TOP ACTIVATIONS
MAX = 1.000

statements he has made to date , he did not appear
( bending open and slamming shut at high -
Reading Below Advertisement <|endoftext|> UN ITED N ATIONS ( Reuters )
delight . TW O WOM EN . It
} -> " E ", { 1 , 15 } ->
Y au hen i Hut ar ovich ( Equ ipe Cycl
the flows . This is very important , as
boot . build ' -- Save the results to cl ojure
igh insol uble , given that the valves are
than anything . RELATED : ' King
why go that one small step further and eliminate
} -> " E ", { 2 , 15 } ->
all . ( UPDATE : Sherman suffered a rupt
area . Cor respond ents say the mine may
that its role was to destroy itself in the
with no sed ative or muscle relax ant effects for doses
Development of the F - 35 fighter jet will cost over
also somewhat erratic and highly dependent on feedback .
find it . READ MORE : Calgary police officer
butter : Bl end , adding more almond milk

MIN ACTIVATIONS
MIN = -1.238

2010 boys beware Reviewer : j wt 0001 -
bad idea . Reviewer : Mike M anners -
os _ cache (); } } One feature of
, I think Reviewer : B iz r Pix
Control " 40 / 6000 + 30 : 20 / 3000
iff Tra x Reviewer : V the Happy L
01 : 44 : 24 # 19 edit , n vm
er magnet ? Reviewer : hey _ ler oy
was about homosexuality Reviewer : k imp unk rock
are Here .... Reviewer : SAS K ATCH EW
_ os _ cache (); } } One feature
post - election conflicts of interest like the ones seen in
1 2 3 Next All <|endoftext|> Republican Sen .
the prime challenge Belfast Te legraph . co . uk Dis
lad en with exp let ives , expressing dismay that there
5 ); ++ count ; } RAW _ ASS ERT (
10 . 13 71 / journal . p one . 00
, Mikhail Al "] [ Result " 1 / 2 -
. Is teacher turnover high ? P
United States 228 65 Posts # 13 On September 20 2013

INTERVAL 0.441 - 1.000
CONTAINS 0.839%

is a quick and fast slot receiver who was also pursued
the J on their entire stretch , and one of the
, the first African - American woman elected to Congress .[
itions of any deal to save the Def erred Action for
explains . Setting aside the drama of tsun am

INTERVAL -0.119 - 0.441
CONTAINS 77.521%

| prev _ state : Option < Board >, // The
also let you see if something is biased or even just
V ad im And rey uk , owner of
on his own . We taught him how to ask for
who allowed just two receptions for 11 yards vs . Seattle

INTERVAL -0.678 - -0.119
CONTAINS 21.584%

jointly owns four numbered Ontario real estate holding companies with his
may or may not have been used before and change
us / blog / power - bi - desktop - se
Britain cannot start formal trade negotiations until it leaves the bloc
week should be a tougher task , as I expect Peterson

INTERVAL -1.238 - -0.678
CONTAINS 0.056%

. Height ))) ) } } Catch { Write - Warning
1 = New - Object System . Draw ing . Rect
M ATE 16 . 04 + at all , I
will see if he can serve as an upgrade , and
band aged children . They stare at Sullivan , some with
Token statements
Token ID6299
Feature activation+3.72e-01

Pos logit contributions
owler+0.973
ynes+0.924
perty+0.859
perse+0.804
gow+0.790
Neg logit contributions
CLASSIFIED-1.181
batch-1.145
KC-1.118
 Koen-1.111
 Organisation-1.063
Token he
Token ID339
Feature activation+4.02e-02

Pos logit contributions
owler+0.997
ynes+0.964
perty+0.910
gow+0.846
perse+0.846
Neg logit contributions
CLASSIFIED-1.003
batch-0.958
KC-0.909
 Koen-0.884
 Parties-0.870
Token has
Token ID468
Feature activation-4.26e-02

Pos logit contributions
owler+0.117
ynes+0.112
perty+0.106
perse+0.103
gow+0.102
Neg logit contributions
CLASSIFIED-0.103
 Koen-0.096
batch-0.094
KC-0.092
 Rim-0.089
Token made
Token ID925
Feature activation+6.81e-02

Pos logit contributions
CLASSIFIED+0.098
 Koen+0.090
batch+0.090
KC+0.087
 Parties+0.083
Neg logit contributions
owler-0.133
ynes-0.128
perty-0.124
perse-0.118
gow-0.117
Token to
Token ID284
Feature activation+1.67e-01

