hands , feet , and wrists .[ 1
A lot of what we know about Philadelphia
is a breath of fresh air in a TV landscape that

INTERVAL -1.038 - 0.039
CONTAINS 56.159%

--+ | ... | + -------------------- --+ + -------------------- --+ <
International goals As of 12 June 2016 [ 91
U . S . energy policy , something that the country
period . But Section 2 of the law wasn 't affected
the isolated settlement - city of Ariel and the Green line

INTERVAL -2.116 - -1.038
CONTAINS 0.390%

do nothing and continue making temporary repairs . City
the city is supposed to fix the sidewalks , at their
and whiff ling and w aff ling of the trolls )
Ferrari , believes the true pe cking order is yet to
ers atz " social ism " devoid of social content
Token Where
Token ID6350
Feature activation-8.80e-02

Pos logit contributions
 unden+1.029
 rall+1.004
 arrang+0.940
 reluct+0.933
fort+0.915
Neg logit contributions
ocket-0.895
adiator-0.858
Explore-0.854
 replay-0.844
rium-0.838
Token Primary
Token ID21087
Feature activation+4.52e-01

Pos logit contributions
 unden+0.196
 rall+0.192
 arrang+0.182
 reluct+0.181
fort+0.178
Neg logit contributions
ocket-0.102
adiator-0.096
Explore-0.095
 replay-0.094
rium-0.093
Token |
Token ID930
Feature activation-4.98e-01

Pos logit contributions
ocket+0.503
adiator+0.474
Explore+0.469
rium+0.459
 replay+0.458
Neg logit contributions
 unden-1.031
 rall-1.011
 arrang-0.959
 reluct-0.953
fort-0.936
Token Select
Token ID9683
Feature activation-4.84e-01

Pos logit contributions
 unden+0.917
 rall+0.893
 arrang+0.837
 reluct+0.831
fort+0.814
Neg logit contributions
ocket-0.773
adiator-0.739
Explore-0.736
 replay-0.726
rium-0.723
Token -
Token ID532
Feature activation-2.45e-01

Pos logit contributions
 unden+0.904
 rall+0.884
 arrang+0.828
 reluct+0.817
 '.+0.811
Neg logit contributions
ocket-0.731
adiator-0.704
Explore-0.695
 replay-0.687
rium-0.684
TokenExp
Token ID16870
Feature activation+2.19e+00

Pos logit contributions
 unden+0.575
 rall+0.564
 arrang+0.537
 reluct+0.532
fort+0.526
Neg logit contributions
ocket-0.254
adiator-0.239
Explore-0.236
 replay-0.231
rium-0.230
Tokenand
Token ID392
Feature activation-1.32e-01

Pos logit contributions
ocket+2.190
Explore+2.083
adiator+2.009
rium+1.994
 replay+1.963
Neg logit contributions
 unden-5.212
 rall-5.092
 reluct-4.908
 arrang-4.883
 Ern-4.695
TokenProperty
Token ID21746
Feature activation+1.31e+00

Pos logit contributions
 unden+0.304
 rall+0.300
 arrang+0.283
 '.+0.282
fort+0.280
Neg logit contributions
ocket-0.142
adiator-0.136
Explore-0.130
 replay-0.129
rium-0.129
Token B
Token ID347
Feature activation+1.08e-01

Pos logit contributions
ocket+2.207
Explore+2.111
adiator+2.090
paces+2.087
 replay+2.081
Neg logit contributions
 unden-2.214
 rall-2.121
 reluct-2.003
 arrang-1.996
fort-1.935
Tokenounds
Token ID3733
Feature activation+1.01e+00

Pos logit contributions
ocket+0.201
adiator+0.193
Explore+0.192
rium+0.191
paces+0.190
Neg logit contributions
 unden-0.165
 rall-0.161
 arrang-0.148
 reluct-0.147
 cir-0.142
Token |
Token ID930
Feature activation-4.20e-01

Pos logit contributions
ocket+1.553
Explore+1.479
adiator+1.466
paces+1.460
 replay+1.443
Neg logit contributions
 unden-1.865
 rall-1.801
 reluct-1.702
 arrang-1.699
fort-1.648
Token get
Token ID651
Feature activation+2.31e-01

Pos logit contributions
ocket+0.116
 replay+0.111
adiator+0.111
Explore+0.110
rium+0.109
Neg logit contributions
 unden-0.169
 rall-0.165
 arrang-0.156
 reluct-0.154
fort-0.150
Token worse
Token ID4785
Feature activation+2.90e-01

Pos logit contributions
ocket+0.327
adiator+0.310
 replay+0.308
Explore+0.307
rium+0.305
Neg logit contributions
 unden-0.455
 rall-0.448
 arrang-0.420
 reluct-0.415
fort-0.410
Token."
Token ID526
Feature activation+7.83e-01

Pos logit contributions
ocket+0.360
adiator+0.337
Explore+0.331
 replay+0.330
rium+0.329
Neg logit contributions
 unden-0.629
 rall-0.619
 arrang-0.581
 reluct-0.578
 '.-0.565
Token
Token ID198
Feature activation+2.82e-01

Pos logit contributions
ocket+0.947
Explore+0.901
adiator+0.893
 replay+0.883
rium+0.876
Neg logit contributions
 unden-1.769
 rall-1.714
 reluct-1.634
 arrang-1.632
 '.-1.532
Token
Token ID198
Feature activation+2.64e-01

Pos logit contributions
ocket+0.359
adiator+0.341
Explore+0.340
 replay+0.334
rium+0.332
Neg logit contributions
 unden-0.608
 rall-0.593
 arrang-0.562
 reluct-0.559
 '.-0.538
Token"…
Token ID24426
Feature activation+2.15e+00

Pos logit contributions
ocket+0.336
Explore+0.321
adiator+0.319
rium+0.311
 replay+0.310
Neg logit contributions
 unden-0.562
 rall-0.549
 arrang-0.519
 reluct-0.516
 '.-0.504
TokenAlright
Token ID31442
Feature activation+8.74e-01

Pos logit contributions
ocket+3.056
Explore+2.958
rium+2.901
Weak+2.883
adiator+2.877
Neg logit contributions
 unden-4.207
 rall-4.128
 arrang-3.858
 reluct-3.855
 '.-3.664
Token."
Token ID526
Feature activation+5.93e-01

Pos logit contributions
ocket+1.060
adiator+0.992
Explore+0.980
rium+0.972
 replay+0.972
Neg logit contributions
 unden-1.903
 rall-1.864
 arrang-1.749
 reluct-1.746
 '.-1.722
Token
Token ID198
Feature activation+1.31e-01

Pos logit contributions
ocket+0.726
Explore+0.690
adiator+0.685
 replay+0.676
rium+0.672
Neg logit contributions
 unden-1.317
 rall-1.279
 arrang-1.216
 reluct-1.214
 '.-1.156
Token
Token ID198
Feature activation+1.78e-01

Pos logit contributions
ocket+0.170
adiator+0.162
Explore+0.160
 replay+0.158
rium+0.157
Neg logit contributions
 unden-0.277
 rall-0.271
 arrang-0.256
 reluct-0.254
 '.-0.248
TokenSte
Token ID7447
Feature activation+6.12e-01

Pos logit contributions
ocket+0.230
Explore+0.219
adiator+0.219
rium+0.213
 replay+0.213
Neg logit contributions
 unden-0.374
 rall-0.366
 arrang-0.345
 reluct-0.343
 '.-0.336
Token Del
Token ID4216
Feature activation+6.62e-01

Pos logit contributions
 unden+0.246
 rall+0.240
 arrang+0.225
 reluct+0.222
fort+0.221
Neg logit contributions
ocket-0.204
adiator-0.198
Explore-0.196
rium-0.192
 replay-0.192
Token Sur
Token ID4198
Feature activation+9.52e-02

Pos logit contributions
ocket+1.366
adiator+1.323
Explore+1.318
 replay+1.308
rium+1.302
Neg logit contributions
 unden-0.878
 rall-0.849
 arrang-0.782
 reluct-0.759
 '.-0.739
Token featuring
Token ID9593
Feature activation+1.32e-01

Pos logit contributions
ocket+0.127
adiator+0.122
Explore+0.120
 replay+0.119
rium+0.118
Neg logit contributions
 unden-0.195
 rall-0.191
 arrang-0.180
 reluct-0.178
fort-0.176
Token Coach
Token ID16393
Feature activation+7.34e-02

Pos logit contributions
ocket+0.205
adiator+0.197
 replay+0.195
Explore+0.194
rium+0.193
Neg logit contributions
 unden-0.243
 rall-0.236
 arrang-0.222
 reluct-0.219
fort-0.215
Token (
Token ID357
Feature activation-1.11e-01

Pos logit contributions
ocket+0.120
adiator+0.116
Explore+0.115
 replay+0.114
rium+0.113
Neg logit contributions
 unden-0.129
 rall-0.125
 arrang-0.117
 reluct-0.116
 '.-0.113
TokenSurv
Token ID34652
Feature activation+1.98e+00

Pos logit contributions
 unden+0.226
 rall+0.222
 arrang+0.209
 reluct+0.207
fort+0.204
Neg logit contributions
ocket-0.149
adiator-0.142
Explore-0.141
 replay-0.139
rium-0.138
Tokeniv
Token ID452
Feature activation-4.81e-01

Pos logit contributions
ocket+2.529
adiator+2.372
iversity+2.335
 replay+2.322
Explore+2.317
Neg logit contributions
 unden-4.226
 rall-4.131
 arrang-3.896
 reluct-3.885
 '.-3.753
Tokenor
Token ID273
Feature activation-3.44e-01

Pos logit contributions
 unden+0.747
 rall+0.726
 arrang+0.672
 reluct+0.661
 '.+0.650
Neg logit contributions
ocket-0.881
adiator-0.852
Explore-0.845
 replay-0.837
rium-0.834
Token T
Token ID309
Feature activation+3.10e-01

Pos logit contributions
 unden+0.656
 rall+0.643
 arrang+0.601
 reluct+0.594
fort+0.591
Neg logit contributions
ocket-0.503
adiator-0.485
Explore-0.479
rium-0.472
paces-0.471
Tokenoc
Token ID420
Feature activation-2.03e-01

Pos logit contributions
ocket+0.440
adiator+0.423
Explore+0.418
 replay+0.412
rium+0.410
Neg logit contributions
 unden-0.608
 rall-0.595
 arrang-0.559
 reluct-0.552
fort-0.547
Tokenant
Token ID415
Feature activation-1.19e-01

Pos logit contributions
 unden+0.360
 rall+0.352
 arrang+0.327
fort+0.325
 reluct+0.324
Neg logit contributions
ocket-0.324
adiator-0.311
Explore-0.310
 replay-0.304
paces-0.303
Token card
Token ID2657
Feature activation+2.53e-01

Pos logit contributions
 unden+0.404
 rall+0.395
 arrang+0.371
 reluct+0.368
 '.+0.363
Neg logit contributions
ocket-0.284
adiator-0.272
Explore-0.269
 replay-0.265
rium-0.264
Token)
Token ID8
Feature activation-1.82e-01

Pos logit contributions
ocket+0.325
adiator+0.310
Explore+0.306
 replay+0.302
rium+0.300
Neg logit contributions
 unden-0.530
 rall-0.519
 arrang-0.490
 reluct-0.485
fort-0.480
Token
Token ID198
Feature activation+2.77e-01

Pos logit contributions
 unden+0.370
 rall+0.361
 arrang+0.341
 reluct+0.337
 '.+0.333
Neg logit contributions
ocket-0.245
adiator-0.235
Explore-0.232
 replay-0.230
rium-0.228
Token
Token ID198
Feature activation+2.34e-01

Pos logit contributions
ocket+0.354
adiator+0.337
Explore+0.335
 replay+0.330
rium+0.328
Neg logit contributions
 unden-0.596
 rall-0.581
 arrang-0.551
 reluct-0.547
 '.-0.528
TokenR
Token ID49
Feature activation-1.30e-01

Pos logit contributions
ocket+0.299
adiator+0.286
Explore+0.285
 replay+0.278
rium+0.277
Neg logit contributions
 unden-0.495
 rall-0.483
 arrang-0.458
 reluct-0.455
 '.-0.445
Tokenattle
Token ID1999
Feature activation+1.91e+00

Pos logit contributions
 unden+0.268
 rall+0.262
 arrang+0.248
 reluct+0.245
 '.+0.242
Neg logit contributions
ocket-0.172
adiator-0.165
Explore-0.161
 replay-0.159
rium-0.159
TokenSnake
Token ID49795
Feature activation+2.19e-01

Pos logit contributions
ocket+2.807
adiator+2.717
Explore+2.669
 replay+2.646
rium+2.627
Neg logit contributions
 unden-3.656
 rall-3.457
 arrang-3.359
 reluct-3.337
 '.-3.158
Token:
Token ID25
Feature activation+2.26e-01

Pos logit contributions
ocket+0.312
adiator+0.298
Explore+0.295
 replay+0.292
rium+0.290
Neg logit contributions
 unden-0.430
 rall-0.419
 arrang-0.396
 reluct-0.391
 '.-0.386
Token La
Token ID4689
Feature activation-1.08e-01

Pos logit contributions
ocket+0.350
adiator+0.337
Explore+0.334
 replay+0.332
rium+0.328
Neg logit contributions
 unden-0.415
 rall-0.401
 arrang-0.379
 reluct-0.375
fort-0.366
TokenN
Token ID45
Feature activation-6.91e-02

Pos logit contributions
 unden+0.205
 rall+0.199
 arrang+0.187
 reluct+0.186
 '.+0.182
Neg logit contributions
ocket-0.162
adiator-0.156
Explore-0.155
 replay-0.153
rium-0.152
Tokenm
Token ID76
Feature activation+5.31e-01

Pos logit contributions
 unden+0.136
 rall+0.132
 arrang+0.125
 reluct+0.124
 '.+0.121
Neg logit contributions
ocket-0.099
adiator-0.095
Explore-0.094
rium-0.092
 replay-0.092
Token)
Token ID8
Feature activation-2.84e-01

Pos logit contributions
ocket+0.667
adiator+0.628
Explore+0.627
 replay+0.625
rium+0.612
Neg logit contributions
 unden-0.931
 rall-0.896
 arrang-0.850
 reluct-0.847
 '.-0.831
Token
Token ID198
Feature activation-5.76e-02

Pos logit contributions
 unden+0.595
 rall+0.580
 arrang+0.550
 reluct+0.546
 '.+0.536
Neg logit contributions
ocket-0.372
adiator-0.353
Explore-0.352
 replay-0.343
rium-0.340
Token
Token ID198
Feature activation-9.30e-02

Pos logit contributions
 unden+0.120
 rall+0.118
 arrang+0.111
 reluct+0.110
 '.+0.108
Neg logit contributions
ocket-0.075
adiator-0.072
Explore-0.071
 replay-0.070
rium-0.070
Token(
Token ID7
Feature activation-2.09e-01

Pos logit contributions
 unden+0.189
 rall+0.185
 arrang+0.175
 reluct+0.173
 '.+0.169
Neg logit contributions
ocket-0.128
Explore-0.123
adiator-0.122
rium-0.118
paces-0.118
TokenK
Token ID42
Feature activation-2.94e-01

Pos logit contributions
 unden+0.421
 rall+0.411
 arrang+0.388
 reluct+0.384
 '.+0.378
Neg logit contributions
ocket-0.290
adiator-0.276
Explore-0.275
 replay-0.270
rium-0.269
Tokenath
Token ID776
Feature activation+1.91e+00

Pos logit contributions
 unden+0.538
 rall+0.525
 arrang+0.491
 reluct+0.486
 '.+0.479
Neg logit contributions
ocket-0.460
adiator-0.442
Explore-0.438
 replay-0.431
rium-0.430
Tokenleen
Token ID20042
Feature activation+9.79e-01

Pos logit contributions
ocket+1.893
adiator+1.744
Explore+1.700
rium+1.697
 replay+1.683
Neg logit contributions
 unden-4.615
 rall-4.475
 arrang-4.341
 reluct-4.269
 '.-4.179
Token Flynn
Token ID14654
Feature activation+3.35e-01

Pos logit contributions
ocket+1.409
adiator+1.334
 replay+1.328
Explore+1.327
rium+1.305
Neg logit contributions
 unden-1.920
 rall-1.847
 arrang-1.774
 reluct-1.751
 '.-1.696
Token)
Token ID8
Feature activation-1.68e-01

Pos logit contributions
ocket+0.442
adiator+0.418
Explore+0.414
 replay+0.408
rium+0.403
Neg logit contributions
 unden-0.695
 rall-0.678
 arrang-0.640
 reluct-0.638
 '.-0.630
Token
Token ID198
Feature activation+9.05e-02

Pos logit contributions
 unden+0.337
 rall+0.329
 arrang+0.311
 reluct+0.307
 '.+0.302
Neg logit contributions
ocket-0.234
adiator-0.221
Explore-0.220
 replay-0.215
rium-0.215
Token
Token ID198
Feature activation+9.23e-02

Pos logit contributions
ocket+0.117
adiator+0.111
Explore+0.111
 replay+0.109
rium+0.108
Neg logit contributions
 unden-0.191
 rall-0.187
 arrang-0.177
 reluct-0.175
 '.-0.171
Token customers
Token ID4297
Feature activation-3.35e-01

Pos logit contributions
 unden+0.270
 rall+0.262
 arrang+0.247
 reluct+0.244
fort+0.242
Neg logit contributions
ocket-0.210
adiator-0.201
Explore-0.200
 replay-0.199
rium-0.196
Token might
Token ID1244
Feature activation+5.06e-02

Pos logit contributions
 unden+0.664
 rall+0.648
 arrang+0.610
 reluct+0.603
fort+0.595
Neg logit contributions
ocket-0.471
adiator-0.451
Explore-0.446
 replay-0.441
rium-0.439
Token need
Token ID761
Feature activation+2.00e-01

Pos logit contributions
ocket+0.074
 replay+0.072
adiator+0.071
Explore+0.071
paces+0.070
Neg logit contributions
 unden-0.098
 rall-0.095
 arrang-0.089
 reluct-0.088
fort-0.086
Token to
Token ID284
Feature activation+1.38e-01

Pos logit contributions
ocket+0.263
adiator+0.253
 replay+0.251
Explore+0.250
rium+0.244
Neg logit contributions
 unden-0.411
 rall-0.402
 arrang-0.379
 reluct-0.375
 '.-0.370
Token be
Token ID307
Feature activation+9.54e-02

Pos logit contributions
ocket+0.187
 replay+0.182
adiator+0.179
Explore+0.177
paces+0.176
Neg logit contributions
 unden-0.284
 rall-0.277
 arrang-0.260
 reluct-0.259
fort-0.253
Token dial
Token ID5980
Feature activation+1.90e+00

Pos logit contributions
ocket+0.146
adiator+0.140
 replay+0.139
Explore+0.138
iversity+0.136
Neg logit contributions
 unden-0.177
 rall-0.174
 arrang-0.162
 reluct-0.161
fort-0.158
Tokened
Token ID276
Feature activation+2.57e-01

Pos logit contributions
ocket+2.187
 replay+2.070
adiator+2.026
Explore+2.019
iversity+1.972
Neg logit contributions
 unden-4.206
 rall-4.113
 arrang-3.932
 reluct-3.905
 '.-3.774
Token back
Token ID736
Feature activation+1.38e-01

Pos logit contributions
ocket+0.377
adiator+0.363
 replay+0.361
Explore+0.358
rium+0.352
Neg logit contributions
 unden-0.491
 rall-0.481
 arrang-0.451
 reluct-0.447
fort-0.436
Token.
Token ID13
Feature activation-3.80e-02

Pos logit contributions
ocket+0.184
adiator+0.176
 replay+0.173
Explore+0.173
paces+0.170
Neg logit contributions
 unden-0.284
 rall-0.278
 arrang-0.262
 reluct-0.259
fort-0.253
Token In
Token ID554
Feature activation-1.41e-01

Pos logit contributions
 unden+0.079
 rall+0.077
 arrang+0.073
 reluct+0.072
fort+0.070
Neg logit contributions
ocket-0.051
Explore-0.049
adiator-0.049
 replay-0.048
rium-0.047
Token a
Token ID257
Feature activation+8.73e-03

Pos logit contributions
 unden+0.258
 rall+0.250
 arrang+0.235
 reluct+0.233
 '.+0.228
Neg logit contributions
ocket-0.223
adiator-0.214
Explore-0.211
 replay-0.211
rium-0.208
Token addition
Token ID3090
Feature activation-1.52e-01

Pos logit contributions
ocket+0.150
 replay+0.144
adiator+0.144
Explore+0.143
rium+0.141
Neg logit contributions
 unden-0.187
 rall-0.182
 arrang-0.171
 reluct-0.170
fort-0.167
Token of
Token ID286
Feature activation+8.71e-02

Pos logit contributions
 unden+0.335
 rall+0.328
 arrang+0.311
 reluct+0.308
fort+0.304
Neg logit contributions
ocket-0.180
adiator-0.172
Explore-0.169
 replay-0.167
rium-0.166
Token crisp
Token ID23453
Feature activation+8.90e-01

Pos logit contributions
ocket+0.131
 replay+0.128
adiator+0.127
Explore+0.126
rium+0.124
Neg logit contributions
 unden-0.164
 rall-0.159
 arrang-0.150
 reluct-0.149
fort-0.146
Token high
Token ID1029
Feature activation+1.86e-01

Pos logit contributions
ocket+1.158
 replay+1.116
adiator+1.111
Explore+1.095
iversity+1.072
Neg logit contributions
 unden-1.848
 rall-1.804
 reluct-1.706
 arrang-1.705
 '.-1.663
Token-
Token ID12
Feature activation+2.39e-01

Pos logit contributions
ocket+0.189
adiator+0.179
 replay+0.177
Explore+0.176
rium+0.172
Neg logit contributions
 unden-0.438
 rall-0.431
 arrang-0.409
 reluct-0.406
fort-0.400
Tokendefinition
Token ID46758
Feature activation+1.85e+00

Pos logit contributions
ocket+0.248
adiator+0.235
Explore+0.232
 replay+0.231
rium+0.228
Neg logit contributions
 unden-0.564
 rall-0.556
 arrang-0.526
 reluct-0.524
 '.-0.511
Token graphics
Token ID9382
Feature activation-1.33e-01

Pos logit contributions
 replay+2.125
ocket+2.075
adiator+1.984
Explore+1.956
rium+1.898
Neg logit contributions
 unden-4.115
 rall-4.002
 reluct-3.856
 arrang-3.808
fort-3.727
Token and
Token ID290
Feature activation+6.20e-02

Pos logit contributions
 unden+0.274
 rall+0.269
 arrang+0.252
 reluct+0.252
 '.+0.247
Neg logit contributions
ocket-0.176
adiator-0.169
Explore-0.168
 replay-0.167
paces-0.165
Token Wii
Token ID16591
Feature activation-1.07e-01

Pos logit contributions
ocket+0.095
 replay+0.094
adiator+0.092
Explore+0.092
rium+0.090
Neg logit contributions
 unden-0.114
 rall-0.111
 arrang-0.104
 reluct-0.104
fort-0.101
Token Motion
Token ID20843
Feature activation+5.10e-01

Pos logit contributions
 unden+0.206
 rall+0.202
 arrang+0.189
 reluct+0.187
fort+0.185
Neg logit contributions
ocket-0.155
adiator-0.148
Explore-0.147
 replay-0.145
rium-0.144
TokenPlus
Token ID17860
Feature activation+6.05e-01

Pos logit contributions
ocket+0.763
adiator+0.732
Explore+0.732
 replay+0.725
rium+0.715
Neg logit contributions
 unden-0.961
 rall-0.938
 arrang-0.882
 reluct-0.873
 '.-0.855
Token
Token ID198
Feature activation+3.31e-01

Pos logit contributions
ocket+1.049
adiator+0.979
Explore+0.975
rium+0.968
 replay+0.963
Neg logit contributions
 unden-1.833
 rall-1.799
 arrang-1.696
 reluct-1.674
 '.-1.662
Token
Token ID198
Feature activation+3.30e-01

Pos logit contributions
ocket+0.421
adiator+0.400
Explore+0.399
 replay+0.392
rium+0.390
Neg logit contributions
 unden-0.712
 rall-0.695
 arrang-0.658
 reluct-0.654
 '.-0.631
Token
Token ID13697
Feature activation+2.25e-02

Pos logit contributions
ocket+0.447
Explore+0.429
adiator+0.425
rium+0.417
 replay+0.414
Neg logit contributions
 unden-0.677
 rall-0.662
 arrang-0.624
 reluct-0.620
 '.-0.604
TokenOh
Token ID5812
Feature activation+5.68e-01