Pos logit contributions
owler+0.175
ynes+0.170
perty+0.160
gow+0.146
perse+0.145
Neg logit contributions
CLASSIFIED-0.192
batch-0.184
KC-0.179
 Koen-0.179
 Organisation-0.171
Token date
Token ID3128
Feature activation+1.00e+00

Pos logit contributions
owler+0.451
ynes+0.441
perty+0.413
perse+0.385
gow+0.378
Neg logit contributions
CLASSIFIED-0.443
batch-0.425
 Koen-0.412
KC-0.408
 Organisation-0.395
Token,
Token ID11
Feature activation-9.65e-03

Pos logit contributions
owler+2.514
ynes+2.491
perty+2.286
perse+2.085
gow+2.072
Neg logit contributions
CLASSIFIED-2.754
batch-2.662
KC-2.529
 Koen-2.472
 Organisation-2.446
Token he
Token ID339
Feature activation-1.53e-01

Pos logit contributions
CLASSIFIED+0.027
batch+0.025
KC+0.025
 Koen+0.024
 Organisation+0.024
Neg logit contributions
owler-0.026
ynes-0.025
perty-0.023
perse-0.021
gow-0.021
Token did
Token ID750
Feature activation+4.67e-02

Pos logit contributions
CLASSIFIED+0.396
batch+0.366
 Koen+0.365
KC+0.357
 Rim+0.340
Neg logit contributions
owler-0.442
ynes-0.430
perty-0.397
gow-0.381
perse-0.380
Token not
Token ID407
Feature activation+2.73e-02

Pos logit contributions
owler+0.116
ynes+0.112
perty+0.104
perse+0.099
gow+0.097
Neg logit contributions
CLASSIFIED-0.138
 Koen-0.129
batch-0.128
KC-0.125
 Organisation-0.121
Token appear
Token ID1656
Feature activation-9.69e-02

Pos logit contributions
owler+0.065
ynes+0.063
perty+0.057
perse+0.054
gow+0.054
Neg logit contributions
CLASSIFIED-0.085
 Koen-0.079
batch-0.078
KC-0.077
 Organisation-0.074
Token (
Token ID357
Feature activation-5.53e-02

Pos logit contributions
owler+0.034
ynes+0.033
perty+0.030
perse+0.029
gow+0.028
Neg logit contributions
CLASSIFIED-0.036
 Koen-0.035
batch-0.034
KC-0.033
 Rim-0.032
Tokenbending
Token ID49667
Feature activation-4.96e-01

Pos logit contributions
CLASSIFIED+0.143
 Koen+0.139
batch+0.131
KC+0.130
 Rim+0.129
Neg logit contributions
owler-0.155
ynes-0.151
perty-0.139
perse-0.133
gow-0.132
Token open
Token ID1280
Feature activation+7.39e-03

Pos logit contributions
CLASSIFIED+1.348
 Koen+1.272
batch+1.260
KC+1.234
 Rim+1.193
Neg logit contributions
ynes-1.340
owler-1.340
perty-1.207
perse-1.143
apesh-1.123
Token and
Token ID290
Feature activation-5.07e-02

Pos logit contributions
owler+0.019
ynes+0.019
perty+0.017
perse+0.016
gow+0.016
Neg logit contributions
CLASSIFIED-0.021
batch-0.020
 Koen-0.020
KC-0.019
 Organisation-0.019
Token slamming
Token ID39603
Feature activation-5.18e-01

Pos logit contributions
CLASSIFIED+0.143
batch+0.137
 Koen+0.137
KC+0.135
 Organisation+0.129
Neg logit contributions
owler-0.127
ynes-0.127
perty-0.115
perse-0.110
apesh-0.107
Token
Token ID198
Feature activation+9.93e-01

Pos logit contributions
CLASSIFIED+1.512
 Koen+1.458
batch+1.457
KC+1.426
 Organisation+1.381
Neg logit contributions
owler-1.261
ynes-1.247
perty-1.140
perse-1.063
gow-1.040
Token
Token ID198
Feature activation+7.40e-01

Pos logit contributions
owler+1.767
ynes+1.697
perse+1.444
gow+1.436
har+1.420
Neg logit contributions
CLASSIFIED-3.653
 Koen-3.279
 Ezek-3.228
batch-3.167
KC-3.157
Tokenshut
Token ID49625
Feature activation-5.65e-01