Pos logit contributions
ocket+0.029
adiator+0.028
Explore+0.028
 replay+0.027
rium+0.027
Neg logit contributions
 unden-0.047
 rall-0.046
 arrang-0.043
 reluct-0.043
fort-0.042
Token my
Token ID616
Feature activation+1.28e-01

Pos logit contributions
ocket+0.724
adiator+0.688
Explore+0.676
rium+0.670
 replay+0.668
Neg logit contributions
 unden-1.201
 rall-1.180
 arrang-1.109
 reluct-1.103
 '.-1.084
Token….
Token ID11580
Feature activation+1.83e+00

Pos logit contributions
ocket+0.174
adiator+0.166
Explore+0.164
 replay+0.162
rium+0.162
Neg logit contributions
 unden-0.260
 rall-0.254
 arrang-0.239
 reluct-0.237
 '.-0.234
Token How
Token ID1374
Feature activation-1.59e-01

Pos logit contributions
ocket+2.656
Explore+2.551
adiator+2.531
rium+2.520
paces+2.493
Neg logit contributions
 unden-3.491
 rall-3.416
 arrang-3.173
 reluct-3.169
 '.-3.084
Token bad
Token ID2089
Feature activation-5.53e-01

Pos logit contributions
 unden+0.308
 rall+0.302
 arrang+0.280
 reluct+0.278
 '.+0.273
Neg logit contributions
ocket-0.234
adiator-0.222
Explore-0.221
 replay-0.220
rium-0.218
Token is
Token ID318
Feature activation+1.00e-01

Pos logit contributions
 unden+1.128
 rall+1.104
 arrang+1.042
 reluct+1.030
fort+1.019
Neg logit contributions
ocket-0.743
adiator-0.712
Explore-0.703
 replay-0.693
rium-0.690
Token it
Token ID340
Feature activation+8.87e-02

Pos logit contributions
ocket+0.128
adiator+0.120
Explore+0.120
 replay+0.118
rium+0.118
Neg logit contributions
 unden-0.212
 rall-0.208
 arrang-0.195
 reluct-0.194
fort-0.191
Token?」
Token ID42943
Feature activation+8.35e-01

Pos logit contributions
ocket+0.111
adiator+0.104
Explore+0.103
rium+0.102
 replay+0.102
Neg logit contributions
 unden-0.191
 rall-0.187
 arrang-0.175
 reluct-0.175
 '.-0.172
Token streaming
Token ID11305
Feature activation+4.97e-01

Pos logit contributions
ocket+0.142
 replay+0.137
adiator+0.136
Explore+0.136
rium+0.134
Neg logit contributions
 unden-0.154
 rall-0.149
 arrang-0.138
 reluct-0.138
fort-0.135
Token five
Token ID1936
Feature activation+2.30e-02

Pos logit contributions
ocket+0.732
 replay+0.713
adiator+0.707
Explore+0.704
paces+0.688
Neg logit contributions
 unden-0.937
 rall-0.911
 reluct-0.861
 arrang-0.854
fort-0.832
Token videos
Token ID5861
Feature activation+8.24e-01

Pos logit contributions
ocket+0.035
adiator+0.034
 replay+0.034
Explore+0.034
paces+0.033
Neg logit contributions
 unden-0.042
 rall-0.041
 arrang-0.039
 reluct-0.038
fort-0.038
Token of
Token ID286
Feature activation-3.62e-02

Pos logit contributions
ocket+1.150
 replay+1.095
adiator+1.089
paces+1.083
Explore+1.074
Neg logit contributions
 unden-1.650
 rall-1.608
 reluct-1.515
 arrang-1.513
fort-1.451
Token high
Token ID1029
Feature activation+2.54e-01

Pos logit contributions
 unden+0.068
 rall+0.066
 reluct+0.063
 arrang+0.063
fort+0.061
Neg logit contributions
ocket-0.053
 replay-0.052
adiator-0.052
Explore-0.051
rium-0.051
Token definition
Token ID6770
Feature activation+1.82e+00

Pos logit contributions
ocket+0.289
 replay+0.283
adiator+0.275
Explore+0.273
iversity+0.268
Neg logit contributions
 unden-0.564
 rall-0.557
 arrang-0.529
 reluct-0.525
fort-0.513
Token video
Token ID2008
Feature activation+6.38e-01

Pos logit contributions
 replay+2.488
ocket+2.436
adiator+2.362
Explore+2.352
 crawl+2.307
Neg logit contributions
 unden-3.561
 rall-3.472
 reluct-3.338
 arrang-3.295
fort-3.209
Token a
Token ID257
Feature activation+1.37e-01

Pos logit contributions
ocket+0.899
 replay+0.875
adiator+0.863
Explore+0.855
paces+0.845
Neg logit contributions
 unden-1.247
 rall-1.224
 reluct-1.145
 arrang-1.143
fort-1.114
Token day
Token ID1110
Feature activation-7.43e-02

Pos logit contributions
ocket+0.210
 replay+0.200
adiator+0.200
Explore+0.198
rium+0.196
Neg logit contributions
 unden-0.255
 rall-0.247
 arrang-0.234
 reluct-0.230
fort-0.225
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
 unden+0.154
 rall+0.151
 arrang+0.142
 reluct+0.141
fort+0.138
Neg logit contributions
ocket-0.098
adiator-0.094
 replay-0.092
Explore-0.092
paces-0.091
Token
Token ID198
Feature activation+7.57e-02

Pos logit contributions
ocket+0.265
Explore+0.253
adiator+0.252
 replay+0.250
rium+0.246
Neg logit contributions
 unden-0.391
 rall-0.382
 arrang-0.359
 reluct-0.357
fort-0.345
Token mon
Token ID937
Feature activation+1.79e-02

Pos logit contributions
ocket+0.094
adiator+0.090
 replay+0.090
Explore+0.089
rium+0.088
Neg logit contributions
 unden-0.114
 rall-0.111
 arrang-0.104
 reluct-0.103
fort-0.101
Tokenologue
Token ID39795
Feature activation-3.06e-01

Pos logit contributions
ocket+0.033
adiator+0.032
 replay+0.032
rium+0.032
Explore+0.031
Neg logit contributions
 unden-0.028
 rall-0.027
 arrang-0.025
 reluct-0.025
 '.-0.024
Token given
Token ID1813
Feature activation-4.97e-02

Pos logit contributions
 unden+0.602
 rall+0.589
 arrang+0.554
 reluct+0.547
fort+0.541
Neg logit contributions
ocket-0.433
adiator-0.416
Explore-0.411
 replay-0.405
rium-0.404
Token by
Token ID416
Feature activation-1.70e-03

Pos logit contributions
 unden+0.096
 rall+0.094
 arrang+0.088
 reluct+0.087
 '.+0.086
Neg logit contributions
ocket-0.072
adiator-0.069
Explore-0.068
 replay-0.068
rium-0.067
Token Jimmy
Token ID12963
Feature activation+4.82e-01

Pos logit contributions
 unden+0.003
 rall+0.003
 arrang+0.003
 reluct+0.003
fort+0.003
Neg logit contributions
ocket-0.003
adiator-0.003
Explore-0.003
 replay-0.003
rium-0.003
Token Kimmel
Token ID46552
Feature activation+1.81e+00

Pos logit contributions
ocket+0.457
adiator+0.421
 replay+0.413
Explore+0.407
iversity+0.404
Neg logit contributions
 unden-1.181
 rall-1.159
 arrang-1.113
 reluct-1.100
 '.-1.073
Token concerning
Token ID9305
Feature activation+1.57e-01

Pos logit contributions
ocket+2.537
adiator+2.398
 replay+2.386
Explore+2.356
iversity+2.321
Neg logit contributions
 unden-3.596
 rall-3.506
 arrang-3.291
 reluct-3.253
 '.-3.170
Token his
Token ID465
Feature activation+1.55e-01

Pos logit contributions
ocket+0.230
adiator+0.221
Explore+0.218
 replay+0.218
rium+0.216
Neg logit contributions
 unden-0.302
 rall-0.295
 arrang-0.277
 reluct-0.274
fort-0.271
Token newborn
Token ID23856
Feature activation+7.34e-01

Pos logit contributions
ocket+0.227
adiator+0.217
 replay+0.217
Explore+0.215
rium+0.212
Neg logit contributions
 unden-0.296
 rall-0.289
 arrang-0.270
 reluct-0.267
fort-0.265
Token son
Token ID3367
Feature activation-1.98e-01

Pos logit contributions
ocket+1.015
adiator+0.972
 replay+0.965
Explore+0.952
rium+0.948
Neg logit contributions
 unden-1.456
 rall-1.432
 arrang-1.338
 reluct-1.328
 '.-1.306
Token.
Token ID13
Feature activation-4.04e-02

Pos logit contributions
 unden+0.389
 rall+0.381
 arrang+0.358
 reluct+0.354
 '.+0.349
Neg logit contributions
ocket-0.282
adiator-0.269
Explore-0.265
 replay-0.264
rium-0.262
Token and
Token ID290
Feature activation-2.04e-01

Pos logit contributions
ocket+0.150
adiator+0.143
Explore+0.141
 replay+0.141
rium+0.139
Neg logit contributions
 unden-0.210
 rall-0.205
 arrang-0.193
 reluct-0.191
fort-0.189
Token spread
Token ID4104
Feature activation+5.70e-01

Pos logit contributions
 unden+0.381
 rall+0.372
 arrang+0.348
 reluct+0.344
fort+0.340
Neg logit contributions
ocket-0.310
adiator-0.298
Explore-0.295
 replay-0.292
rium-0.291
Token them
Token ID606
Feature activation-1.21e-01

Pos logit contributions
ocket+0.770
adiator+0.736
Explore+0.729
 replay+0.726
rium+0.722
Neg logit contributions
 unden-1.159
 rall-1.122
 arrang-1.060
 reluct-1.057
fort-1.037
Token near
Token ID1474
Feature activation+3.19e-01

Pos logit contributions
 unden+0.228
 rall+0.223
 arrang+0.208
 reluct+0.207
fort+0.203
Neg logit contributions
ocket-0.182
adiator-0.174
Explore-0.172
 replay-0.172
rium-0.169
Token the
Token ID262
Feature activation+3.68e-02

Pos logit contributions
ocket+0.483
adiator+0.460
Explore+0.458
rium+0.456
 replay+0.455
Neg logit contributions
 unden-0.597
 rall-0.581
 arrang-0.547
 reluct-0.539
fort-0.532
Token sunk
Token ID24790
Feature activation+1.81e+00

Pos logit contributions
ocket+0.053
adiator+0.051
Explore+0.050
 replay+0.050
rium+0.050
Neg logit contributions
 unden-0.071
 rall-0.070
 arrang-0.066
 reluct-0.065
fort-0.064
Tokenen
Token ID268
Feature activation+4.45e-01

Pos logit contributions
ocket+3.049
adiator+2.919
rium+2.881
Explore+2.862
iversity+2.856
Neg logit contributions
 unden-3.125
 rall-3.057
 arrang-2.857
 reluct-2.831
 '.-2.723
Token fireplace
Token ID44250
Feature activation+6.70e-01

Pos logit contributions
ocket+0.546
adiator+0.517
Explore+0.507
 replay+0.505
rium+0.501
Neg logit contributions
 unden-0.964
 rall-0.946
 arrang-0.892
 reluct-0.885
 '.-0.874
Token.
Token ID13
Feature activation+1.54e-01

Pos logit contributions
ocket+0.852
adiator+0.797
Explore+0.790
 replay+0.787
rium+0.781
Neg logit contributions
 unden-1.425
 rall-1.398
 reluct-1.309
 arrang-1.309
 '.-1.285
Token After
Token ID2293
Feature activation-3.59e-02

Pos logit contributions
ocket+0.212
Explore+0.201
adiator+0.199
 replay+0.198
rium+0.197
Neg logit contributions
 unden-0.316
 rall-0.308
 arrang-0.290
 reluct-0.289
fort-0.279
Token that
Token ID326
Feature activation+6.45e-02

Pos logit contributions
 unden+0.070
 rall+0.068
 arrang+0.064
 reluct+0.064
 '.+0.063
Neg logit contributions
ocket-0.051
adiator-0.049
 replay-0.049
Explore-0.048
rium-0.048
Token
Token ID198
Feature activation-3.24e-02

Pos logit contributions
 unden+0.320
 rall+0.314
 arrang+0.296
 reluct+0.292
fort+0.291
Neg logit contributions
ocket-0.207
adiator-0.198
Explore-0.195
 replay-0.192
rium-0.192
TokenChart
Token ID45488
Feature activation+1.33e-01

Pos logit contributions
 unden+0.067
 rall+0.066
 arrang+0.062
 reluct+0.062
 '.+0.061
Neg logit contributions
ocket-0.042
adiator-0.040
Explore-0.040
 replay-0.039
rium-0.039
Tokenered
Token ID1068
Feature activation-1.12e-01

Pos logit contributions
ocket+0.178
adiator+0.171
Explore+0.171
 replay+0.169
rium+0.169
Neg logit contributions
 unden-0.271
 rall-0.265
 arrang-0.249
 reluct-0.246
 '.-0.243
Token Institute
Token ID5136
Feature activation-6.10e-01

Pos logit contributions
 unden+0.220
 rall+0.216
 arrang+0.202
 reluct+0.200
fort+0.197
Neg logit contributions
ocket-0.159
Explore-0.151
adiator-0.151
 replay-0.150
rium-0.148
Token of
Token ID286
Feature activation+2.79e-01

Pos logit contributions
 unden+1.280
 rall+1.253
 arrang+1.183
 reluct+1.170
 '.+1.156
Neg logit contributions
ocket-0.786
adiator-0.750
Explore-0.742
 replay-0.732
rium-0.727
Token Personnel
Token ID41623
Feature activation+1.79e+00

Pos logit contributions
ocket+0.370
adiator+0.352
Explore+0.351
rium+0.347
 replay+0.345
Neg logit contributions
 unden-0.576
 rall-0.564
 arrang-0.533
 reluct-0.529
fort-0.518
Token and
Token ID290
Feature activation+1.87e-01

Pos logit contributions
ocket+2.402
Explore+2.299
 replay+2.260
rium+2.231
iversity+2.225
Neg logit contributions
 unden-3.644
 rall-3.587
 arrang-3.356
 reluct-3.333
fort-3.245
Token Development
Token ID7712
Feature activation-3.21e-01

Pos logit contributions
ocket+0.282
adiator+0.270
Explore+0.268
 replay+0.266
rium+0.265
Neg logit contributions
 unden-0.351
 rall-0.344
 arrang-0.321
 reluct-0.319
fort-0.313
Token "
Token ID366
Feature activation-9.29e-02

Pos logit contributions
 unden+0.639
 rall+0.626
 arrang+0.587
 reluct+0.581
fort+0.574
Neg logit contributions
ocket-0.450
adiator-0.430
Explore-0.427
 replay-0.422
rium-0.419
TokenOverall
Token ID16350
Feature activation+3.41e-01

Pos logit contributions
 unden+0.202
 rall+0.198
 arrang+0.188
 reluct+0.186
fort+0.183
Neg logit contributions
ocket-0.112
adiator-0.107
Explore-0.106
 replay-0.104
rium-0.103
Token,
Token ID11
Feature activation+3.09e-01

Pos logit contributions
ocket+0.467
adiator+0.449
Explore+0.443
 replay+0.440
iversity+0.436
Neg logit contributions
 unden-0.681
 rall-0.669
 arrang-0.627
 reluct-0.623
fort-0.615
Token
Token ID198
Feature activation+2.25e-01

Pos logit contributions
ocket+0.226
adiator+0.216
Explore+0.214
 replay+0.211
rium+0.210
Neg logit contributions
 unden-0.378
 rall-0.369
 arrang-0.349
 reluct-0.347
 '.-0.336
Token7
Token ID22
Feature activation+9.95e-02

Pos logit contributions
ocket+0.263
adiator+0.250
Explore+0.249
 replay+0.242
rium+0.241
Neg logit contributions
 unden-0.500
 rall-0.490
 arrang-0.465
 reluct-0.461
 '.-0.454
Token.
Token ID13
Feature activation-5.02e-02

Pos logit contributions
ocket+0.122
adiator+0.116
Explore+0.115
 replay+0.113
rium+0.112
Neg logit contributions
 unden-0.219
 rall-0.214
 arrang-0.203
 reluct-0.203
fort-0.194
Token Dw
Token ID19113
Feature activation+4.84e-01

Pos logit contributions
 unden+0.087
 rall+0.085
 arrang+0.079
 reluct+0.079
fort+0.076
Neg logit contributions
ocket-0.084
adiator-0.081
Explore-0.080
rium-0.079
 replay-0.079
Tokenark
Token ID668
Feature activation+2.13e-01

Pos logit contributions
ocket+0.687
adiator+0.660
Explore+0.646
rium+0.642
iversity+0.639
Neg logit contributions
 unden-0.956
 rall-0.937
 arrang-0.881
 reluct-0.874
 '.-0.859
Tokenadh
Token ID24411
Feature activation+1.78e+00

Pos logit contributions
ocket+0.244
adiator+0.231
Explore+0.226
rium+0.223
 replay+0.222
Neg logit contributions
 unden-0.478
 rall-0.468
 arrang-0.444
 reluct-0.440
 '.-0.435
Tokenish
Token ID680
Feature activation+5.01e-01

Pos logit contributions
ocket+2.544
adiator+2.413
rium+2.402
Explore+2.348
iversity+2.332
Neg logit contributions
 unden-3.514
 rall-3.452
 arrang-3.227
 reluct-3.209
 '.-3.121
Token Temple
Token ID10857
Feature activation+2.86e-01

Pos logit contributions
ocket+0.779
adiator+0.747
rium+0.737
Explore+0.735
 replay+0.729
Neg logit contributions
 unden-0.923
 rall-0.907
 arrang-0.843
 reluct-0.837
 '.-0.817
Token
Token ID198
Feature activation+3.98e-01

Pos logit contributions
ocket+0.367
adiator+0.350
Explore+0.345
rium+0.341
 replay+0.339
Neg logit contributions
 unden-0.601
 rall-0.589
 arrang-0.556
 reluct-0.552
 '.-0.541
Token
Token ID198
Feature activation+4.02e-01

Pos logit contributions
ocket+0.504
adiator+0.479
Explore+0.478
 replay+0.470
rium+0.467
Neg logit contributions
 unden-0.863
 rall-0.842
 arrang-0.798
 reluct-0.794
 '.-0.762
TokenAddress
Token ID20231
Feature activation+2.15e-01

Pos logit contributions
ocket+0.608
Explore+0.585
adiator+0.583
rium+0.571
 replay+0.569
Neg logit contributions
 unden-0.762
 rall-0.743
 arrang-0.697
 reluct-0.695
 '.-0.670
Token May
Token ID1737
Feature activation+2.09e-01

Pos logit contributions
ocket+0.431
adiator+0.416
Explore+0.414
 replay+0.411
iversity+0.405
Neg logit contributions
 unden-0.501
 rall-0.489
 arrang-0.459
 reluct-0.456
 '.-0.443
Token 5
Token ID642
Feature activation+2.93e-01

Pos logit contributions
ocket+0.308
adiator+0.295
Explore+0.292
rium+0.288
 replay+0.288
Neg logit contributions
 unden-0.401
 rall-0.392
 arrang-0.369
 reluct-0.365
 '.-0.358
Token).
Token ID737
Feature activation+2.20e-01

Pos logit contributions
ocket+0.362
adiator+0.343
Explore+0.339
 replay+0.336
iversity+0.332
Neg logit contributions
 unden-0.631
 rall-0.616
 arrang-0.585
 reluct-0.579
 '.-0.569
Token The
Token ID383
Feature activation+1.86e-01

Pos logit contributions
ocket+0.308
Explore+0.293
adiator+0.293
 replay+0.289
rium+0.287
Neg logit contributions
 unden-0.443
 rall-0.433
 arrang-0.408
 reluct-0.406
fort-0.392
Token most
Token ID749
Feature activation+2.10e-01

Pos logit contributions
ocket+0.295
adiator+0.282
 replay+0.281
Explore+0.280
rium+0.277
Neg logit contributions
 unden-0.334
 rall-0.326
 arrang-0.304
 reluct-0.300
fort-0.295
Token recent
Token ID2274
Feature activation+1.78e+00

Pos logit contributions
ocket+0.321
adiator+0.306
 replay+0.305
Explore+0.304
rium+0.300
Neg logit contributions
 unden-0.387
 rall-0.380
 arrang-0.355
 reluct-0.352
fort-0.347
Token example
Token ID1672
Feature activation+4.96e-01

Pos logit contributions
ocket+2.638
 replay+2.553
Explore+2.503
adiator+2.480
rium+2.444
Neg logit contributions
 unden-3.339
 rall-3.234
 reluct-3.014
 arrang-3.011
fort-2.960
Token of
Token ID286
Feature activation+5.49e-02

Pos logit contributions
ocket+0.642
adiator+0.611
Explore+0.603
 replay+0.598
rium+0.593
Neg logit contributions
 unden-1.039
 rall-1.018
 arrang-0.960
 reluct-0.950
 '.-0.938
Token the
Token ID262
Feature activation+8.82e-02

Pos logit contributions
ocket+0.082
adiator+0.079
 replay+0.078
Explore+0.078
rium+0.077
Neg logit contributions
 unden-0.103
 rall-0.101
 arrang-0.095
 reluct-0.094
fort-0.093
Token wrong
Token ID2642
Feature activation+5.04e-02

Pos logit contributions
ocket+0.145
 replay+0.139
adiator+0.139
Explore+0.137
rium+0.136
Neg logit contributions
 unden-0.153
 rall-0.150
 arrang-0.139
 reluct-0.137
fort-0.136
Tokenness
Token ID1108
Feature activation+4.89e-01

Pos logit contributions
ocket+0.070
adiator+0.066
 replay+0.066
Explore+0.065
rium+0.065
Neg logit contributions
 unden-0.102
 rall-0.099
 arrang-0.093
 reluct-0.093
 '.-0.091
Token up
Token ID510
Feature activation+1.02e-02

Pos logit contributions
 unden+0.037
 rall+0.036
 arrang+0.034
 reluct+0.033
fort+0.033
Neg logit contributions
ocket-0.027
adiator-0.026
Explore-0.026
 replay-0.026
rium-0.025
Token but
Token ID475
Feature activation-4.46e-02

Pos logit contributions
ocket+0.014
adiator+0.013
 replay+0.013
Explore+0.013
paces+0.013
Neg logit contributions
 unden-0.021
 rall-0.020
 arrang-0.019
 reluct-0.019
fort-0.019
Token I
Token ID314
Feature activation+1.16e-01

Pos logit contributions
 unden+0.086
 rall+0.084
 arrang+0.079
 reluct+0.078
fort+0.078
Neg logit contributions
ocket-0.065
adiator-0.062
 replay-0.061
Explore-0.061
rium-0.060
Token would
Token ID561
Feature activation+1.60e-01

Pos logit contributions
ocket+0.168
 replay+0.163
Explore+0.159
adiator+0.159
rium+0.157
Neg logit contributions
 unden-0.226
 rall-0.220
 arrang-0.205
 reluct-0.202
fort-0.199
Token still
Token ID991
Feature activation+1.16e-01

Pos logit contributions
ocket+0.243
 replay+0.237
adiator+0.231
Explore+0.231
paces+0.228
Neg logit contributions
 unden-0.302
 rall-0.293
 arrang-0.274
 reluct-0.272
fort-0.264
Token recommend
Token ID4313
Feature activation+1.76e+00

Pos logit contributions
ocket+0.181
 replay+0.174
adiator+0.172
Explore+0.172
paces+0.169
Neg logit contributions
 unden-0.212
 rall-0.205
 arrang-0.192
 reluct-0.191
fort-0.187
Token we
Token ID356
Feature activation+3.52e-01

Pos logit contributions
ocket+2.419
 replay+2.318
adiator+2.281
Explore+2.258
iversity+2.204
Neg logit contributions
 unden-3.505
 rall-3.397
 arrang-3.215
 reluct-3.192
fort-3.168
Token sign
Token ID1051
Feature activation-2.41e-01

Pos logit contributions
ocket+0.481
 replay+0.463
Explore+0.455
adiator+0.454
paces+0.444
Neg logit contributions
 unden-0.716
 rall-0.695
 arrang-0.655
 reluct-0.654
fort-0.644
Token him
Token ID683
Feature activation+3.64e-03

Pos logit contributions
 unden+0.485
 rall+0.473
 arrang+0.445
 reluct+0.443
fort+0.436
Neg logit contributions
ocket-0.332
adiator-0.318
Explore-0.313
 replay-0.312
rium-0.306
Token for
Token ID329
Feature activation+5.16e-02

Pos logit contributions
ocket+0.005
adiator+0.004
 replay+0.004
Explore+0.004
paces+0.004
Neg logit contributions
 unden-0.008
 rall-0.007
 arrang-0.007
 reluct-0.007
fort-0.007
Token up
Token ID510
Feature activation-7.01e-02

Pos logit contributions
ocket+0.076
adiator+0.073
 replay+0.073
Explore+0.073
rium+0.071
Neg logit contributions
 unden-0.098
 rall-0.096
 arrang-0.090
 reluct-0.089
fort-0.088
Token chain
Token ID6333
Feature activation+2.64e-01

Pos logit contributions
ocket+0.391
Explore+0.371
adiator+0.371
 replay+0.368
rium+0.363
Neg logit contributions
 unden-0.511
 rall-0.500
 reluct-0.468
 arrang-0.467
 '.-0.455
Token.
Token ID13
Feature activation+2.28e-02

Pos logit contributions
ocket+0.338
adiator+0.322
Explore+0.319
 replay+0.315
paces+0.314
Neg logit contributions
 unden-0.556
 rall-0.548
 arrang-0.515
 reluct-0.510
fort-0.498
Token
Token ID198
Feature activation-1.41e-01

Pos logit contributions
ocket+0.032
adiator+0.031
Explore+0.031
 replay+0.030
rium+0.030
Neg logit contributions
 unden-0.045
 rall-0.044
 arrang-0.042
 reluct-0.041
fort-0.040
Token
Token ID198
Feature activation-1.59e-01

Pos logit contributions
 unden+0.288
 rall+0.282
 arrang+0.266
 reluct+0.262
fort+0.262
Neg logit contributions
ocket-0.186
adiator-0.179
Explore-0.176
 replay-0.174
rium-0.173
TokenM
Token ID44
Feature activation+1.84e-01

Pos logit contributions
 unden+0.349
 rall+0.342
 arrang+0.324
 reluct+0.320
fort+0.319
Neg logit contributions
ocket-0.189
adiator-0.180
Explore-0.176
 replay-0.175
rium-0.174
Tokenounds
Token ID3733
Feature activation+1.74e+00

Pos logit contributions
ocket+0.239
adiator+0.229
Explore+0.225
rium+0.221
 replay+0.221
Neg logit contributions
 unden-0.384
 rall-0.376
 arrang-0.356
 reluct-0.352
 '.-0.347
Token of
Token ID286
Feature activation+3.31e-02

Pos logit contributions
ocket+2.093
Explore+1.991
adiator+1.972
paces+1.950
 replay+1.943
Neg logit contributions
 unden-3.787
 rall-3.686
 arrang-3.514
 reluct-3.490
fort-3.375
Token tail
Token ID7894
Feature activation-2.85e-01

Pos logit contributions
ocket+0.050
adiator+0.049
Explore+0.048
 replay+0.048
rium+0.047
Neg logit contributions
 unden-0.061
 rall-0.060
 arrang-0.056
 reluct-0.056
fort-0.055
Tokenings
Token ID654
Feature activation+1.71e-02

Pos logit contributions
 unden+0.557
 rall+0.544
 arrang+0.512
 reluct+0.506
fort+0.499
Neg logit contributions
ocket-0.409
adiator-0.392
Explore-0.388
 replay-0.383
rium-0.381
Token from
Token ID422
Feature activation+5.68e-02

Pos logit contributions
ocket+0.025
adiator+0.024
Explore+0.024
 replay+0.024
paces+0.023
Neg logit contributions
 unden-0.033
 rall-0.032
 arrang-0.030
 reluct-0.030
 '.-0.029
Token mineral
Token ID18352
Feature activation+4.61e-01

Pos logit contributions
ocket+0.087
adiator+0.085
Explore+0.083
 replay+0.082
rium+0.082
Neg logit contributions
 unden-0.105
 rall-0.102
 arrang-0.097
 reluct-0.095
fort-0.094
Token secession
Token ID43314
Feature activation+5.95e-01

Pos logit contributions
ocket+0.265
 replay+0.255
adiator+0.254
Explore+0.253
rium+0.250
Neg logit contributions
 unden-0.291
 rall-0.281
 arrang-0.262
 reluct-0.259
fort-0.257
Tokenist
Token ID396
Feature activation-2.22e-01

Pos logit contributions
ocket+0.905
adiator+0.873
 replay+0.863
Explore+0.862
rium+0.852
Neg logit contributions
 unden-1.103
 rall-1.065
 arrang-1.005
 reluct-0.990
fort-0.979
Token bloc
Token ID24003
Feature activation-2.21e-01

Pos logit contributions
 unden+0.437
 rall+0.425
 arrang+0.400
 reluct+0.396
fort+0.392
Neg logit contributions
ocket-0.314
adiator-0.301
Explore-0.298
 replay-0.297
rium-0.295
Token after
Token ID706
Feature activation+2.67e-02

Pos logit contributions
 unden+0.444
 rall+0.434
 arrang+0.408
 reluct+0.403
fort+0.398
Neg logit contributions
ocket-0.306
adiator-0.293
Explore-0.289
 replay-0.286
rium-0.285
Token the
Token ID262
Feature activation+1.92e-01

Pos logit contributions
ocket+0.040
adiator+0.038
Explore+0.038
 replay+0.038
rium+0.037
Neg logit contributions
 unden-0.051
 rall-0.050
 arrang-0.047
 reluct-0.046
fort-0.046
Token recent
Token ID2274
Feature activation+1.74e+00

Pos logit contributions
ocket+0.298
 replay+0.287
adiator+0.285
Explore+0.284
rium+0.279
Neg logit contributions
 unden-0.350
 rall-0.340
 arrang-0.318
 reluct-0.316
fort-0.313
Token surge
Token ID13853
Feature activation+2.30e-01

Pos logit contributions
ocket+2.640
 replay+2.598
Explore+2.507
adiator+2.488
 crawl+2.453
Neg logit contributions
 unden-3.146
 rall-3.023
fort-2.832
 reluct-2.828
 arrang-2.819
Token of
Token ID286
Feature activation+2.12e-01

Pos logit contributions
ocket+0.321
adiator+0.309
Explore+0.305
 replay+0.302
rium+0.300
Neg logit contributions
 unden-0.458
 rall-0.448
 arrang-0.421
 reluct-0.416
fort-0.412
Token popular
Token ID2968
Feature activation+3.81e-01

Pos logit contributions
ocket+0.334
adiator+0.321
 replay+0.320
Explore+0.318
rium+0.315
Neg logit contributions
 unden-0.380
 rall-0.370
 arrang-0.347
 reluct-0.343
fort-0.341
Token mobil
Token ID17754
Feature activation-1.27e-01

Pos logit contributions
ocket+0.623
adiator+0.598
 replay+0.598
Explore+0.591
rium+0.586
Neg logit contributions
 unden-0.658
 rall-0.643
 arrang-0.600
 reluct-0.590
fort-0.586
Tokenisation
Token ID5612
Feature activation-3.24e-01

Pos logit contributions
 unden+0.244
 rall+0.237
 arrang+0.222
 reluct+0.221
 '.+0.217
Neg logit contributions
ocket-0.188
adiator-0.180
Explore-0.178
 replay-0.176
rium-0.175
Token federal
Token ID2717
Feature activation-2.79e-01

Pos logit contributions
ocket+0.118
adiator+0.114
Explore+0.112
 replay+0.112
rium+0.111
Neg logit contributions
 unden-0.142
 rall-0.137
 arrang-0.129
 reluct-0.127
fort-0.126
Token reviews
Token ID8088
Feature activation+8.80e-01

Pos logit contributions
 unden+0.516
 rall+0.503
 arrang+0.472
 reluct+0.466
fort+0.460
Neg logit contributions
ocket-0.430
adiator-0.414
Explore-0.409
 replay-0.406
rium-0.403
Token of
Token ID286
Feature activation+1.13e-01

Pos logit contributions
ocket+1.130
adiator+1.068
Explore+1.046
paces+1.044
 replay+1.041
Neg logit contributions
 unden-1.878
 rall-1.837
 arrang-1.723
 reluct-1.702
fort-1.680
Token whether
Token ID1771
Feature activation-5.54e-01

Pos logit contributions
ocket+0.167
adiator+0.160
Explore+0.158
 replay+0.157
rium+0.156
Neg logit contributions
 unden-0.214
 rall-0.209
 arrang-0.196
 reluct-0.194
fort-0.192
Token health
Token ID1535
Feature activation+7.43e-01

Pos logit contributions
 unden+1.059
 rall+1.035
 arrang+0.972
 reluct+0.960
 '.+0.951
Neg logit contributions
ocket-0.815
adiator-0.785
Explore-0.774
 replay-0.762
rium-0.762
Token plans
Token ID3352
Feature activation+1.74e+00

Pos logit contributions
ocket+1.114
Explore+1.058
adiator+1.058
 replay+1.055
iversity+1.042
Neg logit contributions
 unden-1.411
 rall-1.373
 arrang-1.283
 reluct-1.268
fort-1.252
Token in
Token ID287
Feature activation+1.89e-01

Pos logit contributions
ocket+2.399
 replay+2.281
Explore+2.238
paces+2.237
adiator+2.209
Neg logit contributions
 unden-3.522
 rall-3.387
 arrang-3.195
 reluct-3.183
fort-3.108
Token the
Token ID262
Feature activation+1.16e-01

Pos logit contributions
ocket+0.292
adiator+0.279
Explore+0.277
 replay+0.276
rium+0.273
Neg logit contributions
 unden-0.352
 rall-0.341
 arrang-0.322
 reluct-0.317
fort-0.312
Token ACA
Token ID27628
Feature activation+3.19e-01

Pos logit contributions
ocket+0.182
adiator+0.175
Explore+0.173
 replay+0.172
rium+0.171
Neg logit contributions
 unden-0.212
 rall-0.206
 arrang-0.193
 reluct-0.190
fort-0.188
Token market
Token ID1910
Feature activation+7.17e-01

Pos logit contributions
ocket+0.448
adiator+0.427
 replay+0.424
Explore+0.424
rium+0.418
Neg logit contributions
 unden-0.636
 rall-0.619
 arrang-0.584
 reluct-0.577
fort-0.567
Tokenplaces
Token ID23625
Feature activation+6.12e-01

Pos logit contributions
ocket+1.023
adiator+0.968
Explore+0.966
 replay+0.960
rium+0.954
Neg logit contributions
 unden-1.419
 rall-1.382
 arrang-1.300
 reluct-1.290
 '.-1.256
Token Temple
Token ID10857
Feature activation+2.63e-01

Pos logit contributions
ocket+0.367
adiator+0.353
Explore+0.348
rium+0.347
 replay+0.344
Neg logit contributions
 unden-0.386
 rall-0.377
 arrang-0.351
 reluct-0.348
 '.-0.339
Token
Token ID198
Feature activation+4.64e-01

Pos logit contributions
ocket+0.337
adiator+0.321
Explore+0.316
rium+0.312
 replay+0.311
Neg logit contributions
 unden-0.554
 rall-0.543
 arrang-0.512
 reluct-0.508
 '.-0.500
Token
Token ID198
Feature activation+4.56e-01

Pos logit contributions
ocket+0.583
adiator+0.554
Explore+0.554
 replay+0.544
rium+0.540
Neg logit contributions
 unden-1.012
 rall-0.987
 arrang-0.936
 reluct-0.933
 '.-0.891
TokenAddress
Token ID20231
Feature activation+2.49e-01

Pos logit contributions
ocket+0.692
Explore+0.664
adiator+0.664
rium+0.649
 replay+0.648
Neg logit contributions
 unden-0.863
 rall-0.842
 arrang-0.790
 reluct-0.786
 '.-0.759
Token:
Token ID25
Feature activation+3.62e-01

Pos logit contributions
ocket+0.289
adiator+0.275
Explore+0.273
 replay+0.268
rium+0.266
Neg logit contributions
 unden-0.561
 rall-0.549
 arrang-0.521
 reluct-0.518
 '.-0.502
Token Sector
Token ID25892
Feature activation+1.73e+00

Pos logit contributions
ocket+0.605
adiator+0.583
Explore+0.579
rium+0.574
 replay+0.573
Neg logit contributions
 unden-0.626
 rall-0.609
 arrang-0.570
 reluct-0.566
fort-0.541
Token 20
Token ID1160
Feature activation-2.50e-01

Pos logit contributions
ocket+2.676
rium+2.570
adiator+2.563
Explore+2.529
iversity+2.519
Neg logit contributions
 unden-3.191
 rall-3.103
 arrang-2.927
 reluct-2.925
fort-2.733
Token,
Token ID11
Feature activation+4.81e-01

Pos logit contributions
 unden+0.525
 rall+0.514
 arrang+0.485
 reluct+0.481
 '.+0.474
Neg logit contributions
ocket-0.324
adiator-0.309
Explore-0.305
 replay-0.300
rium-0.299
TokenJ
Token ID41
Feature activation-3.05e-02

Pos logit contributions
ocket+0.810
adiator+0.781
Explore+0.776
rium+0.771
 replay+0.766
Neg logit contributions
 unden-0.820
 rall-0.800
 arrang-0.745
 reluct-0.738
fort-0.712
Token Road
Token ID5567
Feature activation-2.30e-01

Pos logit contributions
 unden+0.059
 rall+0.058
 arrang+0.054
 reluct+0.054
 '.+0.053
Neg logit contributions
ocket-0.044
adiator-0.042
Explore-0.042
rium-0.041
 replay-0.041
Token,
Token ID11
Feature activation+3.27e-01

Pos logit contributions
 unden+0.480
 rall+0.471
 arrang+0.444
 reluct+0.440
 '.+0.433
Neg logit contributions
ocket-0.299
adiator-0.285
Explore-0.281
rium-0.278
 replay-0.277
Token priority
Token ID8475
Feature activation-1.10e-01

Pos logit contributions
ocket+0.122
adiator+0.116
 replay+0.115
Explore+0.114
rium+0.114
Neg logit contributions
 unden-0.169
 rall-0.166
 arrang-0.155
 reluct-0.154
 '.-0.152
Token.
Token ID13
Feature activation+1.68e-01

Pos logit contributions
 unden+0.226
 rall+0.223
 arrang+0.208
 reluct+0.208
fort+0.204
Neg logit contributions
ocket-0.145
adiator-0.138
 replay-0.136
Explore-0.136
rium-0.135
Token
Token ID198
Feature activation+8.09e-02

Pos logit contributions
ocket+0.244
Explore+0.233
adiator+0.231
 replay+0.229
rium+0.228
Neg logit contributions
 unden-0.331
 rall-0.322
 arrang-0.304
 reluct-0.303
fort-0.289
Token
Token ID198
Feature activation+5.36e-02

Pos logit contributions
ocket+0.106
adiator+0.101
Explore+0.100
 replay+0.098
rium+0.098
Neg logit contributions
 unden-0.169
 rall-0.165
 arrang-0.156
 reluct-0.154
 '.-0.152
TokenBut
Token ID1537
Feature activation+6.01e-01

Pos logit contributions
ocket+0.068
adiator+0.065
Explore+0.065
 replay+0.063
rium+0.063
Neg logit contributions
 unden-0.114
 rall-0.111
 arrang-0.105
 reluct-0.104
 '.-0.102
Token….
Token ID11580
Feature activation+1.73e+00

Pos logit contributions
ocket+0.917
adiator+0.870
 replay+0.867
Explore+0.865
rium+0.857
Neg logit contributions
 unden-1.121
 rall-1.088
 arrang-1.020
 reluct-1.009
 '.-0.997
Token
Token ID198
Feature activation-2.00e-02

Pos logit contributions
ocket+2.503
Explore+2.373
adiator+2.369
rium+2.351
 replay+2.350
Neg logit contributions
 unden-3.308
 rall-3.211
 arrang-3.012
 reluct-2.988
 '.-2.938
Token
Token ID198
Feature activation+3.34e-02

Pos logit contributions
 unden+0.041
 rall+0.040
 arrang+0.038
 reluct+0.038
fort+0.037
Neg logit contributions
ocket-0.026
adiator-0.025
Explore-0.025
 replay-0.025
rium-0.024
Token"
Token ID1
Feature activation+4.92e-01

Pos logit contributions
ocket+0.043
adiator+0.040
Explore+0.040
 replay+0.039
rium+0.039
Neg logit contributions
 unden-0.071
 rall-0.070
 arrang-0.066
 reluct-0.065
 '.-0.064
TokenAh
Token ID10910
Feature activation+3.88e-01

Pos logit contributions
ocket+0.653
Explore+0.626
adiator+0.620
rium+0.608
 replay+0.605
Neg logit contributions
 unden-1.023
 rall-1.001
 arrang-0.944
 reluct-0.939
 '.-0.913
Token."
Token ID526
Feature activation+5.45e-01

Pos logit contributions
ocket+0.510
adiator+0.486
Explore+0.479
rium+0.474
 replay+0.474
Neg logit contributions
 unden-0.807
 rall-0.792
 arrang-0.744
 reluct-0.738
 '.-0.726
Token //
Token ID3373
Feature activation-1.46e-01

Pos logit contributions
ocket+0.233
adiator+0.224
Explore+0.223
 replay+0.222
rium+0.219
Neg logit contributions
 unden-0.239
 rall-0.232
 arrang-0.217
 reluct-0.214
fort-0.211
Token The
Token ID383
Feature activation+1.34e-01

Pos logit contributions
 unden+0.273
 rall+0.266
 arrang+0.250
 reluct+0.247
fort+0.244
Neg logit contributions
ocket-0.222
adiator-0.213
Explore-0.212
 replay-0.210
rium-0.208
Token previous
Token ID2180
Feature activation+3.89e-01

Pos logit contributions
ocket+0.204
adiator+0.195
 replay+0.195
Explore+0.195
rium+0.191
Neg logit contributions
 unden-0.249
 rall-0.242
 arrang-0.227
 reluct-0.225
fort-0.223
Token board
Token ID3096
Feature activation+4.34e-01

Pos logit contributions
ocket+0.435
adiator+0.409
 replay+0.407
Explore+0.405
rium+0.395
Neg logit contributions
 unden-0.882
 rall-0.861
 arrang-0.817
 reluct-0.810
fort-0.803
Token |
Token ID930
Feature activation-2.45e-01

Pos logit contributions
ocket+0.556
adiator+0.528
Explore+0.521
 replay+0.521
rium+0.511
Neg logit contributions
 unden-0.912
 rall-0.893
 arrang-0.843
 reluct-0.837
fort-0.826
Token ----------------
Token ID34400
Feature activation-2.12e+00

Pos logit contributions
 unden+0.450
 rall+0.439
 arrang+0.411
 reluct+0.406
fort+0.401
Neg logit contributions
ocket-0.379
adiator-0.365
Explore-0.361
 replay-0.357
rium-0.355
Token-------------
Token ID32501
Feature activation-1.24e+00

Pos logit contributions
 unden+3.876
 rall+3.827
 arrang+3.553
 '.+3.512
 reluct+3.493
Neg logit contributions
ocket-3.194
adiator-3.083
Explore-3.020
rium-3.000
paces-2.975
Token recursive
Token ID45115
Feature activation+8.46e-01

Pos logit contributions
 unden+2.189
 rall+2.143
 arrang+1.997
 reluct+1.965
 '.+1.949
Neg logit contributions
ocket-2.001
adiator-1.934
Explore-1.908
rium-1.884
 replay-1.875
Token without
Token ID1231
Feature activation+4.27e-02

Pos logit contributions
ocket+1.132
adiator+1.079
 replay+1.079
Explore+1.072
Weak+1.046
Neg logit contributions
 unden-1.724
 rall-1.681
 arrang-1.582
 reluct-1.574
fort-1.552
Token ind
Token ID773
Feature activation+4.71e-01

Pos logit contributions
ocket+0.064
adiator+0.061
Explore+0.060
 replay+0.060
rium+0.060
Neg logit contributions
 unden-0.081
 rall-0.079
 arrang-0.074
 reluct-0.073
fort-0.072
Tokenirection
Token ID4154
Feature activation+3.58e-01

Pos logit contributions
ocket+0.454
adiator+0.419
 replay+0.413
Explore+0.412
paces+0.410
Neg logit contributions
 unden-1.149
 rall-1.127
 arrang-1.073
 reluct-1.069
 '.-1.045
Token by
Token ID416
Feature activation-3.40e-01

Pos logit contributions
 unden+0.178
 rall+0.174
 arrang+0.163
 reluct+0.161
 '.+0.160
Neg logit contributions
ocket-0.150
adiator-0.145
Explore-0.143
 replay-0.141
rium-0.141
Token clicking
Token ID12264
Feature activation-3.35e-01

Pos logit contributions
 unden+0.532
 rall+0.519
 arrang+0.480
 reluct+0.472
fort+0.468
Neg logit contributions
ocket-0.613
adiator-0.595
Explore-0.589
 replay-0.583
rium-0.582
Token the
Token ID262
Feature activation-3.75e-01

Pos logit contributions
 unden+0.580
 rall+0.568
 arrang+0.528
 '.+0.521
fort+0.520
Neg logit contributions
ocket-0.545
adiator-0.527
Explore-0.520
 replay-0.514
rium-0.513
Token box
Token ID3091
Feature activation-2.75e-02

Pos logit contributions
 unden+0.631
 rall+0.614
 arrang+0.572
 reluct+0.564
fort+0.554
Neg logit contributions
ocket-0.639
adiator-0.617
Explore-0.611
 replay-0.606
rium-0.603
Token.
Token ID13
Feature activation-2.84e-01

Pos logit contributions
 unden+0.061
 rall+0.059
 arrang+0.056
 reluct+0.056
fort+0.054
Neg logit contributions
ocket-0.034
adiator-0.032
Explore-0.032
 replay-0.031
rium-0.031
Token Invalid
Token ID17665
Feature activation-2.05e+00

Pos logit contributions
 unden+0.226
 rall+0.212
 arrang+0.180
 reluct+0.175
fort+0.165
Neg logit contributions
ocket-0.737
adiator-0.720
Explore-0.718
 replay-0.712
rium-0.710
Token email
Token ID3053
Feature activation-1.13e-01

Pos logit contributions
 unden+2.745
 rall+2.731
 '.+2.559
 cir+2.530
fort+2.515
Neg logit contributions
ocket-3.938
adiator-3.871
Explore-3.840
paces-3.793
Weak-3.737
Token address
Token ID2209
Feature activation-2.44e-01

Pos logit contributions
 unden+0.213
 rall+0.206
 arrang+0.193
 reluct+0.192
fort+0.185
Neg logit contributions
ocket-0.177
adiator-0.169
 replay-0.168
Explore-0.167
rium-0.167
Token.
Token ID13
Feature activation-5.03e-01

Pos logit contributions
 unden+0.513
 rall+0.502
 arrang+0.474
 reluct+0.469
 '.+0.466
Neg logit contributions
ocket-0.311
adiator-0.298
Explore-0.293
 replay-0.289
rium-0.288
Token Please
Token ID4222
Feature activation-6.66e-01

Pos logit contributions
 unden+0.899
 rall+0.875
 arrang+0.818
 reluct+0.811
fort+0.786
Neg logit contributions
ocket-0.816
adiator-0.783
Explore-0.782
 replay-0.771
rium-0.767
Token re
Token ID302
Feature activation-1.78e-01

Pos logit contributions
 unden+0.973
 rall+0.943
 arrang+0.868
 reluct+0.854
fort+0.839
Neg logit contributions
ocket-1.283
adiator-1.245
Explore-1.234
 replay-1.224
rium-1.219
Token by
Token ID416
Feature activation-3.02e-01

Pos logit contributions
 unden+0.141
 rall+0.138
 arrang+0.129
 '.+0.127
 reluct+0.127
Neg logit contributions
ocket-0.120
adiator-0.116
Explore-0.115
 replay-0.113
rium-0.113
Token clicking
Token ID12264
Feature activation-4.61e-01

Pos logit contributions
 unden+0.468
 rall+0.457
 arrang+0.423
 reluct+0.415
fort+0.413
Neg logit contributions
ocket-0.547
adiator-0.530
Explore-0.526
 replay-0.520
rium-0.519
Token the
Token ID262
Feature activation-4.12e-01

Pos logit contributions
 unden+0.792
 rall+0.775
 arrang+0.720
 '.+0.714
fort+0.713
Neg logit contributions
ocket-0.752
adiator-0.728
Explore-0.718
 replay-0.710
rium-0.708
Token box
Token ID3091
Feature activation-4.10e-03