Pos logit contributions
ynes+1.957
owler+1.953
perty+1.774
perse+1.734
gow+1.682
Neg logit contributions
 Koen-1.923
CLASSIFIED-1.909
 Organisation-1.808
 Kenn-1.801
 Ezek-1.789
Token at
Token ID379
Feature activation+5.05e-02

Pos logit contributions
CLASSIFIED+1.502
 Koen+1.427
KC+1.403
batch+1.396
 Organisation+1.354
Neg logit contributions
owler-1.559
ynes-1.546
perty-1.406
perse-1.338
gow-1.304
Token high
Token ID1029
Feature activation-2.79e-01

Pos logit contributions
owler+0.131
ynes+0.129
perty+0.117
perse+0.108
apesh+0.107
Neg logit contributions
CLASSIFIED-0.142
batch-0.133
 Koen-0.133
KC-0.131
 Rim-0.126
Token-
Token ID12
Feature activation-9.90e-02

Pos logit contributions
CLASSIFIED+0.738
batch+0.691
 Koen+0.691
KC+0.674
 Kenn+0.646
Neg logit contributions
owler-0.776
ynes-0.765
perty-0.693
gow-0.653
perse-0.647
Token Reading
Token ID11725
Feature activation+1.67e-01

Pos logit contributions
owler+0.520
ynes+0.500
gow+0.449
perty+0.448
perse+0.440
Neg logit contributions
CLASSIFIED-0.467
batch-0.436
KC-0.434
 Koen-0.425
 flavours-0.405
Token Below
Token ID10383
Feature activation+1.59e-01

Pos logit contributions
owler+0.236
ynes+0.220
perty+0.179
perse+0.169
gow+0.167
Neg logit contributions
CLASSIFIED-0.658
batch-0.627
 Koen-0.623
KC-0.620
 flavours-0.603
Token Advertisement
Token ID39711
Feature activation+4.25e-01

Pos logit contributions
owler+0.453
ynes+0.432
perty+0.402
gow+0.391
perse+0.388
Neg logit contributions
CLASSIFIED-0.391
batch-0.374
 Koen-0.363
KC-0.357
 flavours-0.347
Token<|endoftext|>
Token ID50256
Feature activation+3.61e-02

Pos logit contributions
owler+0.999
ynes+0.975
perty+0.894
perse+0.836
gow+0.823
Neg logit contributions
CLASSIFIED-1.256
batch-1.208
 Koen-1.204
KC-1.178
 Kenn-1.123
TokenUN
Token ID4944
Feature activation+6.12e-02

Pos logit contributions
owler+0.095
ynes+0.092
perty+0.086
gow+0.082
perse+0.082
Neg logit contributions
 Koen-0.097
CLASSIFIED-0.095
batch-0.091
 Kenn-0.090
 Rim-0.090
TokenITED
Token ID22061
Feature activation+9.83e-01

Pos logit contributions
owler+0.174
ynes+0.170
perty+0.160
apesh+0.151
gow+0.147
Neg logit contributions
 Koen-0.145
batch-0.140
KC-0.135
CLASSIFIED-0.135
 Ezek-0.133
Token N
Token ID399
Feature activation-4.40e-02

Pos logit contributions
owler+2.141
ynes+2.038
perty+1.902
perse+1.827
gow+1.753
Neg logit contributions
batch-2.785
CLASSIFIED-2.737
 Koen-2.719
akin-2.646
KC-2.605
TokenATIONS
Token ID18421
Feature activation+2.92e-01

Pos logit contributions
batch+0.095
CLASSIFIED+0.093
 Koen+0.093
 Kenn+0.087
akin+0.085
Neg logit contributions
owler-0.135
ynes-0.133
perty-0.123
perse-0.120
apesh-0.118
Token (
Token ID357
Feature activation-2.17e-02

Pos logit contributions
owler+0.751
ynes+0.729
perty+0.694
gow+0.656
apesh+0.648
Neg logit contributions
CLASSIFIED-0.751
batch-0.737
 Koen-0.728
KC-0.718
akin-0.686
TokenReuters
Token ID12637
Feature activation-3.00e-01

Pos logit contributions
 Koen+0.050
CLASSIFIED+0.050
batch+0.048
 Rim+0.047
 Kenn+0.046
Neg logit contributions
owler-0.064
ynes-0.061
perty-0.058
perse-0.055
gow-0.055
Token)
Token ID8
Feature activation-1.08e-01

Pos logit contributions
CLASSIFIED+0.843
batch+0.797
 Koen+0.796
KC+0.769
 Rim+0.755
Neg logit contributions
owler-0.760
ynes-0.744
perty-0.688
gow-0.643
perse-0.635
Token delight
Token ID10974
Feature activation-3.73e-01

Pos logit contributions
owler+0.681
ynes+0.642
perty+0.592
gow+0.560
perse+0.552
Neg logit contributions
CLASSIFIED-0.772
batch-0.727
 Koen-0.716
KC-0.714
 Rim-0.685
Token.
Token ID13
Feature activation-1.34e-01

Pos logit contributions
CLASSIFIED+0.986
 Koen+0.951
batch+0.932
KC+0.927
 Rim+0.893
Neg logit contributions
owler-1.033
ynes-0.995
perty-0.935
perse-0.863
gow-0.863
Token
Token ID564
Feature activation-1.18e-02

Pos logit contributions
CLASSIFIED+0.378
batch+0.360
 Koen+0.353
KC+0.352
 flavours+0.335
Neg logit contributions
owler-0.344
ynes-0.327
perty-0.299
gow-0.291
perse-0.285
Token
Token ID250
Feature activation+5.60e-02

Pos logit contributions
CLASSIFIED+0.023
 Koen+0.022
batch+0.021
KC+0.021
 Rim+0.020
Neg logit contributions
owler-0.040
ynes-0.040
perty-0.037
perse-0.036
gow-0.035
TokenTW
Token ID34551
Feature activation+1.08e-01

Pos logit contributions
owler+0.149
ynes+0.144
perty+0.132
gow+0.128
perse+0.128
Neg logit contributions
CLASSIFIED-0.150
 Koen-0.146
batch-0.140
 Rim-0.138
KC-0.137
TokenO
Token ID46
Feature activation+9.63e-01

Pos logit contributions
owler+0.302
ynes+0.289
perty+0.266
apesh+0.248
perse+0.245
Neg logit contributions
CLASSIFIED-0.278
 Koen-0.276
batch-0.270
KC-0.260
 Rim-0.256
Token WOM
Token ID45386
Feature activation+2.15e-01

Pos logit contributions
owler+2.349
ynes+2.289
perty+2.043
apesh+1.932
perse+1.908
Neg logit contributions
CLASSIFIED-2.592
 Koen-2.582
batch-2.531
KC-2.451
 Rim-2.396
TokenEN
Token ID1677
Feature activation+2.63e-01

Pos logit contributions
ynes+0.533
owler+0.519
perty+0.465
perse+0.445
apesh+0.435
Neg logit contributions
CLASSIFIED-0.608
batch-0.587
 Koen-0.576
 Organisation-0.562
KC-0.556
Token.
Token ID13
Feature activation-6.87e-02

Pos logit contributions
owler+0.655
ynes+0.625
perty+0.581
perse+0.554
gow+0.549
Neg logit contributions
CLASSIFIED-0.738
 Koen-0.706
batch-0.702
KC-0.700
 Rim-0.661
Token It
Token ID632
Feature activation-5.53e-02

Pos logit contributions
CLASSIFIED+0.202
 Koen+0.195
batch+0.195
KC+0.192
 Rim+0.183
Neg logit contributions
owler-0.164
ynes-0.156
perty-0.140
gow-0.137
perse-0.136
Token
Token ID447
Feature activation-2.21e-01

Pos logit contributions
CLASSIFIED+0.156
 Koen+0.151
batch+0.149
KC+0.147
 Rim+0.142
Neg logit contributions
owler-0.143
ynes-0.136
perty-0.124
gow-0.118
perse-0.117
Token}
Token ID92
Feature activation-2.30e-01

Pos logit contributions
CLASSIFIED+0.341
 Koen+0.329
batch+0.325
KC+0.319
 Rim+0.308
Neg logit contributions
owler-0.425
ynes-0.412
perty-0.390
perse-0.367
gow-0.363
Token ->
Token ID4613
Feature activation-1.17e-01

Pos logit contributions
CLASSIFIED+0.637
 Koen+0.603
batch+0.597
KC+0.584
 Dion+0.556
Neg logit contributions
owler-0.603
ynes-0.589
perty-0.547
perse-0.517
gow-0.498
Token "
Token ID366
Feature activation+2.79e-02