Pos logit contributions
 unden+0.681
 rall+0.664
 arrang+0.616
 reluct+0.607
fort+0.602
Neg logit contributions
ocket-0.708
adiator-0.685
Explore-0.678
 replay-0.670
rium-0.669
Token.
Token ID13
Feature activation-3.87e-01

Pos logit contributions
 unden+0.009
 rall+0.009
 arrang+0.008
 reluct+0.008
fort+0.008
Neg logit contributions
ocket-0.005
adiator-0.005
Explore-0.005
 replay-0.005
rium-0.005
Token Invalid
Token ID17665
Feature activation-2.01e+00

Pos logit contributions
 unden+0.305
 rall+0.287
 arrang+0.243
 reluct+0.236
fort+0.224
Neg logit contributions
ocket-1.009
adiator-0.986
Explore-0.982
 replay-0.974
rium-0.972
Token email
Token ID3053
Feature activation+9.40e-04

Pos logit contributions
 unden+2.708
 rall+2.690
 '.+2.504
 cir+2.487
fort+2.466
Neg logit contributions
ocket-3.868
adiator-3.796
Explore-3.760
paces-3.725
Weak-3.667
Token address
Token ID2209
Feature activation-1.14e-01

Pos logit contributions
ocket+0.001
adiator+0.001
 replay+0.001
rium+0.001
Explore+0.001
Neg logit contributions
 unden-0.002
 rall-0.002
 arrang-0.002
 reluct-0.002
fort-0.002
Token.
Token ID13
Feature activation-5.38e-01

Pos logit contributions
 unden+0.242
 rall+0.237
 arrang+0.224
 reluct+0.222
fort+0.219
Neg logit contributions
ocket-0.145
adiator-0.138
Explore-0.136
 replay-0.134
rium-0.134
Token Please
Token ID4222
Feature activation-6.66e-01

Pos logit contributions
 unden+0.962
 rall+0.938
 arrang+0.877
 reluct+0.869
fort+0.842
Neg logit contributions
ocket-0.871
adiator-0.836
Explore-0.835
 replay-0.822
rium-0.819
Token re
Token ID302
Feature activation-7.29e-02

Pos logit contributions
 unden+0.970
 rall+0.941
 arrang+0.865
 reluct+0.851
fort+0.837
Neg logit contributions
ocket-1.284
adiator-1.246
Explore-1.235
 replay-1.224
rium-1.220
Token by
Token ID416
Feature activation-3.74e-01

Pos logit contributions
 unden+0.177
 rall+0.173
 arrang+0.162
 reluct+0.160
fort+0.159
Neg logit contributions
ocket-0.151
adiator-0.145
Explore-0.144
 replay-0.141
rium-0.141
Token clicking
Token ID12264
Feature activation-4.81e-01

Pos logit contributions
 unden+0.576
 rall+0.562
 arrang+0.519
 reluct+0.510
fort+0.509
Neg logit contributions
ocket-0.682
adiator-0.662
Explore-0.657
 replay-0.649
rium-0.649
Token the
Token ID262
Feature activation-4.24e-01

Pos logit contributions
 unden+0.827
 rall+0.809
 arrang+0.752
 '.+0.744
fort+0.743
Neg logit contributions
ocket-0.783
adiator-0.759
Explore-0.749
 replay-0.740
rium-0.738
Token box
Token ID3091
Feature activation-1.64e-01

Pos logit contributions
 unden+0.705
 rall+0.687
 arrang+0.638
 reluct+0.629
fort+0.622
Neg logit contributions
ocket-0.729
adiator-0.705
Explore-0.697
 replay-0.690
rium-0.688
Token.
Token ID13
Feature activation-3.91e-01

Pos logit contributions
 unden+0.352
 rall+0.345
 arrang+0.326
 reluct+0.323
fort+0.316
Neg logit contributions
ocket-0.204
adiator-0.194
Explore-0.192
 replay-0.190
rium-0.188
Token Invalid
Token ID17665
Feature activation-1.97e+00

Pos logit contributions
 unden+0.298
 rall+0.281
 arrang+0.237
 reluct+0.229
fort+0.220
Neg logit contributions
ocket-1.024
adiator-1.002
Explore-0.996
 replay-0.989
rium-0.987
Token email
Token ID3053
Feature activation-7.66e-02

Pos logit contributions
 unden+2.669
 rall+2.647
 '.+2.460
 cir+2.446
fort+2.426
Neg logit contributions
ocket-3.777
adiator-3.711
Explore-3.676
paces-3.640
Weak-3.576
Token address
Token ID2209
Feature activation-8.66e-02

Pos logit contributions
 unden+0.145
 rall+0.140
 arrang+0.131
 reluct+0.131
fort+0.126
Neg logit contributions
ocket-0.118
adiator-0.113
 replay-0.113
rium-0.112
Explore-0.112
Token.
Token ID13
Feature activation-5.26e-01

Pos logit contributions
 unden+0.183
 rall+0.180
 arrang+0.170
 reluct+0.168
fort+0.166
Neg logit contributions
ocket-0.110
adiator-0.105
Explore-0.103
 replay-0.102
rium-0.102
Token Please
Token ID4222
Feature activation-5.87e-01

Pos logit contributions
 unden+0.926
 rall+0.902
 arrang+0.843
 reluct+0.833
fort+0.814
Neg logit contributions
ocket-0.862
adiator-0.829
Explore-0.825
 replay-0.814
rium-0.811
Token re
Token ID302
Feature activation-1.15e-01

Pos logit contributions
 unden+0.861
 rall+0.835
 arrang+0.768
 reluct+0.756
fort+0.742
Neg logit contributions
ocket-1.129
adiator-1.094
Explore-1.085
 replay-1.076
rium-1.072
Token that
Token ID326
Feature activation-1.20e-02

Pos logit contributions
 unden+1.023
 rall+1.001
 arrang+0.943
 reluct+0.932
 '.+0.918
Neg logit contributions
ocket-0.694
adiator-0.663
Explore-0.655
 replay-0.655
rium-0.644
Token's
Token ID338
Feature activation+3.15e-02

Pos logit contributions
 unden+0.023
 rall+0.023
 arrang+0.021
 reluct+0.021
fort+0.021
Neg logit contributions
ocket-0.017
 replay-0.017
adiator-0.016
Explore-0.016
rium-0.016
Token had
Token ID550
Feature activation+7.11e-02

Pos logit contributions
ocket+0.048
 replay+0.047
adiator+0.047
Explore+0.046
rium+0.045
Neg logit contributions
 unden-0.058
 rall-0.056
 arrang-0.053
 reluct-0.053
fort-0.052
Token a
Token ID257
Feature activation+1.40e-01

Pos logit contributions
ocket+0.103
 replay+0.101
adiator+0.099
Explore+0.099
rium+0.097
Neg logit contributions
 unden-0.137
 rall-0.133
 arrang-0.125
 reluct-0.124
fort-0.122
Token story
Token ID1621
Feature activation-5.84e-01

Pos logit contributions
ocket+0.219
 replay+0.215
adiator+0.210
Explore+0.209
rium+0.205
Neg logit contributions
 unden-0.255
 rall-0.248
 arrang-0.233
 reluct-0.231
fort-0.227
Token patch
Token ID8529
Feature activation-1.97e+00

Pos logit contributions
 unden+1.123
 rall+1.097
 arrang+1.031
 reluct+1.018
 '.+1.007
Neg logit contributions
ocket-0.854
adiator-0.820
Explore-0.810
 replay-0.799
rium-0.797
Token.
Token ID13
Feature activation+3.75e-02

Pos logit contributions
 unden+3.793
 rall+3.703
 arrang+3.510
fort+3.467
 '.+3.465
Neg logit contributions
ocket-2.774
adiator-2.687
Explore-2.666
rium-2.611
Weak-2.606
Token That
Token ID1320
Feature activation+1.06e-01

Pos logit contributions
ocket+0.049
Explore+0.047
adiator+0.047
 replay+0.047
rium+0.046
Neg logit contributions
 unden-0.079
 rall-0.077
 arrang-0.073
 reluct-0.073
fort-0.070
Token's
Token ID338
Feature activation-6.22e-02

Pos logit contributions
ocket+0.153
 replay+0.150
Explore+0.146
adiator+0.146
rium+0.144
Neg logit contributions
 unden-0.204
 rall-0.199
 arrang-0.186
 reluct-0.184
 '.-0.181
Token obviously
Token ID6189
Feature activation-2.33e-01

Pos logit contributions
 unden+0.115
 rall+0.112
 arrang+0.105
 reluct+0.104
fort+0.102
Neg logit contributions
ocket-0.095
adiator-0.092
 replay-0.091
Explore-0.091
rium-0.090
Token not
Token ID407
Feature activation+1.89e-02

Pos logit contributions
 unden+0.426
 rall+0.417
 arrang+0.390
 reluct+0.385
fort+0.380
Neg logit contributions
ocket-0.359
 replay-0.346
adiator-0.345
Explore-0.344
rium-0.338
TokenSI
Token ID11584
Feature activation+1.22e-01

Pos logit contributions
ocket+0.097
adiator+0.093
Explore+0.092
 replay+0.091
rium+0.090
Neg logit contributions
 unden-0.134
 rall-0.131
 arrang-0.124
 reluct-0.122
fort-0.121
Token military
Token ID2422
Feature activation+2.96e-01

Pos logit contributions
ocket+0.187
adiator+0.182
 replay+0.179
Explore+0.178
rium+0.177
Neg logit contributions
 unden-0.224
 rall-0.217
 arrang-0.204
 reluct-0.201
fort-0.199
Token was
Token ID373
Feature activation-2.86e-01

Pos logit contributions
ocket+0.461
adiator+0.443
 replay+0.443
Explore+0.436
rium+0.434
Neg logit contributions
 unden-0.538
 rall-0.520
 arrang-0.485
 reluct-0.480
 '.-0.475
Token under
Token ID739
Feature activation-1.52e-01

Pos logit contributions
 unden+0.535
 rall+0.524
 arrang+0.492
 reluct+0.485
 '.+0.479
Neg logit contributions
ocket-0.433
adiator-0.416
Explore-0.410
 replay-0.409
rium-0.404
Token the
Token ID262
Feature activation-3.09e-01

Pos logit contributions
 unden+0.267
 rall+0.260
 arrang+0.243
 reluct+0.240
 '.+0.236
Neg logit contributions
ocket-0.244
adiator-0.238
Explore-0.233
 replay-0.232
rium-0.231
Token command
Token ID3141
Feature activation-1.94e+00

Pos logit contributions
 unden+0.597
 rall+0.580
 arrang+0.546
 reluct+0.541
fort+0.534
Neg logit contributions
ocket-0.445
adiator-0.430
Explore-0.424
 replay-0.424
rium-0.418
Token of
Token ID286
Feature activation-1.06e-01

Pos logit contributions
 unden+3.998
 rall+3.918
 arrang+3.733
 reluct+3.680
fort+3.675
Neg logit contributions
ocket-2.493
Explore-2.393
adiator-2.363
 replay-2.320
paces-2.306
Token General
Token ID3611
Feature activation-2.18e-01

Pos logit contributions
 unden+0.181
 rall+0.176
 arrang+0.164
 reluct+0.162
 '.+0.159
Neg logit contributions
ocket-0.179
adiator-0.174
Explore-0.170
 replay-0.170
rium-0.169
Token Alfred
Token ID22044
Feature activation-8.31e-01

Pos logit contributions
 unden+0.378
 rall+0.367
 arrang+0.343
 reluct+0.339
 '.+0.333
Neg logit contributions
ocket-0.362
adiator-0.349
Explore-0.344
 replay-0.342
rium-0.340
Tokeno
Token ID78
Feature activation-2.89e-03

Pos logit contributions
 unden+1.649
 rall+1.614
 arrang+1.518
 reluct+1.500
fort+1.486
Neg logit contributions
ocket-1.161
adiator-1.113
Explore-1.101
 replay-1.086
rium-1.081
Token Gu
Token ID1962
Feature activation-5.00e-01

Pos logit contributions
 unden+0.005
 rall+0.005
 arrang+0.005
 reluct+0.004
 '.+0.004
Neg logit contributions
ocket-0.005
adiator-0.005
Explore-0.005
 replay-0.005
rium-0.005
Token under
Token ID739
Feature activation-2.27e-01

Pos logit contributions
 unden+2.019
 rall+1.975
 arrang+1.858
 reluct+1.835
fort+1.817
Neg logit contributions
ocket-1.510
adiator-1.448
Explore-1.432
 replay-1.412
rium-1.404
Token Zh
Token ID10511
Feature activation+2.29e-01

Pos logit contributions
 unden+0.425
 rall+0.414
 arrang+0.387
 reluct+0.386
fort+0.379
Neg logit contributions
ocket-0.341
adiator-0.330
Explore-0.325
 replay-0.324
rium-0.322
Tokenuk
Token ID2724
Feature activation-1.03e+00

Pos logit contributions
ocket+0.311
adiator+0.298
Explore+0.294
 replay+0.290
rium+0.289
Neg logit contributions
 unden-0.465
 rall-0.454
 arrang-0.428
 reluct-0.424
 '.-0.417
Tokenov
Token ID709
Feature activation-7.96e-01

Pos logit contributions
 unden+2.137
 rall+2.123
fort+2.042
 '.+2.016
 arrang+1.991
Neg logit contributions
ocket-1.244
adiator-1.175
Explore-1.174
 replay-1.149
paces-1.137
Token's
Token ID338
Feature activation-2.60e-01

Pos logit contributions
 unden+1.537
 rall+1.500
 arrang+1.408
 reluct+1.395
fort+1.375
Neg logit contributions
ocket-1.158
adiator-1.115
Explore-1.098
 replay-1.089
rium-1.083
Token command
Token ID3141
Feature activation-1.94e+00

Pos logit contributions
 unden+0.504
 rall+0.491
 arrang+0.459
 reluct+0.458
fort+0.452
Neg logit contributions
ocket-0.375
adiator-0.360
 replay-0.357
Explore-0.356
rium-0.351
Token.[
Token ID3693
Feature activation+2.42e-01

Pos logit contributions
 unden+3.681
 rall+3.602
 arrang+3.404
 reluct+3.346
 '.+3.344
Neg logit contributions
ocket-2.821
adiator-2.699
Explore-2.695
 replay-2.636
rium-2.625
Token31
Token ID3132
Feature activation+2.67e-02

Pos logit contributions
ocket+0.258
Explore+0.243
adiator+0.243
 replay+0.236
paces+0.233
Neg logit contributions
 unden-0.566
 rall-0.554
 arrang-0.524
 reluct-0.522
 '.-0.511
Token]
Token ID60
Feature activation+1.15e-01

Pos logit contributions
ocket+0.044
adiator+0.042
Explore+0.042
 replay+0.041
iversity+0.041
Neg logit contributions
 unden-0.047
 rall-0.045
 arrang-0.043
 reluct-0.042
 '.-0.042
Token This
Token ID770
Feature activation-6.83e-02

Pos logit contributions
ocket+0.153
Explore+0.147
adiator+0.146
 replay+0.145
rium+0.143
Neg logit contributions
 unden-0.237
 rall-0.230
 reluct-0.219
 arrang-0.218
fort-0.211
Token front
Token ID2166
Feature activation-1.44e+00

Pos logit contributions
 unden+0.128
 rall+0.124
 reluct+0.115
 arrang+0.115
fort+0.114
Neg logit contributions
ocket-0.102
 replay-0.099
adiator-0.098
Explore-0.097
rium-0.096
Token handed
Token ID10158
Feature activation-4.08e-01

Pos logit contributions
 unden+0.027
 rall+0.026
 arrang+0.024
 reluct+0.024
fort+0.024
Neg logit contributions
ocket-0.021
adiator-0.020
Explore-0.020
 replay-0.020
rium-0.020
Token Libya
Token ID13465
Feature activation+8.38e-01

Pos logit contributions
 unden+0.674
 rall+0.656
 arrang+0.610
 reluct+0.601
fort+0.592
Neg logit contributions
ocket-0.707
adiator-0.683
Explore-0.676
 replay-0.670
rium-0.668
Token over
Token ID625
Feature activation-2.01e-01

Pos logit contributions
ocket+1.268
adiator+1.223
 replay+1.216
Explore+1.213
rium+1.199
Neg logit contributions
 unden-1.562
 rall-1.523
 arrang-1.434
 reluct-1.414
fort-1.384
Token to
Token ID284
Feature activation+8.10e-03

Pos logit contributions
 unden+0.432
 rall+0.424
 arrang+0.401
 reluct+0.396
 '.+0.392
Neg logit contributions
ocket-0.248
adiator-0.238
Explore-0.234
 replay-0.232
rium-0.229
Token a
Token ID257
Feature activation+7.33e-02

Pos logit contributions
ocket+0.012
adiator+0.012
Explore+0.012
 replay+0.012
rium+0.011
Neg logit contributions
 unden-0.015
 rall-0.015
 arrang-0.014
 reluct-0.014
fort-0.014
Token patch
Token ID8529
Feature activation-1.89e+00

Pos logit contributions
ocket+0.114
adiator+0.109
Explore+0.108
 replay+0.107
rium+0.107
Neg logit contributions
 unden-0.134
 rall-0.131
 arrang-0.123
 reluct-0.121
fort-0.120
Tokenwork
Token ID1818
Feature activation+1.50e-01

Pos logit contributions
 unden+3.784
 rall+3.729
 arrang+3.561
fort+3.528
 '.+3.498
Neg logit contributions
ocket-2.489
adiator-2.395
Explore-2.366
rium-2.362
paces-2.356
Token of
Token ID286
Feature activation-5.50e-03

Pos logit contributions
ocket+0.184
adiator+0.176
 replay+0.173
Explore+0.172
rium+0.170
Neg logit contributions
 unden-0.324
 rall-0.316
 arrang-0.299
 reluct-0.296
fort-0.293
Token tribal
Token ID17054
Feature activation+2.87e-01

Pos logit contributions
 unden+0.010
 rall+0.010
 arrang+0.009
 reluct+0.009
fort+0.009
Neg logit contributions
ocket-0.008
adiator-0.008
 replay-0.008
Explore-0.008
rium-0.008
Token and
Token ID290
Feature activation+1.32e-02

Pos logit contributions
ocket+0.402
adiator+0.390
 replay+0.387
Explore+0.381
iversity+0.376
Neg logit contributions
 unden-0.569
 rall-0.549
 arrang-0.518
 reluct-0.515
 '.-0.505
Token Al
Token ID978
Feature activation-3.27e-01

Pos logit contributions
ocket+0.020
adiator+0.020
Explore+0.019
 replay+0.019
rium+0.019
Neg logit contributions
 unden-0.024
 rall-0.024
 arrang-0.022
 reluct-0.022
fort-0.022
Token by
Token ID416
Feature activation-2.85e-01

Pos logit contributions
ocket+0.074
adiator+0.071
Explore+0.070
 replay+0.069
rium+0.069
Neg logit contributions
 unden-0.091
 rall-0.089
 arrang-0.083
 reluct-0.082
fort-0.081
Token clicking
Token ID12264
Feature activation-3.88e-01

Pos logit contributions
 unden+0.451
 rall+0.439
 arrang+0.407
 reluct+0.401
fort+0.395
Neg logit contributions
ocket-0.511
adiator-0.495
Explore-0.491
 replay-0.486
rium-0.484
Token the
Token ID262
Feature activation-3.49e-01

Pos logit contributions
 unden+0.678
 rall+0.663
 arrang+0.617
 reluct+0.608
 '.+0.607
Neg logit contributions
ocket-0.629
adiator-0.608
Explore-0.601
 replay-0.594
rium-0.592
Token box
Token ID3091
Feature activation+3.03e-03

Pos logit contributions
 unden+0.597
 rall+0.579
 arrang+0.541
 reluct+0.535
fort+0.520
Neg logit contributions
ocket-0.589
adiator-0.568
Explore-0.564
 replay-0.559
rium-0.556
Token.
Token ID13
Feature activation-4.03e-01

Pos logit contributions
ocket+0.004
adiator+0.003
Explore+0.003
 replay+0.003
rium+0.003
Neg logit contributions
 unden-0.007
 rall-0.007
 arrang-0.006
 reluct-0.006
fort-0.006
Token Invalid
Token ID17665
Feature activation-1.88e+00

Pos logit contributions
 unden+0.339
 rall+0.316
 arrang+0.272
 reluct+0.266
fort+0.245
Neg logit contributions
ocket-1.035
adiator-1.011
Explore-1.010
 replay-1.000
rium-0.998
Token email
Token ID3053
Feature activation+7.02e-02

Pos logit contributions
 unden+2.601
 rall+2.571
 '.+2.382
 cir+2.366
fort+2.358
Neg logit contributions
ocket-3.582
adiator-3.507
Explore-3.483
paces-3.443
rium-3.385
Token address
Token ID2209
Feature activation-2.25e-02

Pos logit contributions
ocket+0.106
 replay+0.101
rium+0.101
adiator+0.101
Explore+0.100
Neg logit contributions
 unden-0.136
 rall-0.131
 arrang-0.124
 reluct-0.124
fort-0.117
Token.
Token ID13
Feature activation-5.34e-01

Pos logit contributions
 unden+0.048
 rall+0.047
 arrang+0.045
 reluct+0.044
fort+0.043
Neg logit contributions
ocket-0.028
adiator-0.027
Explore-0.026
 replay-0.026
rium-0.026
Token Please
Token ID4222
Feature activation-6.48e-01

Pos logit contributions
 unden+0.975
 rall+0.951
 arrang+0.889
 reluct+0.884
fort+0.850
Neg logit contributions
ocket-0.853
Explore-0.819
adiator-0.817
 replay-0.804
rium-0.802
Token re
Token ID302
Feature activation-3.49e-02

Pos logit contributions
 unden+0.963
 rall+0.932
 arrang+0.858
 reluct+0.847
fort+0.827
Neg logit contributions
ocket-1.240
adiator-1.201
Explore-1.192
 replay-1.183
rium-1.177
Token to
Token ID284
Feature activation-5.93e-02

Pos logit contributions
 unden+0.538
 rall+0.528
 arrang+0.499
 reluct+0.495
fort+0.487
Neg logit contributions
ocket-0.329
adiator-0.313
 replay-0.310
Explore-0.309
rium-0.303
Token learn
Token ID2193
Feature activation-7.07e-01

Pos logit contributions
 unden+0.117
 rall+0.114
 reluct+0.107
 arrang+0.107
fort+0.104
Neg logit contributions
ocket-0.084
 replay-0.082
Explore-0.080
adiator-0.079
paces-0.078
Token more
Token ID517
Feature activation-4.11e-01

Pos logit contributions
 unden+1.317
 rall+1.290
 arrang+1.206
 reluct+1.191
fort+1.175
Neg logit contributions
ocket-1.076
adiator-1.034
Explore-1.024
 replay-1.019
rium-1.009
Token about
Token ID546
Feature activation-2.34e-01

Pos logit contributions
 unden+0.705
 rall+0.691
 arrang+0.639
 reluct+0.632
fort+0.622
Neg logit contributions
ocket-0.688
adiator-0.663
Explore-0.656
 replay-0.653
rium-0.648
Token social
Token ID1919
Feature activation-1.08e+00

Pos logit contributions
 unden+0.454
 rall+0.443
 arrang+0.414
 reluct+0.411
fort+0.407
Neg logit contributions
ocket-0.338
adiator-0.322
 replay-0.321
Explore-0.319
rium-0.314
Token justice
Token ID5316
Feature activation-1.88e+00

Pos logit contributions
 unden+2.014
 rall+1.968
 arrang+1.841
 reluct+1.821
fort+1.799
Neg logit contributions
ocket-1.637
adiator-1.572
Explore-1.555
 replay-1.541
rium-1.530
Token from
Token ID422
Feature activation-2.23e-01

Pos logit contributions
 unden+3.665
 rall+3.577
 arrang+3.373
 reluct+3.330
 '.+3.296
Neg logit contributions
ocket-2.689
adiator-2.584
Explore-2.554
 replay-2.516
rium-2.508
Token atheists
Token ID28473
Feature activation+8.71e-02

Pos logit contributions
 unden+0.433
 rall+0.422
 arrang+0.398
 reluct+0.394
fort+0.389
Neg logit contributions
ocket-0.323
adiator-0.308
 replay-0.307
Explore-0.307
rium-0.301
Token who
Token ID508
Feature activation+4.15e-02

Pos logit contributions
ocket+0.113
adiator+0.107
Explore+0.105
paces+0.105
 replay+0.105
Neg logit contributions
 unden-0.183
 rall-0.179
 arrang-0.169
 reluct-0.167
fort-0.164
Token shared
Token ID4888
Feature activation-6.46e-01

Pos logit contributions
ocket+0.062
 replay+0.060
Explore+0.059
adiator+0.059
paces+0.058
Neg logit contributions
 unden-0.079
 rall-0.076
 arrang-0.072
 reluct-0.071
fort-0.070
Token their
Token ID511
Feature activation-1.37e-02

Pos logit contributions
 unden+1.349
 rall+1.323
 arrang+1.247
 reluct+1.234
fort+1.220
Neg logit contributions
ocket-0.837
adiator-0.796
Explore-0.788
 replay-0.783
rium-0.773
Token if
Token ID611
Feature activation-1.55e-01

Pos logit contributions
ocket+0.342
adiator+0.326
 replay+0.323
Explore+0.321
rium+0.320
Neg logit contributions
 unden-0.437
 rall-0.427
 arrang-0.401
 reluct-0.398
fort-0.388
Token you
Token ID345
Feature activation-1.38e-02

Pos logit contributions
 unden+0.285
 rall+0.278
 arrang+0.260
 reluct+0.258
fort+0.254
Neg logit contributions
ocket-0.239
adiator-0.229
 replay-0.227
Explore-0.227
rium-0.225
Token're
Token ID821
Feature activation-1.76e-01

Pos logit contributions
 unden+0.026
 rall+0.025
 arrang+0.024
 reluct+0.024
fort+0.023
Neg logit contributions
ocket-0.021
adiator-0.020
 replay-0.020
Explore-0.020
rium-0.019
Token really
Token ID1107
Feature activation+5.40e-02

Pos logit contributions
 unden+0.355
 rall+0.346
 arrang+0.326
 reluct+0.324
fort+0.318
Neg logit contributions
ocket-0.243
adiator-0.231
 replay-0.228
Explore-0.228
paces-0.226
Token f
Token ID277
Feature activation-3.13e-01

Pos logit contributions
ocket+0.080
adiator+0.076
 replay+0.076
Explore+0.075
paces+0.075
Neg logit contributions
 unden-0.104
 rall-0.101
 arrang-0.095
 reluct-0.094
fort-0.092
Token****
Token ID2466
Feature activation-1.88e+00

Pos logit contributions
 unden+0.575
 rall+0.559
 arrang+0.524
 reluct+0.517
 '.+0.509
Neg logit contributions
ocket-0.490
adiator-0.471
Explore-0.466
 replay-0.460
rium-0.459
Tokend
Token ID67
Feature activation-2.52e-01

Pos logit contributions
 unden+3.598
 rall+3.563
 arrang+3.334
fort+3.304
 '.+3.283
Neg logit contributions
ocket-2.664
adiator-2.552
Explore-2.533
 replay-2.505
rium-2.466
Token.
Token ID13
Feature activation-3.35e-01

Pos logit contributions
 unden+0.461
 rall+0.450
 arrang+0.421
 reluct+0.416
fort+0.410
Neg logit contributions
ocket-0.392
adiator-0.378
Explore-0.373
 replay-0.370
rium-0.368
Token
Token ID198
Feature activation-2.34e-01

Pos logit contributions
 unden+0.677
 rall+0.662
 arrang+0.623
 reluct+0.617
fort+0.607
Neg logit contributions
ocket-0.461
adiator-0.440
Explore-0.436
 replay-0.432
rium-0.428
Token
Token ID198
Feature activation-1.85e-01

Pos logit contributions
 unden+0.480
 rall+0.470
 arrang+0.443
 reluct+0.438
fort+0.436
Neg logit contributions
ocket-0.308
adiator-0.295
Explore-0.291
 replay-0.287
rium-0.286
TokenLet
Token ID5756
Feature activation-3.96e-03

Pos logit contributions
 unden+0.403
 rall+0.395
 arrang+0.373
 reluct+0.370
 '.+0.365
Neg logit contributions
ocket-0.224
adiator-0.214
Explore-0.211
 replay-0.207
rium-0.206
Tokenvm
Token ID14761
Feature activation-2.99e-01

Pos logit contributions
ocket+0.306
adiator+0.291
Explore+0.288
 replay+0.283
rium+0.282
Neg logit contributions
 unden-0.534
 rall-0.523
 arrang-0.495
 reluct-0.490
fort-0.484
Tokenash
Token ID1077
Feature activation-2.81e-01

Pos logit contributions
 unden+0.616
 rall+0.602
 arrang+0.568
 reluct+0.563
fort+0.555
Neg logit contributions
ocket-0.399
adiator-0.381
Explore-0.376
rium-0.371
 replay-0.370
Token ship
Token ID4074
Feature activation+1.87e-01

Pos logit contributions
 unden+0.558
 rall+0.545
 arrang+0.513
 reluct+0.508
fort+0.500
Neg logit contributions
ocket-0.392
adiator-0.376
Explore-0.372
 replay-0.367
rium-0.367
Tokenyard
Token ID9413
Feature activation-3.18e-01

Pos logit contributions
ocket+0.204
adiator+0.194
Explore+0.191
 replay+0.187
rium+0.187
Neg logit contributions
 unden-0.428
 rall-0.420
 arrang-0.398
 reluct-0.395
 '.-0.390
Token at
Token ID379
Feature activation-3.08e-01

Pos logit contributions
 unden+0.622
 rall+0.607
 arrang+0.571
 reluct+0.565
fort+0.557
Neg logit contributions
ocket-0.456
adiator-0.436
Explore-0.432
 replay-0.427
rium-0.425
Token Sever
Token ID26434
Feature activation-1.87e+00

Pos logit contributions
 unden+0.541
 rall+0.525
 arrang+0.492
 reluct+0.488
fort+0.476
Neg logit contributions
ocket-0.503
adiator-0.485
Explore-0.482
rium-0.479
 replay-0.477
Tokenod
Token ID375
Feature activation-2.85e-01

Pos logit contributions
 unden+3.185
 rall+3.119
 arrang+2.889
fort+2.840
 reluct+2.835
Neg logit contributions
ocket-3.109
adiator-3.019
Explore-2.992
 replay-2.959
paces-2.935
Tokenv
Token ID85
Feature activation-1.66e-01

Pos logit contributions
 unden+0.560
 rall+0.548
 arrang+0.515
 reluct+0.509
fort+0.503
Neg logit contributions
ocket-0.405
adiator-0.389
Explore-0.384
 replay-0.379
rium-0.378
Tokeninsk
Token ID35803
Feature activation+6.81e-01

Pos logit contributions
 unden+0.406
 rall+0.399
 arrang+0.380
 reluct+0.376
 '.+0.373
Neg logit contributions
ocket-0.156
adiator-0.146
Explore-0.143
 replay-0.141
rium-0.139
Token,
Token ID11
Feature activation+8.85e-02

Pos logit contributions
ocket+0.898
adiator+0.853
Explore+0.847
rium+0.832
 replay+0.829
Neg logit contributions
 unden-1.408
 rall-1.374
 arrang-1.295
 reluct-1.292
fort-1.258
Token which
Token ID543
Feature activation+2.04e-01

Pos logit contributions
ocket+0.124
Explore+0.119
adiator+0.118
 replay+0.117
rium+0.116
Neg logit contributions
 unden-0.175
 rall-0.170
 arrang-0.160
 reluct-0.159
fort-0.157
Token series
Token ID2168
Feature activation-1.77e-01

Pos logit contributions
ocket+0.269
adiator+0.259
Explore+0.256
 replay+0.256
rium+0.252
Neg logit contributions
 unden-0.320
 rall-0.311
 arrang-0.292
 reluct-0.289
fort-0.284
Token Natural
Token ID12068
Feature activation+5.20e-01

Pos logit contributions
 unden+0.321
 rall+0.312
 arrang+0.293
 reluct+0.290
fort+0.283
Neg logit contributions
ocket-0.279
adiator-0.268
Explore-0.266
 replay-0.264
rium-0.262
Token World
Token ID2159
Feature activation-3.95e-01

Pos logit contributions
ocket+0.710
adiator+0.679
Explore+0.674
 replay+0.665
rium+0.661
Neg logit contributions
 unden-1.050
 rall-1.026
 arrang-0.969
 reluct-0.959
fort-0.944
Token episode
Token ID4471
Feature activation+7.37e-01

Pos logit contributions
 unden+0.800
 rall+0.782
 arrang+0.737
 reluct+0.729
fort+0.720
Neg logit contributions
ocket-0.539
adiator-0.515
Explore-0.509
 replay-0.503
rium-0.501
Token "
Token ID366
Feature activation+3.75e-03

Pos logit contributions
ocket+1.155
Explore+1.105
adiator+1.105
 replay+1.097
rium+1.090
Neg logit contributions
 unden-1.350
 rall-1.306
 arrang-1.232
 reluct-1.222
fort-1.178
TokenSnow
Token ID28974
Feature activation-1.87e+00

Pos logit contributions
ocket+0.005
Explore+0.005
adiator+0.005
 replay+0.005
rium+0.005
Neg logit contributions
 unden-0.008
 rall-0.007
 arrang-0.007
 reluct-0.007
 '.-0.007
Token Leopard
Token ID49072
Feature activation-3.73e-01

Pos logit contributions
 unden+3.092
 rall+3.045
 arrang+2.809
fort+2.788
 '.+2.774
Neg logit contributions
ocket-3.168
adiator-3.071
Explore-3.021
 replay-2.996
rium-2.992
Token
Token ID784
Feature activation-1.19e-01

Pos logit contributions
 unden+0.716
 rall+0.700
 arrang+0.657
 reluct+0.650
fort+0.641
Neg logit contributions
ocket-0.547
adiator-0.526
Explore-0.520
 replay-0.514
rium-0.511
Token Beyond
Token ID12197
Feature activation-1.86e-01

Pos logit contributions
 unden+0.218
 rall+0.212
 arrang+0.199
 reluct+0.197
fort+0.193
Neg logit contributions
ocket-0.186
adiator-0.179
Explore-0.178
 replay-0.176
rium-0.175
Token the
Token ID262
Feature activation-7.81e-02

Pos logit contributions
 unden+0.343
 rall+0.335
 arrang+0.313
 reluct+0.310
fort+0.305
Neg logit contributions
ocket-0.287
adiator-0.276
Explore-0.274
 replay-0.270
rium-0.269
Token Myth
Token ID18900
Feature activation-1.83e-01

Pos logit contributions
 unden+0.134
 rall+0.131
 arrang+0.122
 reluct+0.120
fort+0.118
Neg logit contributions
ocket-0.130
adiator-0.125
Explore-0.125
 replay-0.123
rium-0.123
Token bronze
Token ID22101
Feature activation-2.40e-02

Pos logit contributions
 unden+0.632
 rall+0.612
 arrang+0.577
 reluct+0.573
fort+0.568
Neg logit contributions
ocket-0.501
adiator-0.482
Explore-0.481
 replay-0.480
rium-0.478
Token and
Token ID290
Feature activation-2.86e-01

Pos logit contributions
 unden+0.048
 rall+0.047
 arrang+0.044
 reluct+0.044
 '.+0.043
Neg logit contributions
ocket-0.033
adiator-0.032
Explore-0.031
 replay-0.031
rium-0.031
Token steel
Token ID7771
Feature activation+7.68e-02

Pos logit contributions
 unden+0.558
 rall+0.544
 arrang+0.513
 reluct+0.507
 '.+0.501
Neg logit contributions
ocket-0.410
adiator-0.394
Explore-0.388
 replay-0.386
rium-0.384
Token have
Token ID423
Feature activation-4.53e-01

Pos logit contributions
ocket+0.111
adiator+0.106
Explore+0.105
 replay+0.104
rium+0.104
Neg logit contributions
 unden-0.149
 rall-0.146
 arrang-0.137
 reluct-0.136
 '.-0.134
Token been
Token ID587
Feature activation-1.23e-01

Pos logit contributions
 unden+0.825
 rall+0.805
 arrang+0.754
 reluct+0.745
fort+0.735
Neg logit contributions
ocket-0.707
adiator-0.680
Explore-0.674
 replay-0.667
rium-0.664
Token collected
Token ID7723
Feature activation-1.84e+00

Pos logit contributions
 unden+0.235
 rall+0.228
 arrang+0.213
 reluct+0.212
fort+0.209
Neg logit contributions
ocket-0.182
adiator-0.173
Explore-0.172
 replay-0.171
rium-0.170
Token in
Token ID287
Feature activation-1.97e-01

Pos logit contributions
 unden+3.362
 rall+3.282
 arrang+3.084
 reluct+3.039
 '.+3.018
Neg logit contributions
ocket-2.822
adiator-2.716
Explore-2.684
 replay-2.648
rium-2.641
Token tribute
Token ID17547
Feature activation+5.07e-01

Pos logit contributions
 unden+0.361
 rall+0.350
 arrang+0.329
 reluct+0.326
fort+0.322
Neg logit contributions
ocket-0.306
adiator-0.294
Explore-0.293
 replay-0.292
rium-0.290
Token to
Token ID284
Feature activation-9.46e-02

Pos logit contributions
ocket+0.633
adiator+0.604
Explore+0.596
 replay+0.588
rium+0.585
Neg logit contributions
 unden-1.084
 rall-1.062
 arrang-1.002
 reluct-0.992
fort-0.981
Token some
Token ID617
Feature activation-1.10e-01

Pos logit contributions
 unden+0.170
 rall+0.164
 arrang+0.155
 reluct+0.153
fort+0.151
Neg logit contributions
ocket-0.149
adiator-0.145
Explore-0.143
 replay-0.143
rium-0.142
Token of
Token ID286
Feature activation-2.16e-01

Pos logit contributions
 unden+0.232
 rall+0.226
 arrang+0.215
 reluct+0.212
fort+0.210
Neg logit contributions
ocket-0.139
adiator-0.132
Explore-0.130
 replay-0.129
rium-0.128
Token which
Token ID543
Feature activation+2.20e-01

Pos logit contributions
 unden+0.137
 rall+0.134
 arrang+0.126
 reluct+0.125
fort+0.123
Neg logit contributions
ocket-0.093
adiator-0.090
Explore-0.088
 replay-0.087
rium-0.087
Token are
Token ID389
Feature activation-4.91e-02

Pos logit contributions
ocket+0.320
adiator+0.306
Explore+0.305
 replay+0.302
paces+0.298
Neg logit contributions
 unden-0.426
 rall-0.415
 arrang-0.391
 reluct-0.387
fort-0.381
Token probably
Token ID2192
Feature activation-1.23e-01

Pos logit contributions
 unden+0.093
 rall+0.091
 arrang+0.085
 reluct+0.084
fort+0.083
Neg logit contributions
ocket-0.073
adiator-0.070
Explore-0.070
 replay-0.069
rium-0.068
Token easy
Token ID2562
Feature activation+4.61e-01

Pos logit contributions
 unden+0.239
 rall+0.234
 arrang+0.220
 reluct+0.218
fort+0.214
Neg logit contributions
ocket-0.178
adiator-0.170
Explore-0.169
 replay-0.168
rium-0.166
Token to
Token ID284
Feature activation-6.29e-02

Pos logit contributions
ocket+0.586
adiator+0.563
Explore+0.557
 replay+0.552
rium+0.544
Neg logit contributions
 unden-0.970
 rall-0.954
 arrang-0.895
 reluct-0.894
fort-0.876
Token fix
Token ID4259
Feature activation-1.83e+00

Pos logit contributions
 unden+0.121
 rall+0.119
 reluct+0.112
 arrang+0.111
fort+0.108
Neg logit contributions
ocket-0.092
 replay-0.089
adiator-0.088
Explore-0.088
paces-0.086
Token,
Token ID11
Feature activation+1.20e-02

Pos logit contributions
 unden+3.577
 rall+3.489
 arrang+3.309
 '.+3.275
fort+3.260
Neg logit contributions
ocket-2.525
adiator-2.433
Explore-2.406
rium-2.365
 replay-2.350
Token but
Token ID475
Feature activation-4.87e-03

Pos logit contributions
ocket+0.016
adiator+0.015
Explore+0.015
 replay+0.015
rium+0.015
Neg logit contributions
 unden-0.025
 rall-0.024
 arrang-0.023
 reluct-0.023
fort-0.022
Token it
Token ID340
Feature activation-5.87e-02

Pos logit contributions
 unden+0.009
 rall+0.009
 arrang+0.009
 reluct+0.009
fort+0.008
Neg logit contributions
ocket-0.007
adiator-0.007
Explore-0.007
 replay-0.007
rium-0.007
Token just
Token ID655
Feature activation-1.80e-01

Pos logit contributions
 unden+0.124
 rall+0.122
 arrang+0.115
 reluct+0.113
 '.+0.112
Neg logit contributions
ocket-0.075
adiator-0.071
Explore-0.071
 replay-0.070
rium-0.069
Token takes
Token ID2753
Feature activation+2.62e-01

Pos logit contributions
 unden+0.361
 rall+0.352
 arrang+0.332
 reluct+0.328
fort+0.324
Neg logit contributions
ocket-0.249
adiator-0.239
Explore-0.236
 replay-0.233
rium-0.232
Token bow
Token ID9563
Feature activation-9.20e-02

Pos logit contributions
 unden+0.111
 rall+0.107
 reluct+0.099
 arrang+0.099
fort+0.098
Neg logit contributions
ocket-0.100
 replay-0.096
adiator-0.096
Explore-0.096
rium-0.094
Token in
Token ID287
Feature activation-4.82e-02

Pos logit contributions
 unden+0.182
 rall+0.178
 arrang+0.166
 reluct+0.166
fort+0.161
Neg logit contributions
ocket-0.131
adiator-0.125
Explore-0.123
 replay-0.123
rium-0.122
Token person
Token ID1048
Feature activation-3.11e-02

Pos logit contributions
 unden+0.088
 rall+0.085
 arrang+0.080
 reluct+0.079
fort+0.078
Neg logit contributions
ocket-0.076
adiator-0.073
 replay-0.072
Explore-0.072
rium-0.071
Token but
Token ID475
Feature activation-1.92e-02

Pos logit contributions
 unden+0.064
 rall+0.062
 arrang+0.058
 reluct+0.058
fort+0.057
Neg logit contributions
ocket-0.042
adiator-0.040
Explore-0.039
 replay-0.039
rium-0.039
Token their
Token ID511
Feature activation-1.38e-02

Pos logit contributions
 unden+0.037
 rall+0.036
 arrang+0.034
 reluct+0.034
fort+0.033
Neg logit contributions
ocket-0.028
adiator-0.027
Explore-0.027
 replay-0.026
paces-0.026
Token collected
Token ID7723
Feature activation-1.81e+00

Pos logit contributions
 unden+0.026
 rall+0.025
 reluct+0.023
 arrang+0.023
fort+0.023
Neg logit contributions
ocket-0.021
 replay-0.020
adiator-0.020
Explore-0.020
rium-0.020
Token correspondence
Token ID22440
Feature activation-3.75e-02

Pos logit contributions
 unden+3.285
 rall+3.212
 arrang+3.009
 reluct+2.962
 '.+2.932
Neg logit contributions
ocket-2.826
adiator-2.725
Explore-2.694
rium-2.656
 replay-2.653
Token contains
Token ID4909
Feature activation-2.69e-01

Pos logit contributions
 unden+0.072
 rall+0.070
 arrang+0.066
 reluct+0.065
fort+0.064
Neg logit contributions
ocket-0.055
adiator-0.053
Explore-0.052
 replay-0.052
rium-0.052
Token no
Token ID645
Feature activation-2.24e-01

Pos logit contributions
 unden+0.511
 rall+0.499
 arrang+0.468
 reluct+0.464
fort+0.458
Neg logit contributions
ocket-0.396
adiator-0.382
 replay-0.378
Explore-0.377
rium-0.370
Token letter
Token ID3850
Feature activation-9.24e-02

Pos logit contributions
 unden+0.436
 rall+0.426
 arrang+0.398
 reluct+0.397
fort+0.392
Neg logit contributions
ocket-0.321
adiator-0.307
 replay-0.305
Explore-0.304
rium-0.296
Token saying
Token ID2282
Feature activation+1.31e-01

Pos logit contributions
 unden+0.183
 rall+0.178
 arrang+0.167
 reluct+0.166
fort+0.163
Neg logit contributions
ocket-0.131
adiator-0.125
Explore-0.124
 replay-0.123
rium-0.122
Token This
Token ID770
Feature activation+5.07e-01

Pos logit contributions
ocket+0.092
Explore+0.088
adiator+0.087
 replay+0.087
paces+0.086
Neg logit contributions
 unden-0.126
 rall-0.123
 reluct-0.115
 arrang-0.115
fort-0.112
Token is
Token ID318
Feature activation-2.34e-01

Pos logit contributions
ocket+0.637
 replay+0.613
adiator+0.600
Explore+0.597
rium+0.590
Neg logit contributions
 unden-1.079
 rall-1.053
 reluct-0.986
 arrang-0.981
fort-0.968
Token explained
Token ID4893
Feature activation+6.66e-02

Pos logit contributions
 unden+0.438
 rall+0.428
 arrang+0.400
 reluct+0.397
fort+0.389
Neg logit contributions
ocket-0.356
adiator-0.341
Explore-0.338
 replay-0.337
rium-0.334
Token here
Token ID994
Feature activation-1.18e-01

Pos logit contributions
ocket+0.100
adiator+0.096
 replay+0.095
Explore+0.095
paces+0.094
Neg logit contributions
 unden-0.126
 rall-0.123
 arrang-0.115
 reluct-0.114
fort-0.112
Token.
Token ID13
Feature activation-2.52e-01

Pos logit contributions
 unden+0.248
 rall+0.243
 arrang+0.228
 reluct+0.226
fort+0.222
Neg logit contributions
ocket-0.152
adiator-0.145
Explore-0.142
 replay-0.142
paces-0.140
Token *
Token ID1635
Feature activation-1.78e+00

Pos logit contributions
 unden+0.491
 rall+0.480
 arrang+0.448
 reluct+0.446
fort+0.438
Neg logit contributions
ocket-0.362
adiator-0.346
Explore-0.345
 replay-0.343
paces-0.340
Tokenmod
Token ID4666
Feature activation+5.28e-01

Pos logit contributions
 unden+3.430
 rall+3.355
 arrang+3.158
 reluct+3.107
 '.+3.095
Neg logit contributions
ocket-2.587
adiator-2.492
Explore-2.447
 replay-2.423
rium-2.417
Tokeneline
Token ID4470
Feature activation-4.30e-01

Pos logit contributions
ocket+0.928
adiator+0.889
Explore+0.885
rium+0.878
paces+0.874
Neg logit contributions
 unden-0.872
 rall-0.840
 reluct-0.785
 arrang-0.783
 cir-0.750
Token*
Token ID9
Feature activation-9.06e-01

Pos logit contributions
 unden+0.835
 rall+0.815
 arrang+0.766
 reluct+0.759
fort+0.745
Neg logit contributions
ocket-0.622
adiator-0.596
Explore-0.592
 replay-0.585
rium-0.580
Token *
Token ID1635
Feature activation-9.64e-01

Pos logit contributions
 unden+1.723
 rall+1.683
 arrang+1.580
 reluct+1.561
fort+1.542
Neg logit contributions
ocket-1.341
adiator-1.289
Explore-1.274
 replay-1.259
rium-1.254
Tokenvim
Token ID31124
Feature activation-1.06e+00

Pos logit contributions
 unden+1.774
 rall+1.731
 arrang+1.621
 reluct+1.602
fort+1.579
Neg logit contributions
ocket-1.489
adiator-1.433
Explore-1.419
 replay-1.402
rium-1.396
Token month
Token ID1227
Feature activation-4.72e-01

Pos logit contributions
ocket+0.302
 replay+0.290
adiator+0.287
Explore+0.285
rium+0.281
Neg logit contributions
 unden-0.388
 rall-0.373
 arrang-0.353
 reluct-0.350
fort-0.343
Token is
Token ID318
Feature activation-1.30e-01

Pos logit contributions
 unden+0.917
 rall+0.893
 arrang+0.839
 reluct+0.830
 '.+0.818
Neg logit contributions
ocket-0.685
adiator-0.657
Explore-0.648
 replay-0.642
rium-0.637
Token to
Token ID284
Feature activation+8.76e-03

Pos logit contributions
 unden+0.257
 rall+0.251
 arrang+0.236
 reluct+0.234
fort+0.231
Neg logit contributions
ocket-0.182
adiator-0.174
Explore-0.172
 replay-0.172
rium-0.169
Token try
Token ID1949
Feature activation+3.31e-01

Pos logit contributions
ocket+0.013
 replay+0.012
Explore+0.012
adiator+0.012
paces+0.012
Neg logit contributions
 unden-0.017
 rall-0.017
 reluct-0.015
 arrang-0.015
fort-0.015
Token and
Token ID290
Feature activation-1.87e-01