Pos logit contributions
CLASSIFIED+0.315
 Koen+0.301
batch+0.294
KC+0.292
 Organisation+0.277
Neg logit contributions
owler-0.308
ynes-0.299
perty-0.276
perse-0.265
gow-0.258
TokenE
Token ID36
Feature activation+1.44e-01

Pos logit contributions
owler+0.077
ynes+0.076
perty+0.070
perse+0.067
gow+0.066
Neg logit contributions
CLASSIFIED-0.072
 Koen-0.070
batch-0.068
KC-0.066
 Rim-0.064
Token",
Token ID1600
Feature activation+9.37e-02

Pos logit contributions
ynes+0.382
owler+0.379
perty+0.353
gow+0.328
perse+0.323
Neg logit contributions
CLASSIFIED-0.396
 Koen-0.379
batch-0.369
KC-0.354
 Rim-0.354
Token {
Token ID1391
Feature activation+9.50e-01

Pos logit contributions
owler+0.249
ynes+0.242
perty+0.222
perse+0.210
gow+0.205
Neg logit contributions
CLASSIFIED-0.258
 Koen-0.241
batch-0.240
KC-0.235
 Organisation-0.225
Token1
Token ID16
Feature activation+1.66e-01

Pos logit contributions
owler+2.627
ynes+2.557
perty+2.410
perse+2.367
apesh+2.201
Neg logit contributions
CLASSIFIED-2.305
 Koen-2.272
batch-2.167
 Bened-2.093
 Kenn-2.092
Token,
Token ID11
Feature activation-2.19e-02

Pos logit contributions
owler+0.434
ynes+0.418
perty+0.384
perse+0.374
gow+0.357
Neg logit contributions
CLASSIFIED-0.461
 Koen-0.439
batch-0.437
KC-0.421
 Parties-0.412
Token 15
Token ID1315
Feature activation+5.90e-03

Pos logit contributions
CLASSIFIED+0.057
 Koen+0.054
batch+0.053
KC+0.051
 Rim+0.050
Neg logit contributions
owler-0.062
ynes-0.059
perty-0.055
perse-0.053
apesh-0.051
Token}
Token ID92
Feature activation-3.63e-01

Pos logit contributions
owler+0.015
ynes+0.014
perty+0.013
perse+0.012
apesh+0.012
Neg logit contributions
CLASSIFIED-0.017
 Koen-0.016
batch-0.016
KC-0.016
 Rim-0.015
Token ->
Token ID4613
Feature activation-1.72e-02

Pos logit contributions
CLASSIFIED+1.014
batch+0.959
 Koen+0.959
KC+0.938
 Kenn+0.890
Neg logit contributions
owler-0.947
ynes-0.923
perty-0.848
perse-0.805
gow-0.784
Token Y
Token ID575
Feature activation-3.72e-01

Pos logit contributions
CLASSIFIED+0.306
batch+0.282
KC+0.273
akin+0.256
 Koen+0.256
Neg logit contributions
owler-0.326
ynes-0.314
perty-0.289
gow-0.283
perse-0.281
Tokenau
Token ID559
Feature activation+6.77e-02

Pos logit contributions
CLASSIFIED+1.079
batch+0.989
 Koen+0.981
KC+0.948
 Parties+0.946
Neg logit contributions
owler-1.008
ynes-0.964
perty-0.859
perse-0.859
gow-0.821
Tokenhen
Token ID831
Feature activation+3.23e-01

Pos logit contributions
ynes+0.199
owler+0.199
har+0.179
perty+0.177
gow+0.172
Neg logit contributions
CLASSIFIED-0.175
 Koen-0.151
batch-0.149
KC-0.148
 Rim-0.144
Tokeni
Token ID72
Feature activation+1.93e-01

Pos logit contributions
owler+0.976
ynes+0.973
gow+0.863
perty+0.861
har+0.860
Neg logit contributions
CLASSIFIED-0.769
batch-0.709
KC-0.683
 Koen-0.631
 Pelicans-0.625
Token Hut
Token ID32767
Feature activation+1.63e-01

Pos logit contributions
owler+0.560
ynes+0.552
perty+0.482
perse+0.475
gow+0.470
Neg logit contributions
CLASSIFIED-0.508
batch-0.447
KC-0.436
 Koen-0.429
20439-0.419
Tokenar
Token ID283
Feature activation+9.46e-01

Pos logit contributions
owler+0.440
ynes+0.440
perty+0.400
perse+0.397
gew+0.384
Neg logit contributions
CLASSIFIED-0.468
 Koen-0.409
KC-0.399
batch-0.392
 Kenn-0.369
Tokenovich
Token ID18198
Feature activation-3.07e-02

Pos logit contributions
ynes+2.973
owler+2.955
apesh+2.674
perty+2.652
ral+2.635
Neg logit contributions
CLASSIFIED-2.278
batch-1.902
20439-1.811
KC-1.808
 babe-1.748
Token (
Token ID357
Feature activation+2.64e-01

Pos logit contributions
CLASSIFIED+0.080
batch+0.074
KC+0.072
 Koen+0.071
 Parties+0.068
Neg logit contributions
owler-0.086
ynes-0.084
perty-0.077
gow-0.074
perse-0.074
TokenEqu
Token ID23588
Feature activation+3.30e-01

Pos logit contributions
owler+0.700
ynes+0.697
perty+0.630
gow+0.625
har+0.621
Neg logit contributions
CLASSIFIED-0.681
 Koen-0.634
batch-0.622
 Bened-0.608
 Dion-0.592
Tokenipe
Token ID3757
Feature activation+1.07e-01

Pos logit contributions
owler+0.920
ynes+0.905
perty+0.825
apesh+0.762
gow+0.759
Neg logit contributions
CLASSIFIED-0.931
 Koen-0.837
KC-0.819
batch-0.793
 Parties-0.786
Token Cycl
Token ID28007
Feature activation-2.69e-01

Pos logit contributions
ynes+0.274
owler+0.270
perty+0.238
apesh+0.234
perse+0.233
Neg logit contributions
CLASSIFIED-0.294
batch-0.276
 Koen-0.270
KC-0.269
akin-0.255
Token the
Token ID262
Feature activation-8.53e-02

Pos logit contributions
CLASSIFIED+0.175
KC+0.164
batch+0.161
 Koen+0.160
 Organisation+0.152
Neg logit contributions
ynes-0.154
owler-0.154
perty-0.138
perse-0.131
gow-0.129
Token flows
Token ID15623
Feature activation-1.35e-02

Pos logit contributions
CLASSIFIED+0.249
KC+0.228
 Koen+0.226
batch+0.223
 Kenn+0.213
Neg logit contributions
ynes-0.220
owler-0.217
perty-0.191
gow-0.180
perse-0.177
Token.
Token ID13
Feature activation-5.43e-02

Pos logit contributions
CLASSIFIED+0.038
 Koen+0.034
batch+0.034
KC+0.034
 Rim+0.033
Neg logit contributions
ynes-0.037
owler-0.036
perty-0.033
perse-0.031
gow-0.031
Token This
Token ID770
Feature activation-4.62e-02

Pos logit contributions
CLASSIFIED+0.153
batch+0.141
KC+0.139
 Koen+0.137
akin+0.132
Neg logit contributions
owler-0.138
ynes-0.136
perty-0.120
gow-0.119
perse-0.118
Token is
Token ID318
Feature activation-2.25e-02

Pos logit contributions
CLASSIFIED+0.132
batch+0.121
 Koen+0.120
KC+0.118
 Rim+0.112
Neg logit contributions
owler-0.120
ynes-0.119
perty-0.106
gow-0.100
perse-0.099
Token
Token ID198
Feature activation+9.24e-01

Pos logit contributions
CLASSIFIED+0.066
batch+0.062
 Koen+0.060
KC+0.060
 Organisation+0.057
Neg logit contributions
owler-0.056
ynes-0.055
perty-0.050
perse-0.047
gow-0.046
Token
Token ID198
Feature activation+6.81e-01

Pos logit contributions
owler+1.677
ynes+1.603
perse+1.375
gow+1.365
har+1.340
Neg logit contributions
CLASSIFIED-3.354
 Koen-3.025
 Ezek-2.958
batch-2.928
KC-2.914
Tokenvery
Token ID548
Feature activation-2.90e-01

Pos logit contributions
owler+1.770
ynes+1.749
perty+1.580
perse+1.569
har+1.563
Neg logit contributions
 Koen-1.779
CLASSIFIED-1.763
 Ezek-1.678
 Rim-1.641
 Organisation-1.636
Token important
Token ID1593
Feature activation-5.22e-02

Pos logit contributions
CLASSIFIED+0.853
batch+0.800
 Koen+0.795
KC+0.792
 Rim+0.757
Neg logit contributions
owler-0.718
ynes-0.713
perty-0.637
perse-0.613
apesh-0.582
Token,
Token ID11
Feature activation+8.99e-02