Pos logit contributions
ocket+0.448
adiator+0.429
Explore+0.423
 replay+0.423
iversity+0.415
Neg logit contributions
 unden-0.670
 rall-0.655
 arrang-0.616
 reluct-0.612
fort-0.602
Token collect
Token ID2824
Feature activation-1.78e+00

Pos logit contributions
 unden+0.367
 rall+0.358
 reluct+0.336
 arrang+0.334
fort+0.327
Neg logit contributions
ocket-0.267
 replay-0.260
Explore-0.255
adiator-0.254
paces-0.251
Token the
Token ID262
Feature activation-7.73e-02

Pos logit contributions
 unden+3.226
 rall+3.151
 arrang+2.948
 reluct+2.907
 '.+2.876
Neg logit contributions
ocket-2.802
adiator-2.700
Explore-2.671
 replay-2.632
rium-2.631
Token Cur
Token ID4424
Feature activation-1.97e-01

Pos logit contributions
 unden+0.143
 rall+0.139
 arrang+0.130
 reluct+0.129
fort+0.127
Neg logit contributions
ocket-0.119
 replay-0.114
adiator-0.114
Explore-0.113
rium-0.111
Tokenric
Token ID1173
Feature activation-4.29e-01

Pos logit contributions
 unden+0.410
 rall+0.401
 arrang+0.379
 reluct+0.375
 '.+0.370
Neg logit contributions
ocket-0.259
adiator-0.247
Explore-0.244
rium-0.241
 replay-0.241
Tokenulum
Token ID14452
Feature activation+1.51e-01

Pos logit contributions
 unden+1.018
 rall+0.999
 arrang+0.950
 reluct+0.942
 '.+0.931
Neg logit contributions
ocket-0.435
adiator-0.410
Explore-0.403
 replay-0.396
rium-0.393
Token Vit
Token ID18271
Feature activation-1.33e-01

Pos logit contributions
ocket+0.229
adiator+0.220
Explore+0.219
 replay+0.219
rium+0.215
Neg logit contributions
 unden-0.282
 rall-0.276
 arrang-0.258
 reluct-0.256
fort-0.251
Token show
Token ID905
Feature activation-5.17e-01

Pos logit contributions
 unden+0.075
 rall+0.072
 reluct+0.068
 arrang+0.068
fort+0.066
Neg logit contributions
ocket-0.053
 replay-0.052
Explore-0.051
adiator-0.051
paces-0.050
Token you
Token ID345
Feature activation+1.84e-01

Pos logit contributions
 unden+1.003
 rall+0.977
 arrang+0.916
 reluct+0.907
fort+0.897
Neg logit contributions
ocket-0.745
adiator-0.717
 replay-0.714
Explore-0.708
rium-0.700
Token a
Token ID257
Feature activation-1.10e-01

Pos logit contributions
ocket+0.291
adiator+0.279
 replay+0.279
Explore+0.276
rium+0.274
Neg logit contributions
 unden-0.332
 rall-0.324
 arrang-0.302
 reluct-0.299
fort-0.294
Token way
Token ID835
Feature activation+7.35e-02

Pos logit contributions
 unden+0.200
 rall+0.195
 arrang+0.181
 reluct+0.179
fort+0.178
Neg logit contributions
ocket-0.172
 replay-0.166
adiator-0.166
Explore-0.163
rium-0.162
Token to
Token ID284
Feature activation-1.37e-01

Pos logit contributions
ocket+0.093
adiator+0.089
Explore+0.088
 replay+0.087
rium+0.086
Neg logit contributions
 unden-0.156
 rall-0.153
 arrang-0.144
 reluct-0.143
 '.-0.141
Token fix
Token ID4259
Feature activation-1.78e+00

Pos logit contributions
 unden+0.272
 rall+0.266
 reluct+0.249
 arrang+0.248
fort+0.244
Neg logit contributions
ocket-0.190
 replay-0.184
adiator-0.181
Explore-0.180
paces-0.178
Token it
Token ID340
Feature activation+1.70e-02

Pos logit contributions
 unden+3.350
 rall+3.280
 arrang+3.079
 reluct+3.031
 '.+3.008
Neg logit contributions
ocket-2.652
adiator-2.557
Explore-2.539
rium-2.493
iversity-2.485
Token by
Token ID416
Feature activation-2.32e-01

Pos logit contributions
ocket+0.023
adiator+0.022
 replay+0.021
Explore+0.021
paces+0.021
Neg logit contributions
 unden-0.035
 rall-0.035
 arrang-0.032
 reluct-0.032
fort-0.031
Token spending
Token ID4581
Feature activation-1.95e-01

Pos logit contributions
 unden+0.461
 rall+0.450
 arrang+0.423
 reluct+0.420
fort+0.416
Neg logit contributions
ocket-0.323
 replay-0.306
adiator-0.306
Explore-0.301
rium-0.298
Token less
Token ID1342
Feature activation+1.34e-01

Pos logit contributions
 unden+0.342
 rall+0.335
 arrang+0.311
 reluct+0.309
 '.+0.302
Neg logit contributions
ocket-0.317
adiator-0.304
 replay-0.301
Explore-0.301
rium-0.299
Token than
Token ID621
Feature activation+2.75e-02

Pos logit contributions
ocket+0.164
adiator+0.156
Explore+0.154
 replay+0.152
rium+0.151
Neg logit contributions
 unden-0.288
 rall-0.282
 arrang-0.266
 reluct-0.264
fort-0.261
Token't
Token ID470
Feature activation-2.83e-03

Pos logit contributions
 unden+0.237
 rall+0.231
 arrang+0.218
 reluct+0.216
 '.+0.209
Neg logit contributions
ocket-0.169
adiator-0.162
Explore-0.161
 replay-0.158
rium-0.158
Token.
Token ID13
Feature activation+1.90e-01

Pos logit contributions
 unden+0.006
 rall+0.005
 reluct+0.005
 arrang+0.005
fort+0.005
Neg logit contributions
ocket-0.004
 replay-0.004
adiator-0.004
Explore-0.004
paces-0.004
Token They
Token ID1119
Feature activation+1.16e-01

Pos logit contributions
ocket+0.271
Explore+0.259
adiator+0.258
 replay+0.255
paces+0.252
Neg logit contributions
 unden-0.374
 rall-0.365
 arrang-0.345
 reluct-0.342
fort-0.332
Token need
Token ID761
Feature activation+2.68e-01

Pos logit contributions
ocket+0.179
 replay+0.172
adiator+0.171
Explore+0.170
rium+0.169
Neg logit contributions
 unden-0.216
 rall-0.210
 arrang-0.198
 reluct-0.195
fort-0.191
Token a
Token ID257
Feature activation+2.49e-01

Pos logit contributions
ocket+0.358
adiator+0.343
 replay+0.340
Explore+0.337
iversity+0.334
Neg logit contributions
 unden-0.547
 rall-0.533
 arrang-0.506
 reluct-0.501
fort-0.493
Token *
Token ID1635
Feature activation-1.77e+00

Pos logit contributions
ocket+0.379
 replay+0.365
adiator+0.363
Explore+0.356
paces+0.354
Neg logit contributions
 unden-0.462
 rall-0.448
 arrang-0.423
 reluct-0.418
fort-0.411
Tokenlot
Token ID26487
Feature activation+5.94e-01

Pos logit contributions
 unden+3.397
 rall+3.323
 arrang+3.118
fort+3.117
 reluct+3.074
Neg logit contributions
ocket-2.536
adiator-2.439
Explore-2.384
rium-2.360
 replay-2.357
Token*
Token ID9
Feature activation-3.03e-01

Pos logit contributions
ocket+0.839
adiator+0.806
Explore+0.797
 replay+0.793
rium+0.785
Neg logit contributions
 unden-1.167
 rall-1.141
 arrang-1.073
 reluct-1.057
 '.-1.040
Token more
Token ID517
Feature activation+1.13e-01

Pos logit contributions
 unden+0.598
 rall+0.585
 arrang+0.551
 reluct+0.543
fort+0.537
Neg logit contributions
ocket-0.426
adiator-0.409
Explore-0.404
 replay-0.400
rium-0.397
Token populism
Token ID47584
Feature activation+5.53e-02

Pos logit contributions
ocket+0.154
adiator+0.147
 replay+0.146
Explore+0.145
iversity+0.143
Neg logit contributions
 unden-0.225
 rall-0.220
 arrang-0.208
 reluct-0.206
fort-0.204
Token -
Token ID532
Feature activation-3.65e-01

Pos logit contributions
ocket+0.070
adiator+0.067
Explore+0.066
 replay+0.065
rium+0.065
Neg logit contributions
 unden-0.117
 rall-0.115
 arrang-0.108
 reluct-0.107
fort-0.105
Token memo
Token ID16155
Feature activation+4.18e-01

Pos logit contributions
 unden+0.107
 rall+0.104
 arrang+0.097
 reluct+0.096
fort+0.095
Neg logit contributions
ocket-0.099
 replay-0.096
adiator-0.095
Explore-0.095
rium-0.093
Token either
Token ID2035
Feature activation-5.83e-01

Pos logit contributions
ocket+0.568
adiator+0.538
 replay+0.528
Explore+0.527
rium+0.523
Neg logit contributions
 unden-0.854
 rall-0.838
 arrang-0.783
 reluct-0.778
 '.-0.763
Token.
Token ID13
Feature activation-5.45e-02

Pos logit contributions
 unden+1.238
 rall+1.214
 arrang+1.146
 reluct+1.134
 '.+1.121
Neg logit contributions
ocket-0.737
adiator-0.702
Explore-0.691
 replay-0.684
rium-0.680
Token In
Token ID554
Feature activation-1.12e-01

Pos logit contributions
 unden+0.107
 rall+0.104
 arrang+0.098
 reluct+0.098
fort+0.094
Neg logit contributions
ocket-0.079
Explore-0.076
adiator-0.075
 replay-0.075
rium-0.074
Token the
Token ID262
Feature activation-1.56e-01

Pos logit contributions
 unden+0.201
 rall+0.195
 arrang+0.183
 reluct+0.181
fort+0.178
Neg logit contributions
ocket-0.179
adiator-0.173
Explore-0.171
 replay-0.169
rium-0.168
Token recent
Token ID2274
Feature activation+1.34e+00

Pos logit contributions
 unden+0.292
 rall+0.285
 arrang+0.267
 reluct+0.264
fort+0.261
Neg logit contributions
ocket-0.236
adiator-0.227
Explore-0.225
 replay-0.225
rium-0.222
Token UN
Token ID4725
Feature activation+5.08e-01

Pos logit contributions
ocket+2.066
 replay+2.026
adiator+1.989
Explore+1.966
rium+1.951
Neg logit contributions
 unden-2.416
 rall-2.323
 arrang-2.170
 reluct-2.160
fort-2.138
Token report
Token ID989
Feature activation+2.06e-01

Pos logit contributions
ocket+0.691
adiator+0.660
 replay+0.653
Explore+0.652
rium+0.642
Neg logit contributions
 unden-1.029
 rall-1.002
 arrang-0.942
 reluct-0.937
 '.-0.923
Token investigating
Token ID10240
Feature activation-3.59e-01

Pos logit contributions
ocket+0.273
adiator+0.261
Explore+0.258
 replay+0.255
rium+0.253
Neg logit contributions
 unden-0.426
 rall-0.417
 arrang-0.392
 reluct-0.389
fort-0.384
Token Protective
Token ID45004
Feature activation-4.30e-01

Pos logit contributions
 unden+0.651
 rall+0.635
 arrang+0.593
 reluct+0.587
 '.+0.579
Neg logit contributions
ocket-0.563
adiator-0.543
Explore-0.536
 replay-0.534
rium-0.529
Token Edge
Token ID13113
Feature activation-3.15e-01

Pos logit contributions
 unden+0.771
 rall+0.752
 arrang+0.701
 reluct+0.696
 '.+0.679
Neg logit contributions
ocket-0.690
adiator-0.664
Explore-0.657
 replay-0.652
rium-0.648
Token43
Token ID3559
Feature activation-4.77e-02

Pos logit contributions
ocket+0.302
adiator+0.289
Explore+0.288
 replay+0.284
rium+0.284
Neg logit contributions
 unden-0.401
 rall-0.389
 arrang-0.367
 reluct-0.365
fort-0.352
Token in
Token ID287
Feature activation+5.10e-02

Pos logit contributions
 unden+0.092
 rall+0.090
 arrang+0.085
 reluct+0.084
fort+0.083
Neg logit contributions
ocket-0.069
adiator-0.067
Explore-0.066
 replay-0.065
rium-0.065
Token the
Token ID262
Feature activation-5.58e-02

Pos logit contributions
ocket+0.076
adiator+0.073
 replay+0.072
Explore+0.072
rium+0.072
Neg logit contributions
 unden-0.097
 rall-0.094
 arrang-0.088
 reluct-0.088
fort-0.086
Token 2014
Token ID1946
Feature activation+5.20e-01

Pos logit contributions
 unden+0.121
 rall+0.118
 arrang+0.112
 reluct+0.111
fort+0.110
Neg logit contributions
ocket-0.068
adiator-0.065
Explore-0.064
 replay-0.063
rium-0.063
Token National
Token ID2351
Feature activation-3.74e-01

Pos logit contributions
ocket+0.882
adiator+0.855
 replay+0.848
Explore+0.848
rium+0.842
Neg logit contributions
 unden-0.873
 rall-0.851
 arrang-0.790
 reluct-0.784
fort-0.769
Token Draft
Token ID13650
Feature activation+1.48e+00

Pos logit contributions
 unden+0.677
 rall+0.661
 arrang+0.618
 reluct+0.611
fort+0.601
Neg logit contributions
ocket-0.590
adiator-0.569
Explore-0.563
 replay-0.558
rium-0.556
Token,
Token ID11
Feature activation+5.20e-02

Pos logit contributions
ocket+1.881
adiator+1.791
 replay+1.760
Explore+1.750
iversity+1.735
Neg logit contributions
 unden-3.125
 rall-3.064
 arrang-2.905
 reluct-2.861
fort-2.805
Token Mc
Token ID1982
Feature activation+6.78e-01

Pos logit contributions
ocket+0.090
adiator+0.086
Explore+0.086
 replay+0.085
rium+0.084
Neg logit contributions
 unden-0.087
 rall-0.084
 arrang-0.079
 reluct-0.077
fort-0.076
TokenGovern
Token ID29168
Feature activation-6.31e-01

Pos logit contributions
ocket+1.216
adiator+1.174
Explore+1.168
 replay+1.153
rium+1.149
Neg logit contributions
 unden-1.086
 rall-1.058
 arrang-0.981
 reluct-0.969
 '.-0.943
Token made
Token ID925
Feature activation-1.23e-01

Pos logit contributions
 unden+1.195
 rall+1.167
 arrang+1.094
 reluct+1.081
fort+1.067
Neg logit contributions
ocket-0.941
adiator-0.905
Explore-0.896
 replay-0.885
rium-0.880
Token his
Token ID465
Feature activation-1.45e-01

Pos logit contributions
 unden+0.246
 rall+0.240
 arrang+0.224
 reluct+0.224
fort+0.220
Neg logit contributions
ocket-0.170
adiator-0.162
 replay-0.161
Explore-0.161
rium-0.159
Token Knowledge
Token ID20414
Feature activation+7.79e-02

Pos logit contributions
ocket+0.170
adiator+0.163
Explore+0.161
 replay+0.159
rium+0.159
Neg logit contributions
 unden-0.235
 rall-0.230
 arrang-0.216
 reluct-0.214
 '.-0.210
Token Fund
Token ID7557
Feature activation+1.05e-01

Pos logit contributions
ocket+0.117
Explore+0.112
adiator+0.112
rium+0.110
 replay+0.110
Neg logit contributions
 unden-0.147
 rall-0.143
 arrang-0.135
 reluct-0.133
 '.-0.131
Token,
Token ID11
Feature activation-7.92e-02

Pos logit contributions
ocket+0.134
adiator+0.127
Explore+0.126
 replay+0.124
rium+0.123
Neg logit contributions
 unden-0.222
 rall-0.217
 arrang-0.205
 reluct-0.203
 '.-0.199
Token a
Token ID257
Feature activation-5.85e-02

Pos logit contributions
 unden+0.153
 rall+0.149
 arrang+0.140
 reluct+0.139
fort+0.137
Neg logit contributions
ocket-0.115
Explore-0.110
adiator-0.110
 replay-0.108
rium-0.108
Token venture
Token ID13189
Feature activation+2.98e-01

Pos logit contributions
 unden+0.112
 rall+0.109
 arrang+0.103
 reluct+0.102
fort+0.100
Neg logit contributions
ocket-0.086
adiator-0.083
Explore-0.082
 replay-0.081
rium-0.081
Token capital
Token ID3139
Feature activation+1.15e+00

Pos logit contributions
ocket+0.414
adiator+0.396
Explore+0.394
 replay+0.388
rium+0.388
Neg logit contributions
 unden-0.595
 rall-0.581
 arrang-0.546
 reluct-0.541
 '.-0.532
Token fund
Token ID1814
Feature activation+4.58e-01

Pos logit contributions
ocket+1.725
adiator+1.641
Explore+1.632
 replay+1.628
rium+1.613
Neg logit contributions
 unden-2.193
 rall-2.126
 reluct-1.983
 arrang-1.980
fort-1.941
Token of
Token ID286
Feature activation+2.40e-02

Pos logit contributions
ocket+0.629
Explore+0.596
adiator+0.596
 replay+0.584
rium+0.584
Neg logit contributions
 unden-0.923
 rall-0.905
 arrang-0.848
 reluct-0.841
fort-0.825
Token $
Token ID720
Feature activation+2.47e-01

Pos logit contributions
ocket+0.038
Explore+0.037
adiator+0.037
rium+0.037
 replay+0.037
Neg logit contributions
 unden-0.043
 rall-0.042
 arrang-0.039
 reluct-0.038
fort-0.038
Token50
Token ID1120
Feature activation-7.17e-01

Pos logit contributions
ocket+0.268
Explore+0.254
adiator+0.253
rium+0.246
 replay+0.246
Neg logit contributions
 unden-0.578
 rall-0.563
 arrang-0.536
 reluct-0.535
 '.-0.515
Token million
Token ID1510
Feature activation-1.25e-01

Pos logit contributions
 unden+1.397
 rall+1.364
 arrang+1.283
 reluct+1.271
 '.+1.252
Neg logit contributions
ocket-1.031
adiator-0.989
Explore-0.978
 replay-0.966
rium-0.962
Token it
Token ID340
Feature activation-4.75e-02

Pos logit contributions
 unden+1.394
 rall+1.364
 arrang+1.284
 reluct+1.271
fort+1.255
Neg logit contributions
ocket-0.970
adiator-0.933
Explore-0.923
rium-0.905
 replay-0.904
Token was
Token ID373
Feature activation+1.44e-01

Pos logit contributions
 unden+0.089
 rall+0.087
 arrang+0.081
 reluct+0.080
 '.+0.079
Neg logit contributions
ocket-0.072
adiator-0.069
 replay-0.069
Explore-0.068
rium-0.068
Token the
Token ID262
Feature activation-4.72e-02

Pos logit contributions
ocket+0.215
 replay+0.204
adiator+0.203
Explore+0.201
rium+0.199
Neg logit contributions
 unden-0.273
 rall-0.267
 arrang-0.251
 reluct-0.248
fort-0.245
Token Caps
Token ID23534
Feature activation+4.94e-01

Pos logit contributions
 unden+0.090
 rall+0.088
 arrang+0.082
 reluct+0.081
fort+0.080
Neg logit contributions
ocket-0.070
adiator-0.067
 replay-0.066
Explore-0.066
rium-0.065
Token who
Token ID508
Feature activation+2.78e-01

Pos logit contributions
ocket+0.689
adiator+0.652
 replay+0.647
Explore+0.645
rium+0.637
Neg logit contributions
 unden-0.987
 rall-0.962
 arrang-0.909
 reluct-0.896
 '.-0.884
Token struck
Token ID7425
Feature activation+1.15e+00

Pos logit contributions
ocket+0.418
 replay+0.399
adiator+0.394
Explore+0.391
paces+0.391
Neg logit contributions
 unden-0.527
 rall-0.509
 arrang-0.479
 reluct-0.474
 '.-0.464
Token first
Token ID717
Feature activation-2.89e-01

Pos logit contributions
ocket+1.494
 replay+1.422
adiator+1.411
rium+1.397
Explore+1.390
Neg logit contributions
 unden-2.385
 rall-2.337
 arrang-2.193
 reluct-2.177
 '.-2.139
Token when
Token ID618
Feature activation+4.83e-01

Pos logit contributions
 unden+0.597
 rall+0.585
 arrang+0.552
 reluct+0.546
fort+0.540
Neg logit contributions
ocket-0.381
adiator-0.365
Explore-0.361
 replay-0.355
rium-0.354
Token Alex
Token ID4422
Feature activation-1.84e-01

Pos logit contributions
ocket+0.798
 replay+0.764
adiator+0.762
Explore+0.753
rium+0.747
Neg logit contributions
 unden-0.838
 rall-0.812
 arrang-0.759
 reluct-0.749
fort-0.740
Token O
Token ID440
Feature activation+5.25e-02

Pos logit contributions
 unden+0.280
 rall+0.272
 arrang+0.251
 reluct+0.247
fort+0.243
Neg logit contributions
ocket-0.342
adiator-0.331
Explore-0.328
 replay-0.326
rium-0.324
Tokenve
Token ID303
Feature activation-2.38e-01

Pos logit contributions
ocket+0.064
adiator+0.060
paces+0.059
Explore+0.059
 replay+0.059
Neg logit contributions
 unden-0.115
 rall-0.113
 arrang-0.106
 reluct-0.106
fort-0.103
Token projected
Token ID13301
Feature activation-1.53e-01

Pos logit contributions
 unden+0.271
 rall+0.266
 arrang+0.248
 reluct+0.245
fort+0.243
Neg logit contributions
ocket-0.230
adiator-0.220
Explore-0.219
 replay-0.218
rium-0.216
Token costs
Token ID3484
Feature activation+1.36e-01

Pos logit contributions
 unden+0.286
 rall+0.280
 arrang+0.262
 reluct+0.259
fort+0.256
Neg logit contributions
ocket-0.233
adiator-0.224
Explore-0.222
 replay-0.220
rium-0.218
Token for
Token ID329
Feature activation+2.68e-01

Pos logit contributions
ocket+0.191
adiator+0.183
Explore+0.181
 replay+0.179
rium+0.178
Neg logit contributions
 unden-0.268
 rall-0.263
 arrang-0.247
 reluct-0.244
 '.-0.241
Token power
Token ID1176
Feature activation+4.01e-01

Pos logit contributions
ocket+0.394
adiator+0.377
Explore+0.376
 replay+0.374
rium+0.369
Neg logit contributions
 unden-0.511
 rall-0.502
 arrang-0.469
 reluct-0.465
fort-0.460
Token from
Token ID422
Feature activation+1.06e-01

Pos logit contributions
ocket+0.592
adiator+0.568
Explore+0.565
 replay+0.562
rium+0.554
Neg logit contributions
 unden-0.764
 rall-0.748
 arrang-0.698
 reluct-0.693
fort-0.682
Token natural
Token ID3288
Feature activation+1.14e+00

Pos logit contributions
ocket+0.152
adiator+0.146
Explore+0.145
 replay+0.144
rium+0.143
Neg logit contributions
 unden-0.206
 rall-0.202
 arrang-0.190
 reluct-0.188
fort-0.186
Token gas
Token ID3623
Feature activation-2.19e-01

Pos logit contributions
ocket+1.515
adiator+1.450
 replay+1.447
Explore+1.447
rium+1.411
Neg logit contributions
 unden-2.327
 rall-2.281
 arrang-2.160
 reluct-2.133
 '.-2.097
Token supplied
Token ID14275
Feature activation-2.90e-01

Pos logit contributions
 unden+0.431
 rall+0.421
 arrang+0.396
 reluct+0.392
fort+0.387
Neg logit contributions
ocket-0.311
adiator-0.298
Explore-0.295
 replay-0.292
rium-0.290
Token power
Token ID1176
Feature activation+1.98e-01

Pos logit contributions
 unden+0.584
 rall+0.573
 arrang+0.540
 reluct+0.533
fort+0.525
Neg logit contributions
ocket-0.396
adiator-0.380
Explore-0.378
 replay-0.372
paces-0.369
Token plants
Token ID6134
Feature activation+1.50e-01

Pos logit contributions
ocket+0.297
adiator+0.285
Explore+0.284
 replay+0.281
rium+0.278
Neg logit contributions
 unden-0.372
 rall-0.363
 arrang-0.339
 reluct-0.337
 '.-0.330
Token,
Token ID11
Feature activation-4.15e-02

Pos logit contributions
ocket+0.219
adiator+0.210
Explore+0.208
 replay+0.205
rium+0.204
Neg logit contributions
 unden-0.290
 rall-0.283
 arrang-0.266
 reluct-0.263
fort-0.259
Token and
Token ID290
Feature activation-2.92e-02

Pos logit contributions
ocket+0.433
adiator+0.412
Explore+0.408
 replay+0.407
rium+0.402
Neg logit contributions
 unden-0.664
 rall-0.652
 reluct-0.606
 arrang-0.605
fort-0.597
Token found
Token ID1043
Feature activation+9.35e-01

Pos logit contributions
 unden+0.054
 rall+0.053
 arrang+0.049
 reluct+0.049
fort+0.049
Neg logit contributions
ocket-0.044
adiator-0.042
Explore-0.042
 replay-0.042
rium-0.042
Token the
Token ID262
Feature activation-3.18e-02

Pos logit contributions
ocket+1.285
Explore+1.213
 replay+1.211
adiator+1.210
rium+1.192
Neg logit contributions
 unden-1.862
 rall-1.821
 arrang-1.709
 reluct-1.691
fort-1.672
Token private
Token ID2839
Feature activation+3.95e-01

Pos logit contributions
 unden+0.059
 rall+0.057
 arrang+0.054
 reluct+0.053
fort+0.052
Neg logit contributions
ocket-0.049
adiator-0.047
 replay-0.046
Explore-0.046
rium-0.046
Token route
Token ID6339
Feature activation-2.23e-01

Pos logit contributions
ocket+0.595
adiator+0.567
Explore+0.560
rium+0.559
 replay+0.559
Neg logit contributions
 unden-0.746
 rall-0.728
 arrang-0.676
 reluct-0.673
fort-0.664
Token was
Token ID373
Feature activation+9.30e-02

Pos logit contributions
 unden+0.437
 rall+0.429
 arrang+0.402
 reluct+0.397
fort+0.392
Neg logit contributions
ocket-0.317
adiator-0.303
Explore-0.301
 replay-0.297
rium-0.294
Token faster
Token ID5443
Feature activation+4.02e-02

Pos logit contributions
ocket+0.144
adiator+0.137
Explore+0.137
 replay+0.135
rium+0.135
Neg logit contributions
 unden-0.171
 rall-0.168
 arrang-0.156
 reluct-0.155
fort-0.152
Token.
Token ID13
Feature activation-2.03e-02

Pos logit contributions
ocket+0.053
adiator+0.051
Explore+0.050
 replay+0.050
rium+0.049
Neg logit contributions
 unden-0.083
 rall-0.081
 arrang-0.076
 reluct-0.076
fort-0.075
Token
Token ID198
Feature activation-1.46e-01

Pos logit contributions
 unden+0.043
 rall+0.042
 arrang+0.040
 reluct+0.040
fort+0.039
Neg logit contributions
ocket-0.026
adiator-0.024
Explore-0.024
 replay-0.024
rium-0.024
Token
Token ID198
Feature activation-1.67e-01

Pos logit contributions
 unden+0.301
 rall+0.295
 arrang+0.278
 reluct+0.275
fort+0.272
Neg logit contributions
ocket-0.191
adiator-0.183
Explore-0.181
 replay-0.178
rium-0.177
TokenTheir
Token ID14574
Feature activation+1.57e-01

Pos logit contributions
 unden+0.384
 rall+0.377
 arrang+0.357
 reluct+0.354
fort+0.350
Neg logit contributions
ocket-0.183
adiator-0.173
Explore-0.170
 replay-0.167
rium-0.166
Token fit
Token ID4197
Feature activation-3.80e-01

Pos logit contributions
 unden+1.274
 rall+1.244
 arrang+1.170
 reluct+1.158
 '.+1.142
Neg logit contributions
ocket-0.952
adiator-0.914
Explore-0.903
 replay-0.895
rium-0.889
Token their
Token ID511
Feature activation+8.20e-02

Pos logit contributions
 unden+0.783
 rall+0.766
 arrang+0.721
 reluct+0.715
fort+0.707
Neg logit contributions
ocket-0.505
adiator-0.483
Explore-0.477
 replay-0.475
rium-0.469
Token locker
Token ID17355
Feature activation+1.33e+00

Pos logit contributions
ocket+0.121
 replay+0.117
adiator+0.116
Explore+0.115
rium+0.112
Neg logit contributions
 unden-0.157
 rall-0.153
 arrang-0.143
 reluct-0.142
fort-0.141
Token room
Token ID2119
Feature activation+1.00e+00

Pos logit contributions
ocket+1.359
adiator+1.281
 replay+1.265
Explore+1.252
rium+1.230
Neg logit contributions
 unden-3.148
 rall-3.083
 reluct-2.927
 arrang-2.895
 '.-2.842
Token and
Token ID290
Feature activation+3.26e-02

Pos logit contributions
ocket+1.314
 replay+1.254
adiator+1.253
Explore+1.240
rium+1.216
Neg logit contributions
 unden-2.063
 rall-2.038
 reluct-1.896
 arrang-1.874
 '.-1.851
Token culture
Token ID3968
Feature activation+7.09e-01

Pos logit contributions
ocket+0.046
adiator+0.044
Explore+0.044
 replay+0.044
paces+0.043
Neg logit contributions
 unden-0.064
 rall-0.063
 arrang-0.059
 reluct-0.059
fort-0.058
Token,
Token ID11
Feature activation+1.11e-01

Pos logit contributions
ocket+0.866
adiator+0.824
 replay+0.818
Explore+0.818
paces+0.811
Neg logit contributions
 unden-1.534
 rall-1.510
 reluct-1.409
 arrang-1.408
fort-1.378
Token and
Token ID290
Feature activation-1.38e-02

Pos logit contributions
ocket+0.159
adiator+0.153
Explore+0.152
 replay+0.151
rium+0.148
Neg logit contributions
 unden-0.215
 rall-0.210
 arrang-0.198
 reluct-0.195
fort-0.194
Token they
Token ID484
Feature activation+2.82e-01

Pos logit contributions
 unden+0.026
 rall+0.026
 arrang+0.024
 reluct+0.024
fort+0.024
Neg logit contributions
ocket-0.021
adiator-0.020
Explore-0.020
 replay-0.019
rium-0.019
Token're
Token ID821
Feature activation+7.73e-02

Pos logit contributions
ocket+0.394
 replay+0.379
Explore+0.374
adiator+0.373
rium+0.368
Neg logit contributions
 unden-0.567
 rall-0.550
 arrang-0.519
 reluct-0.513
fort-0.504
Token desperately
Token ID16459
Feature activation+5.20e-01

Pos logit contributions
ocket+0.106
adiator+0.101
 replay+0.100
Explore+0.100
paces+0.098
Neg logit contributions
 unden-0.156
 rall-0.152
 arrang-0.144
 reluct-0.141
fort-0.140
Token border
Token ID4865
Feature activation-2.33e-01

Pos logit contributions
 unden+0.303
 rall+0.294
 arrang+0.275
 reluct+0.273
fort+0.270
Neg logit contributions
ocket-0.275
adiator-0.265
 replay-0.264
Explore-0.262
rium-0.261
Token of
Token ID286
Feature activation-5.41e-02

Pos logit contributions
 unden+0.500
 rall+0.490
 arrang+0.463
 reluct+0.458
fort+0.453
Neg logit contributions
ocket-0.287
adiator-0.274
Explore-0.270
 replay-0.267
rium-0.265
Token the
Token ID262
Feature activation-1.16e-02

Pos logit contributions
 unden+0.101
 rall+0.098
 arrang+0.092
 reluct+0.091
fort+0.090
Neg logit contributions
ocket-0.082
adiator-0.079
 replay-0.079
rium-0.078
Explore-0.078
Token hands
Token ID2832
Feature activation+2.83e-01

Pos logit contributions
 unden+0.022
 rall+0.021
 arrang+0.020
 reluct+0.019
fort+0.019
Neg logit contributions
ocket-0.018
 replay-0.017
adiator-0.017
Explore-0.017
rium-0.017
Token,
Token ID11
Feature activation-9.56e-03

Pos logit contributions
ocket+0.371
adiator+0.349
paces+0.344
Explore+0.343
 replay+0.342
Neg logit contributions
 unden-0.595
 rall-0.583
 arrang-0.548
 reluct-0.544
fort-0.531
Token feet
Token ID3625
Feature activation+4.51e-01

Pos logit contributions
 unden+0.018
 rall+0.018
 arrang+0.017
 reluct+0.017
fort+0.016
Neg logit contributions
ocket-0.014
adiator-0.013
Explore-0.013
 replay-0.013
rium-0.013
Token,
Token ID11
Feature activation-9.05e-02

Pos logit contributions
ocket+0.550
adiator+0.515
Explore+0.511
paces+0.505
 replay+0.505
Neg logit contributions
 unden-0.980
 rall-0.964
 arrang-0.907
 reluct-0.902
 '.-0.887
Token and
Token ID290
Feature activation-1.57e-01

Pos logit contributions
 unden+0.179
 rall+0.175
 arrang+0.165
 reluct+0.162
fort+0.161
Neg logit contributions
ocket-0.127
adiator-0.121
Explore-0.120
 replay-0.120
rium-0.120
Token wrists
Token ID38163
Feature activation+5.13e-01

Pos logit contributions
 unden+0.296
 rall+0.288
 arrang+0.271
 reluct+0.267
fort+0.265
Neg logit contributions
ocket-0.235
adiator-0.225
Explore-0.223
 replay-0.223
rium-0.222
Token.[
Token ID3693
Feature activation+6.19e-01

Pos logit contributions
ocket+0.653
adiator+0.614
paces+0.606
Explore+0.605
 replay+0.603
Neg logit contributions
 unden-1.094
 rall-1.075
 arrang-1.009
 reluct-1.002
fort-0.981
Token1
Token ID16
Feature activation+2.07e-01

Pos logit contributions
ocket+0.662
Explore+0.624
adiator+0.623
 replay+0.611
rium+0.604
Neg logit contributions
 unden-1.443
 rall-1.411
 arrang-1.344
 reluct-1.334
 '.-1.305
Token
Token ID198
Feature activation-8.15e-02

Pos logit contributions
 unden+0.099
 rall+0.097
 arrang+0.091
 reluct+0.090
fort+0.089
Neg logit contributions
ocket-0.062
adiator-0.060
Explore-0.059
 replay-0.058
rium-0.058
Token
Token ID447
Feature activation-1.29e-01

Pos logit contributions
 unden+0.174
 rall+0.171
 arrang+0.162
 reluct+0.160
 '.+0.158
Neg logit contributions
ocket-0.102
adiator-0.097
Explore-0.096
 replay-0.094
rium-0.094
Token
Token ID250
Feature activation-1.33e-01

Pos logit contributions
 unden+0.271
 rall+0.265
 arrang+0.251
 reluct+0.248
fort+0.245
Neg logit contributions
ocket-0.166
adiator-0.159
Explore-0.157
 replay-0.154
rium-0.154
TokenA
Token ID32
Feature activation-2.78e-02

Pos logit contributions
 unden+0.283
 rall+0.278
 arrang+0.262
 reluct+0.260
fort+0.257
Neg logit contributions
ocket-0.167
adiator-0.160
Explore-0.158
 replay-0.155
rium-0.154
Token lot
Token ID1256
Feature activation+9.82e-02

Pos logit contributions
 unden+0.052
 rall+0.050
 arrang+0.047
 reluct+0.047
fort+0.046
Neg logit contributions
ocket-0.043
adiator-0.041
Explore-0.040
 replay-0.040
rium-0.040
Token of
Token ID286
Feature activation+2.67e-01

Pos logit contributions
ocket+0.119
adiator+0.113
Explore+0.112
 replay+0.110
rium+0.109
Neg logit contributions
 unden-0.213
 rall-0.209
 arrang-0.198
 reluct-0.196
fort-0.194
Token what
Token ID644
Feature activation-1.28e-01

Pos logit contributions
ocket+0.395
adiator+0.378
Explore+0.377
 replay+0.374
rium+0.372
Neg logit contributions
 unden-0.505
 rall-0.494
 arrang-0.463
 reluct-0.457
fort-0.452
Token we
Token ID356
Feature activation+5.38e-02

Pos logit contributions
 unden+0.246
 rall+0.240
 arrang+0.225
 reluct+0.222
fort+0.220
Neg logit contributions
ocket-0.187
adiator-0.180
Explore-0.179
 replay-0.177
rium-0.176
Token know
Token ID760
Feature activation-1.78e-01

Pos logit contributions
ocket+0.077
Explore+0.074
adiator+0.074
 replay+0.073
rium+0.072
Neg logit contributions
 unden-0.105
 rall-0.102
 arrang-0.097
 reluct-0.095
fort-0.094
Token about
Token ID546
Feature activation-1.80e-01

Pos logit contributions
 unden+0.283
 rall+0.276
 arrang+0.255
 reluct+0.252
 '.+0.246
Neg logit contributions
ocket-0.321
adiator-0.311
Explore-0.309
 replay-0.305
rium-0.305
Token Philadelphia
Token ID8857
Feature activation-3.30e-02

Pos logit contributions
 unden+0.318
 rall+0.309
 arrang+0.289
 reluct+0.286
fort+0.282
Neg logit contributions
ocket-0.289
adiator-0.278
Explore-0.276
 replay-0.274
rium-0.272
Token is
Token ID318
Feature activation-1.96e-01

Pos logit contributions
ocket+0.620
adiator+0.593
Explore+0.589
 replay+0.588
iversity+0.578
Neg logit contributions
 unden-0.973
 rall-0.955
 arrang-0.895
 reluct-0.890
 '.-0.879
Token a
Token ID257
Feature activation+1.64e-01

Pos logit contributions
 unden+0.362
 rall+0.354
 arrang+0.331
 reluct+0.328
 '.+0.323
Neg logit contributions
ocket-0.302
adiator-0.290
Explore-0.288
 replay-0.285
rium-0.283
Token breath
Token ID8033
Feature activation+4.88e-01

Pos logit contributions
ocket+0.255
adiator+0.245
Explore+0.242
 replay+0.241
rium+0.238
Neg logit contributions
 unden-0.302
 rall-0.295
 arrang-0.276
 reluct-0.273
fort-0.269
Token of
Token ID286
Feature activation+4.90e-02

Pos logit contributions
ocket+0.570
adiator+0.541
Explore+0.533
 replay+0.527
rium+0.519
Neg logit contributions
 unden-1.082
 rall-1.061
 arrang-1.006
 reluct-0.996
 '.-0.985
Token fresh
Token ID4713
Feature activation-3.54e-01

Pos logit contributions
ocket+0.089
adiator+0.086
Explore+0.085
 replay+0.085
rium+0.084
Neg logit contributions
 unden-0.077
 rall-0.075
 arrang-0.069
 reluct-0.068
fort-0.067
Token air
Token ID1633
Feature activation+1.03e-01

Pos logit contributions
 unden+0.619
 rall+0.605
 arrang+0.565
 reluct+0.557
fort+0.549
Neg logit contributions
ocket-0.576
adiator-0.556
Explore-0.551
 replay-0.546
rium-0.544
Token in
Token ID287
Feature activation+3.07e-02

Pos logit contributions
ocket+0.147
adiator+0.141
Explore+0.139
 replay+0.137
rium+0.137
Neg logit contributions
 unden-0.200
 rall-0.196
 arrang-0.184
 reluct-0.182
fort-0.180
Token a
Token ID257
Feature activation+1.25e-01

Pos logit contributions
ocket+0.047
adiator+0.045
Explore+0.045
 replay+0.045
rium+0.044
Neg logit contributions
 unden-0.056
 rall-0.055
 arrang-0.052
 reluct-0.051
fort-0.050
Token TV
Token ID3195
Feature activation+7.74e-01

Pos logit contributions
ocket+0.184
adiator+0.177
Explore+0.175
 replay+0.173
rium+0.172
Neg logit contributions
 unden-0.239
 rall-0.233
 arrang-0.219
 reluct-0.217
fort-0.214
Token landscape
Token ID10747
Feature activation+1.79e-02

Pos logit contributions
ocket+1.176
adiator+1.131
Explore+1.120
 replay+1.110
rium+1.101
Neg logit contributions
 unden-1.437
 rall-1.408
 arrang-1.317
 reluct-1.303
 '.-1.288
Token that
Token ID326
Feature activation-9.94e-02

Pos logit contributions
ocket+0.024
adiator+0.023
Explore+0.022
 replay+0.022
rium+0.022
Neg logit contributions
 unden-0.037
 rall-0.036
 arrang-0.034
 reluct-0.034
fort-0.033
Token--+
Token ID44785
Feature activation-4.58e-01

Pos logit contributions
 unden+0.522
 rall+0.513
 arrang+0.487
 '.+0.481
fort+0.480
Neg logit contributions
ocket-0.263
adiator-0.249
Explore-0.245
 replay-0.242
rium-0.241
Token |
Token ID930
Feature activation-1.22e-02

Pos logit contributions
 unden+0.752
 rall+0.728
 arrang+0.678
 reluct+0.670
fort+0.650
Neg logit contributions
ocket-0.808
adiator-0.781
Explore-0.776
 replay-0.770
rium-0.764
Token...
Token ID2644
Feature activation+7.92e-01

Pos logit contributions
 unden+0.027
 rall+0.026
 arrang+0.025
 reluct+0.024
fort+0.024
Neg logit contributions
ocket-0.015
adiator-0.014
Explore-0.014
 replay-0.014
rium-0.013
Token |
Token ID930
Feature activation-3.44e-02

Pos logit contributions
ocket+1.315
Explore+1.270
 replay+1.265
adiator+1.265
rium+1.249
Neg logit contributions
 unden-1.437
 rall-1.374
 reluct-1.296
 arrang-1.295
fort-1.185
Token +
Token ID1343
Feature activation-3.63e-01

Pos logit contributions
 unden+0.054
 rall+0.052
 arrang+0.048
 reluct+0.048
fort+0.047
Neg logit contributions
ocket-0.062
adiator-0.060
 replay-0.060
Explore-0.060
rium-0.059
Token--------------------
Token ID19351
Feature activation-2.08e-01

Pos logit contributions
 unden+0.691
 rall+0.675
 arrang+0.634
 reluct+0.626
fort+0.618
Neg logit contributions
ocket-0.538
adiator-0.517
Explore-0.511
 replay-0.505
rium-0.503
Token--+
Token ID44785
Feature activation-4.07e-01

Pos logit contributions
 unden+0.465
 rall+0.456
 arrang+0.433
 '.+0.428
fort+0.428
Neg logit contributions
ocket-0.235
adiator-0.222
Explore-0.219
 replay-0.216
rium-0.215
Token +
Token ID1343
Feature activation-2.53e-01

Pos logit contributions
 unden+0.643
 rall+0.621
 arrang+0.576
 reluct+0.571
fort+0.549
Neg logit contributions
ocket-0.745
adiator-0.720
Explore-0.717
 replay-0.715
rium-0.707
Token--------------------
Token ID19351
Feature activation-1.47e-01

Pos logit contributions
 unden+0.486
 rall+0.475
 arrang+0.446
 reluct+0.441
 '.+0.433
Neg logit contributions
ocket-0.371
adiator-0.356
Explore-0.354
 replay-0.349
rium-0.347
Token--+
Token ID44785
Feature activation-4.12e-01

Pos logit contributions
 unden+0.329
 rall+0.322
 arrang+0.307
 '.+0.303
fort+0.303
Neg logit contributions
ocket-0.166
adiator-0.158
Explore-0.155
 replay-0.153
rium-0.152
Token <
Token ID1279
Feature activation-1.15e+00

Pos logit contributions
 unden+0.685
 rall+0.667
 arrang+0.619
 reluct+0.610
fort+0.600
Neg logit contributions
ocket-0.711
adiator-0.685
Explore-0.681
 replay-0.677
rium-0.670
TokenInternational
Token ID24274
Feature activation-4.89e-01

Pos logit contributions
ocket+0.806
Explore+0.775
adiator+0.771
Weak+0.750
 replay+0.747
Neg logit contributions
 unden-1.358
 rall-1.331
 arrang-1.258
 reluct-1.252
 '.-1.220
Token goals
Token ID4661
Feature activation+8.54e-02

Pos logit contributions
 unden+0.944
 rall+0.922
 arrang+0.867
 reluct+0.856
 '.+0.846
Neg logit contributions
ocket-0.710
adiator-0.683
Explore-0.675
 replay-0.665
rium-0.663
Token
Token ID198
Feature activation+3.47e-01

Pos logit contributions
ocket+0.125
adiator+0.120
Explore+0.118
 replay+0.118
paces+0.117
Neg logit contributions
 unden-0.164
 rall-0.160
 arrang-0.151
 reluct-0.149
fort-0.147
Token
Token ID198
Feature activation+2.71e-01

Pos logit contributions
ocket+0.439
adiator+0.418
Explore+0.417
 replay+0.410
rium+0.407
Neg logit contributions
 unden-0.753
 rall-0.734
 arrang-0.697
 reluct-0.693
 '.-0.665
TokenAs
Token ID1722
Feature activation+1.11e-01

Pos logit contributions
ocket+0.332
Explore+0.317
adiator+0.317
 replay+0.307
rium+0.306
Neg logit contributions
 unden-0.587
 rall-0.575
 arrang-0.544
 reluct-0.540
 '.-0.529
Token of
Token ID286
Feature activation+1.57e-02

Pos logit contributions
ocket+0.164
adiator+0.158
Explore+0.156
 replay+0.154
rium+0.154
Neg logit contributions
 unden-0.212
 rall-0.207
 arrang-0.194
 reluct-0.192
fort-0.189
Token 12
Token ID1105
Feature activation-3.90e-02

Pos logit contributions
ocket+0.024
adiator+0.023
 replay+0.023
Explore+0.023
rium+0.022
Neg logit contributions
 unden-0.029
 rall-0.028
 arrang-0.027
 reluct-0.027
fort-0.026
Token June
Token ID2795
Feature activation-2.66e-01

Pos logit contributions
 unden+0.069
 rall+0.067
 arrang+0.063
 reluct+0.063
fort+0.061
Neg logit contributions
ocket-0.063
adiator-0.061
Explore-0.060
 replay-0.060
iversity-0.059
Token 2016
Token ID1584
Feature activation+2.77e-02

Pos logit contributions
 unden+0.640
 rall+0.628
 arrang+0.598
 reluct+0.592
fort+0.586
Neg logit contributions
ocket-0.260
adiator-0.244
Explore-0.241
 replay-0.237
rium-0.234
Token[
Token ID58
Feature activation-2.73e-01

Pos logit contributions
ocket+0.038
adiator+0.036
Explore+0.036
 replay+0.035
rium+0.035
Neg logit contributions
 unden-0.056
 rall-0.055
 arrang-0.052
 reluct-0.051
fort-0.050
Token91
Token ID6420
Feature activation-1.74e-01

Pos logit contributions
 unden+0.519
 rall+0.506
 arrang+0.475
 reluct+0.470
 '.+0.460
Neg logit contributions
ocket-0.408
adiator-0.391
Explore-0.389
 replay-0.383
rium-0.381
Token U
Token ID471
Feature activation+2.13e-01

Pos logit contributions
 unden+0.681
 rall+0.665
 arrang+0.624
 reluct+0.618
fort+0.611
Neg logit contributions
ocket-0.498
adiator-0.472
 replay-0.472
Explore-0.469
rium-0.462
Token.
Token ID13
Feature activation+9.23e-04

Pos logit contributions
ocket+0.265
adiator+0.252
Explore+0.251
 replay+0.246
rium+0.245
Neg logit contributions
 unden-0.462
 rall-0.452
 arrang-0.428
 reluct-0.425
 '.-0.414
TokenS
Token ID50
Feature activation-6.53e-02

Pos logit contributions
ocket+0.001
adiator+0.001
Explore+0.001
 replay+0.001
rium+0.001
Neg logit contributions
 unden-0.002
 rall-0.002
 arrang-0.002
 reluct-0.002
fort-0.002
Token.
Token ID13
Feature activation-1.33e-01

Pos logit contributions
 unden+0.144
 rall+0.141
 arrang+0.134
 reluct+0.133
fort+0.130
Neg logit contributions
ocket-0.078
adiator-0.074
Explore-0.073
rium-0.072
 replay-0.072
Token energy
Token ID2568
Feature activation+1.04e-01

Pos logit contributions
 unden+0.275
 rall+0.269
 arrang+0.254
 reluct+0.251
fort+0.249
Neg logit contributions
ocket-0.176
adiator-0.167
Explore-0.165
 replay-0.165
rium-0.163
Token policy
Token ID2450
Feature activation-3.97e-01

Pos logit contributions
ocket+0.151
adiator+0.144
 replay+0.143
Explore+0.143
rium+0.140
Neg logit contributions
 unden-0.200
 rall-0.195
 arrang-0.183
 reluct-0.183
 '.-0.180
Token,
Token ID11
Feature activation+5.45e-02

Pos logit contributions
 unden+0.827
 rall+0.809
 arrang+0.763
 reluct+0.756
fort+0.746
Neg logit contributions
ocket-0.519
adiator-0.495
Explore-0.489
 replay-0.485
rium-0.480
Token something
Token ID1223
Feature activation-7.45e-01

Pos logit contributions
ocket+0.082
Explore+0.079
 replay+0.079
adiator+0.078
paces+0.077
Neg logit contributions
 unden-0.102
 rall-0.099
 arrang-0.093
 reluct-0.093
fort-0.091
Token that
Token ID326
Feature activation-6.40e-02

Pos logit contributions
 unden+1.402
 rall+1.369
 arrang+1.283
 reluct+1.268
fort+1.253
Neg logit contributions
ocket-1.119
adiator-1.078
Explore-1.064
 replay-1.051
rium-1.048
Token the
Token ID262
Feature activation+3.05e-02

Pos logit contributions
 unden+0.121
 rall+0.118
 arrang+0.111
 reluct+0.109
fort+0.108
Neg logit contributions
ocket-0.095
adiator-0.091
Explore-0.091
 replay-0.090
rium-0.089
Token country
Token ID1499
Feature activation-6.54e-03

Pos logit contributions
ocket+0.047
adiator+0.045
 replay+0.045
Explore+0.045
rium+0.045
Neg logit contributions
 unden-0.056
 rall-0.054
 arrang-0.051
 reluct-0.050
fort-0.050
Token period
Token ID2278
Feature activation+2.41e-01

Pos logit contributions
ocket+0.110
adiator+0.105
 replay+0.104
Explore+0.103
paces+0.102
Neg logit contributions
 unden-0.143
 rall-0.140
 arrang-0.131
 reluct-0.130
fort-0.128
Token.
Token ID13
Feature activation-5.76e-02

Pos logit contributions
ocket+0.292
adiator+0.279
Explore+0.272
 replay+0.271
iversity+0.270
Neg logit contributions
 unden-0.522
 rall-0.513
 arrang-0.484
 reluct-0.480
 '.-0.473
Token But
Token ID887
Feature activation+3.48e-01

Pos logit contributions
 unden+0.116
 rall+0.112
 arrang+0.107
 reluct+0.107
fort+0.102
Neg logit contributions
ocket-0.082
Explore-0.078
adiator-0.077
 replay-0.077
paces-0.076
Token Section
Token ID7275
Feature activation+1.07e+00

Pos logit contributions
ocket+0.497
 replay+0.472
adiator+0.466
Explore+0.462
paces+0.459
Neg logit contributions
 unden-0.680
 rall-0.659
 arrang-0.626
 reluct-0.621
fort-0.611
Token 2
Token ID362
Feature activation+2.33e-01

Pos logit contributions
ocket+1.602
adiator+1.535
 replay+1.528
Explore+1.513
rium+1.492
Neg logit contributions
 unden-2.009
 rall-1.938
 arrang-1.830
 reluct-1.815
fort-1.783
Token of
Token ID286
Feature activation+2.22e-02

Pos logit contributions
ocket+0.293
adiator+0.277
Explore+0.272
 replay+0.270
paces+0.267
Neg logit contributions
 unden-0.496
 rall-0.486
 arrang-0.460
 reluct-0.455
 '.-0.450
Token the
Token ID262
Feature activation-4.04e-02

Pos logit contributions
ocket+0.036
adiator+0.034
 replay+0.034
Explore+0.034
rium+0.034
Neg logit contributions
 unden-0.040
 rall-0.038
 arrang-0.036
 reluct-0.036
fort-0.035
Token law
Token ID1099
Feature activation-6.43e-01

Pos logit contributions
 unden+0.080
 rall+0.077
 arrang+0.074
 reluct+0.073
fort+0.072
Neg logit contributions
ocket-0.057
adiator-0.054
 replay-0.054
Explore-0.053
rium-0.053
Token wasn
Token ID2492
Feature activation-4.40e-01

Pos logit contributions
 unden+1.254
 rall+1.225
 arrang+1.152
 reluct+1.139
fort+1.125
Neg logit contributions
ocket-0.923
adiator-0.885
Explore-0.875
 replay-0.866
rium-0.860
Token't
Token ID470
Feature activation-3.86e-01

Pos logit contributions
 unden+0.848
 rall+0.829
 arrang+0.779
 reluct+0.769
fort+0.762
Neg logit contributions
ocket-0.638
adiator-0.613
Explore-0.606
 replay-0.599
rium-0.596
Token affected
Token ID5676
Feature activation-4.19e-01

Pos logit contributions
 unden+0.740
 rall+0.721
 arrang+0.680
 reluct+0.674
fort+0.664
Neg logit contributions
ocket-0.574
adiator-0.542
 replay-0.539
Explore-0.537
rium-0.528
Token the
Token ID262
Feature activation-5.92e-02

Pos logit contributions
ocket+1.116
adiator+1.077
 replay+1.073
Explore+1.072
rium+1.063
Neg logit contributions
 unden-1.315
 rall-1.282
 arrang-1.203
 reluct-1.196
 '.-1.164
Token isolated
Token ID11557
Feature activation-4.01e-01

Pos logit contributions
 unden+0.104
 rall+0.101
 arrang+0.095
 reluct+0.094
 '.+0.092
Neg logit contributions
ocket-0.095
adiator-0.092
Explore-0.091
 replay-0.091
rium-0.090
Token settlement
Token ID9443
Feature activation+2.72e-01

Pos logit contributions
 unden+0.747
 rall+0.726
 arrang+0.679
 reluct+0.675
 '.+0.664
Neg logit contributions
ocket-0.609
adiator-0.587
Explore-0.582
 replay-0.580
rium-0.572
Token-
Token ID12
Feature activation+2.81e-02

Pos logit contributions
ocket+0.390
adiator+0.374
Explore+0.372
 replay+0.367
rium+0.366
Neg logit contributions
 unden-0.526
 rall-0.514
 reluct-0.479
 arrang-0.479
 '.-0.472
Tokencity
Token ID19205
Feature activation-2.51e-01

Pos logit contributions
ocket+0.041
Explore+0.040
adiator+0.039
rium+0.039
paces+0.039
Neg logit contributions
 unden-0.055
 rall-0.053
 reluct-0.050
 arrang-0.049
 '.-0.048
Token of
Token ID286
Feature activation+1.32e-02

Pos logit contributions
 unden+0.497
 rall+0.485
 arrang+0.455
 reluct+0.452
 '.+0.446
Neg logit contributions
ocket-0.351
adiator-0.337
Explore-0.333
 replay-0.329
rium-0.328
Token Ariel
Token ID33364
Feature activation+1.77e-01

Pos logit contributions
ocket+0.022
adiator+0.021
Explore+0.021
rium+0.021
 replay+0.021
Neg logit contributions
 unden-0.023
 rall-0.022
 reluct-0.021
 arrang-0.021
fort-0.020
Token and
Token ID290
Feature activation-4.39e-02

Pos logit contributions
ocket+0.245
adiator+0.235
Explore+0.232
rium+0.228
 replay+0.228
Neg logit contributions
 unden-0.354
 rall-0.347
 arrang-0.326
 reluct-0.323
 '.-0.319
Token the
Token ID262
Feature activation+4.82e-02

Pos logit contributions
 unden+0.079
 rall+0.078
 arrang+0.072
 reluct+0.072
fort+0.070
Neg logit contributions
ocket-0.069
adiator-0.067
Explore-0.066
 replay-0.065
rium-0.065
Token Green
Token ID3469
Feature activation+8.95e-02

Pos logit contributions
ocket+0.077
adiator+0.075
Explore+0.074
 replay+0.074
rium+0.074
Neg logit contributions
 unden-0.085
 rall-0.083
 arrang-0.077
 reluct-0.077
fort-0.075
Token line
Token ID1627
Feature activation-2.75e-01

Pos logit contributions
ocket+0.164
adiator+0.159
Explore+0.157
 replay+0.156
rium+0.155
Neg logit contributions
 unden-0.140
 rall-0.135
 arrang-0.125
 reluct-0.124
 '.-0.121
Token do
Token ID466
Feature activation-2.83e-02

Pos logit contributions
ocket+0.047
 replay+0.046
Explore+0.045
adiator+0.045
paces+0.044
Neg logit contributions
 unden-0.059
 rall-0.057
 reluct-0.054
 arrang-0.053
fort-0.052
Token nothing
Token ID2147
Feature activation-4.77e-01

Pos logit contributions
 unden+0.059
 rall+0.058
 arrang+0.055
 reluct+0.054
fort+0.053
Neg logit contributions
ocket-0.037
adiator-0.035
Explore-0.035
 replay-0.034
rium-0.034
Token and
Token ID290
Feature activation-1.83e-01

Pos logit contributions
 unden+0.911
 rall+0.890
 arrang+0.838
 reluct+0.826
fort+0.819
Neg logit contributions
ocket-0.698
adiator-0.672
Explore-0.664
 replay-0.656
rium-0.654
Token continue
Token ID2555
Feature activation-7.28e-01

Pos logit contributions
 unden+0.350
 rall+0.341
 arrang+0.320
 reluct+0.317
fort+0.313
Neg logit contributions
ocket-0.272
adiator-0.259
 replay-0.258
Explore-0.258
rium-0.253
Token making
Token ID1642
Feature activation-1.95e-01

Pos logit contributions
 unden+1.471
 rall+1.437
 arrang+1.354
 reluct+1.340
fort+1.325
Neg logit contributions
ocket-0.996
adiator-0.953
Explore-0.942
 replay-0.930
rium-0.924
Token temporary
Token ID8584
Feature activation-1.07e+00

Pos logit contributions
 unden+0.355
 rall+0.344
 arrang+0.319
 reluct+0.318
fort+0.314
Neg logit contributions
ocket-0.310
adiator-0.297
Explore-0.294
 replay-0.294
rium-0.289
Token repairs
Token ID20097
Feature activation-9.50e-01

Pos logit contributions
 unden+1.716
 rall+1.664
 arrang+1.536
 reluct+1.522
fort+1.499
Neg logit contributions
ocket-1.930
adiator-1.864
Explore-1.847
 replay-1.833
rium-1.818
Token.
Token ID13
Feature activation-6.65e-02

Pos logit contributions
 unden+1.826
 rall+1.785
 arrang+1.677
 reluct+1.657
fort+1.638
Neg logit contributions
ocket-1.384
adiator-1.331
Explore-1.316
 replay-1.299
rium-1.294
Token
Token ID198
Feature activation-1.47e-01

Pos logit contributions
 unden+0.137
 rall+0.134
 arrang+0.126
 reluct+0.125
fort+0.122
Neg logit contributions
ocket-0.090
Explore-0.085
adiator-0.085
 replay-0.084
rium-0.083
Token
Token ID198
Feature activation-1.79e-01

Pos logit contributions
 unden+0.300
 rall+0.294
 arrang+0.277
 reluct+0.274
fort+0.273
Neg logit contributions
ocket-0.195
adiator-0.187
Explore-0.184
 replay-0.182
rium-0.181
TokenCity
Token ID14941
Feature activation-2.37e-01

Pos logit contributions
 unden+0.388
 rall+0.380
 arrang+0.359
 reluct+0.356
 '.+0.351
Neg logit contributions
ocket-0.220
adiator-0.210
Explore-0.208
 replay-0.204
rium-0.203
Token the
Token ID262
Feature activation-1.81e-01

Pos logit contributions
 unden+0.339
 rall+0.331
 arrang+0.309
 reluct+0.307
fort+0.303
Neg logit contributions
ocket-0.281
adiator-0.269
 replay-0.267
Explore-0.267
rium-0.264
Token city
Token ID1748
Feature activation-9.74e-02

Pos logit contributions
 unden+0.335
 rall+0.326
 arrang+0.305
 reluct+0.303
fort+0.300
Neg logit contributions
ocket-0.277
adiator-0.266
 replay-0.263
Explore-0.262
rium-0.260
Token is
Token ID318
Feature activation-1.38e-01

Pos logit contributions
 unden+0.195
 rall+0.190
 arrang+0.179
 reluct+0.178
fort+0.175
Neg logit contributions
ocket-0.135
adiator-0.129
Explore-0.127
 replay-0.127
rium-0.126
Token supposed
Token ID4385
Feature activation-5.91e-01

Pos logit contributions
 unden+0.252
 rall+0.245
 arrang+0.229
 reluct+0.226
fort+0.222
Neg logit contributions
ocket-0.218
adiator-0.209
 replay-0.206
Explore-0.206
rium-0.204
Token to
Token ID284
Feature activation-8.51e-02

Pos logit contributions
 unden+1.179
 rall+1.160
fort+1.100
 '.+1.097
 arrang+1.093
Neg logit contributions
ocket-0.782
adiator-0.749
Explore-0.735
rium-0.725
 replay-0.721
Token fix
Token ID4259
Feature activation-1.75e+00

Pos logit contributions
 unden+0.165
 rall+0.160
 reluct+0.151
 arrang+0.149
fort+0.146
Neg logit contributions
ocket-0.125
 replay-0.122
Explore-0.118
adiator-0.118
 crawl-0.117
Token the
Token ID262
Feature activation-1.52e-01

Pos logit contributions
 unden+3.344
 rall+3.278
 arrang+3.089
 reluct+3.033
 '.+3.020
Neg logit contributions
ocket-2.529
adiator-2.444
Explore-2.415
 replay-2.371
rium-2.366
Token sidewalks
Token ID38282
Feature activation-6.45e-03

Pos logit contributions
 unden+0.282
 rall+0.273
 arrang+0.255
 reluct+0.254
fort+0.252
Neg logit contributions
ocket-0.233
 replay-0.221
adiator-0.221
Explore-0.219
rium-0.218
Token,
Token ID11
Feature activation-1.02e-01

Pos logit contributions
 unden+0.013
 rall+0.013
 arrang+0.012
 reluct+0.012
fort+0.012
Neg logit contributions
ocket-0.009
adiator-0.008
Explore-0.008
 replay-0.008
paces-0.008
Token at
Token ID379
Feature activation-1.66e-01

Pos logit contributions
 unden+0.199
 rall+0.193
 arrang+0.182
 reluct+0.182
fort+0.179
Neg logit contributions
ocket-0.146
adiator-0.139
 replay-0.138
Explore-0.138
paces-0.136
Token their
Token ID511
Feature activation-1.05e-01

Pos logit contributions
 unden+0.303
 rall+0.295
 arrang+0.277
 reluct+0.274
fort+0.270
Neg logit contributions
ocket-0.258
adiator-0.248
rium-0.246
Explore-0.245
 replay-0.245
Token and
Token ID290
Feature activation-4.95e-02

Pos logit contributions
ocket+0.208
adiator+0.199
Explore+0.197
 replay+0.196
rium+0.194
Neg logit contributions
 unden-0.278
 rall-0.272
 arrang-0.256
 reluct-0.253
 '.-0.250
Token whiff
Token ID48112
Feature activation+7.26e-02

Pos logit contributions
 unden+0.089
 rall+0.087
 arrang+0.082
 reluct+0.081
fort+0.080
Neg logit contributions
ocket-0.078
adiator-0.075
Explore-0.074
 replay-0.074
rium-0.073
Tokenling
Token ID1359
Feature activation+1.71e-01

Pos logit contributions
ocket+0.096
adiator+0.092
Explore+0.090
 replay+0.089
rium+0.089
Neg logit contributions
 unden-0.150
 rall-0.147
 arrang-0.138
 reluct-0.137
 '.-0.135
Token and
Token ID290
Feature activation+1.57e-02

Pos logit contributions
ocket+0.221
adiator+0.211
Explore+0.209
 replay+0.207
rium+0.206
Neg logit contributions
 unden-0.357
 rall-0.349
 arrang-0.330
 reluct-0.326
 '.-0.323
Token w
Token ID266
Feature activation+3.08e-02

Pos logit contributions
ocket+0.025
adiator+0.024
Explore+0.024
 replay+0.023
rium+0.023
Neg logit contributions
 unden-0.028
 rall-0.028
 arrang-0.026
 reluct-0.025
fort-0.025
Tokenaff
Token ID2001
Feature activation-1.49e+00

Pos logit contributions
ocket+0.029
adiator+0.028
Explore+0.027
 replay+0.027
rium+0.027
Neg logit contributions
 unden-0.075
 rall-0.073
 arrang-0.070
 reluct-0.069
fort-0.068
Tokenling
Token ID1359
Feature activation-1.23e-01

Pos logit contributions
 unden+2.904
 rall+2.844
 arrang+2.671
 reluct+2.641
fort+2.623
Neg logit contributions
ocket-2.124
adiator-2.039
Explore-2.016
 replay-1.989
rium-1.975
Token of
Token ID286
Feature activation-4.69e-02

Pos logit contributions
 unden+0.250
 rall+0.244
 arrang+0.230
 reluct+0.228
 '.+0.225
Neg logit contributions
ocket-0.167
adiator-0.160
Explore-0.158
 replay-0.156
rium-0.155
Token the
Token ID262
Feature activation-6.35e-02

Pos logit contributions
 unden+0.086
 rall+0.084
 arrang+0.078
 reluct+0.077
fort+0.077
Neg logit contributions
ocket-0.073
adiator-0.070
Explore-0.069
 replay-0.069
rium-0.069
Token trolls
Token ID24727
Feature activation+1.02e-02

Pos logit contributions
 unden+0.116
 rall+0.114
 arrang+0.107
 reluct+0.105
fort+0.104
Neg logit contributions
ocket-0.098
adiator-0.094
Explore-0.094
 replay-0.093
rium-0.092
Token)
Token ID8
Feature activation-8.33e-02

Pos logit contributions
ocket+0.013
adiator+0.013
Explore+0.012
 replay+0.012
rium+0.012
Neg logit contributions
 unden-0.021
 rall-0.021
 arrang-0.020
 reluct-0.019
 '.-0.019
Token Ferrari
Token ID23502
Feature activation-6.87e-02

Pos logit contributions
 unden+0.363
 rall+0.353
 arrang+0.331
 reluct+0.327
fort+0.322
Neg logit contributions
ocket-0.327
adiator-0.315
Explore-0.313
 replay-0.311
rium-0.308
Token,
Token ID11
Feature activation-1.69e-02

Pos logit contributions
 unden+0.141
 rall+0.137
 arrang+0.130
 reluct+0.128
fort+0.126
Neg logit contributions
ocket-0.092
adiator-0.088
Explore-0.087
 replay-0.086
rium-0.085
Token believes
Token ID5804
Feature activation+3.01e-01

Pos logit contributions
 unden+0.032
 rall+0.031
 arrang+0.030
 reluct+0.029
fort+0.029
Neg logit contributions
ocket-0.025
adiator-0.024
Explore-0.024
 replay-0.024
paces-0.023
Token the
Token ID262
Feature activation+1.16e-01

Pos logit contributions
ocket+0.434
 replay+0.417
Explore+0.415
adiator+0.415
rium+0.404
Neg logit contributions
 unden-0.582
 rall-0.564
 arrang-0.532
 reluct-0.527
fort-0.521
Token true
Token ID2081
Feature activation+2.81e-01

Pos logit contributions
ocket+0.169
 replay+0.162
adiator+0.162
Explore+0.160
rium+0.158
Neg logit contributions
 unden-0.222
 rall-0.215
 arrang-0.202
 reluct-0.201
fort-0.198
Token pe
Token ID613
Feature activation-1.07e+00

Pos logit contributions
ocket+0.420
adiator+0.402
 replay+0.402
Explore+0.400
rium+0.392
Neg logit contributions
 unden-0.527
 rall-0.514
 arrang-0.484
 reluct-0.479
fort-0.474
Tokencking
Token ID44377
Feature activation-2.08e-01

Pos logit contributions
 unden+2.297
 rall+2.257
 arrang+2.141
fort+2.118
 '.+2.111
Neg logit contributions
ocket-1.289
Explore-1.224
adiator-1.215
 replay-1.198
rium-1.192
Token order
Token ID1502
Feature activation-5.80e-02

Pos logit contributions
 unden+0.336
 rall+0.326
 arrang+0.301
 reluct+0.298
fort+0.293
Neg logit contributions
ocket-0.369
adiator-0.356
Explore-0.353
 replay-0.351
rium-0.348
Token is
Token ID318
Feature activation+1.92e-01

Pos logit contributions
 unden+0.113
 rall+0.111
 arrang+0.104
 reluct+0.103
fort+0.101
Neg logit contributions
ocket-0.083
adiator-0.080
Explore-0.079
 replay-0.078
rium-0.078
Token yet
Token ID1865
Feature activation-3.22e-01

Pos logit contributions
ocket+0.274
adiator+0.263
Explore+0.262
 replay+0.260
rium+0.256
Neg logit contributions
 unden-0.372
 rall-0.366
 arrang-0.344
 reluct-0.342
fort-0.336
Token to
Token ID284
Feature activation+1.59e-01

Pos logit contributions
 unden+0.684
 rall+0.671
 arrang+0.634
 reluct+0.627
fort+0.620
Neg logit contributions
ocket-0.404
adiator-0.385
Explore-0.380
 replay-0.375
rium-0.373
Token
Token ID220
Feature activation-3.52e-01

Pos logit contributions
 unden+0.135
 rall+0.132
 arrang+0.124
 reluct+0.123
fort+0.121
Neg logit contributions
ocket-0.110
adiator-0.106
Explore-0.105
 replay-0.104
rium-0.103
Tokeners
Token ID364
Feature activation-9.46e-02

Pos logit contributions
 unden+0.703
 rall+0.687
 arrang+0.647
 reluct+0.641
 '.+0.632
Neg logit contributions
ocket-0.492
adiator-0.470
Explore-0.465
 replay-0.457
rium-0.456
Tokenatz
Token ID27906
Feature activation+1.72e-01

Pos logit contributions
 unden+0.161
 rall+0.157
 arrang+0.146
 reluct+0.144
fort+0.142
Neg logit contributions
ocket-0.159
adiator-0.154
Explore-0.152
 replay-0.151
rium-0.150
Token "
Token ID366
Feature activation+7.47e-02

Pos logit contributions
ocket+0.255
adiator+0.247
 replay+0.245
Explore+0.244
rium+0.240
Neg logit contributions
 unden-0.324
 rall-0.315
 arrang-0.296
 reluct-0.295
fort-0.289
Tokensocial
Token ID14557
Feature activation-1.30e+00

Pos logit contributions
ocket+0.108
adiator+0.104
Explore+0.104
rium+0.101
 replay+0.101
Neg logit contributions
 unden-0.145
 rall-0.142
 arrang-0.133
 reluct-0.133
 '.-0.129
Tokenism
Token ID1042
Feature activation-1.37e+00

Pos logit contributions
 unden+2.604
 rall+2.547
 arrang+2.400
 reluct+2.368
 '.+2.344
Neg logit contributions
ocket-1.806
adiator-1.732
Explore-1.710
 replay-1.685
rium-1.682
Token"
Token ID1
Feature activation+1.45e-01

Pos logit contributions
 unden+2.846
 rall+2.786
 arrang+2.628
 reluct+2.588
 '.+2.581
Neg logit contributions
ocket-1.796
adiator-1.707
Explore-1.682
 replay-1.660
rium-1.656
Token devoid
Token ID34065
Feature activation+6.33e-02

Pos logit contributions
ocket+0.200
adiator+0.192
Explore+0.191
 replay+0.189
rium+0.187
Neg logit contributions
 unden-0.291
 rall-0.285
 arrang-0.268
 reluct-0.265
fort-0.262
Token of
Token ID286
Feature activation+1.24e-01

Pos logit contributions
ocket+0.074
adiator+0.070
Explore+0.069
 replay+0.068
rium+0.068
Neg logit contributions
 unden-0.140
 rall-0.137
 arrang-0.130
 reluct-0.129
fort-0.128
Token social
Token ID1919
Feature activation-7.39e-01

Pos logit contributions
ocket+0.173
 replay+0.167
adiator+0.167
Explore+0.166
rium+0.163
Neg logit contributions
 unden-0.243
 rall-0.238
 arrang-0.223
 reluct-0.223
fort-0.220
Token content
Token ID2695
Feature activation-2.42e-01

Pos logit contributions
 unden+1.453
 rall+1.421
 arrang+1.336
 reluct+1.322
fort+1.306
Neg logit contributions
ocket-1.046
adiator-1.003
Explore-0.991
 replay-0.980
rium-0.975