Pos logit contributions
CLASSIFIED+0.143
batch+0.134
 Koen+0.134
KC+0.131
 Kenn+0.125
Neg logit contributions
owler-0.138
ynes-0.135
perty-0.124
perse-0.118
gow-0.117
Token as
Token ID355
Feature activation-1.73e-01

Pos logit contributions
owler+0.250
ynes+0.244
perty+0.224
perse+0.209
gow+0.206
Neg logit contributions
CLASSIFIED-0.238
batch-0.224
KC-0.218
 Koen-0.216
 Organisation-0.203
Tokenboot
Token ID18769
Feature activation+7.77e-02

Pos logit contributions
owler+0.656
ynes+0.632
perty+0.577
perse+0.560
gow+0.554
Neg logit contributions
CLASSIFIED-0.675
 Koen-0.668
KC-0.628
batch-0.627
 Rim-0.622
Token.
Token ID13
Feature activation+1.22e-01

Pos logit contributions
owler+0.230
ynes+0.221
perty+0.206
gow+0.199
perse+0.196
Neg logit contributions
CLASSIFIED-0.189
 Koen-0.183
batch-0.172
KC-0.170
 Apost-0.167
Tokenbuild
Token ID11249
Feature activation+9.45e-02

Pos logit contributions
owler+0.385
ynes+0.375
perty+0.350
gow+0.337
perse+0.336
Neg logit contributions
CLASSIFIED-0.270
 Koen-0.262
batch-0.244
KC-0.243
 Kenn-0.238
Token'
Token ID6
Feature activation+6.59e-02

Pos logit contributions
owler+0.274
ynes+0.265
perty+0.250
perse+0.236
gow+0.234
Neg logit contributions
CLASSIFIED-0.233
 Koen-0.225
batch-0.217
KC-0.214
 Rim-0.208
Token --
Token ID1377
Feature activation+1.63e-01

Pos logit contributions
owler+0.161
ynes+0.154
perty+0.139
perse+0.134
gow+0.131
Neg logit contributions
CLASSIFIED-0.193
 Koen-0.183
batch-0.179
KC-0.178
akin-0.172
Token Save
Token ID12793
Feature activation+9.15e-01

Pos logit contributions
owler+0.436
ynes+0.414
perty+0.379
gow+0.372
perse+0.370
Neg logit contributions
CLASSIFIED-0.439
 Koen-0.413
KC-0.411
batch-0.399
 Dion-0.388
Token the
Token ID262
Feature activation+3.71e-01

Pos logit contributions
owler+2.215
ynes+2.119
perty+1.868
gow+1.791
perse+1.760
Neg logit contributions
CLASSIFIED-2.619
 Koen-2.510
KC-2.441
 Dion-2.370
batch-2.367
Token results
Token ID2482
Feature activation+2.93e-01

Pos logit contributions
owler+0.959
ynes+0.921
perty+0.814
gow+0.794
apesh+0.763
Neg logit contributions
CLASSIFIED-1.048
 Koen-0.972
KC-0.961
batch-0.932
 Rim-0.914
Token to
Token ID284
Feature activation+1.44e-01

Pos logit contributions
owler+0.886
ynes+0.867
perty+0.817
perse+0.771
gow+0.764
Neg logit contributions
CLASSIFIED-0.690
 Koen-0.658
batch-0.642
KC-0.639
 Rim-0.615
Token cl
Token ID537
Feature activation+2.95e-01

Pos logit contributions
owler+0.403
ynes+0.391
perty+0.360
perse+0.343
gow+0.341
Neg logit contributions
CLASSIFIED-0.374
 Koen-0.358
KC-0.349
batch-0.347
 Dion-0.331
Tokenojure
Token ID32511
Feature activation+3.57e-01

Pos logit contributions
owler+0.640
ynes+0.616
perty+0.543
gow+0.516
perse+0.501
Neg logit contributions
CLASSIFIED-1.030
 Koen-0.947
KC-0.912
batch-0.900
 Organisation-0.895
Tokenigh
Token ID394
Feature activation+5.23e-01

Pos logit contributions
owler+0.001
ynes+0.001
perty+0.001
perse+0.001
gow+0.001
Neg logit contributions
CLASSIFIED-0.002
 Koen-0.002
KC-0.002
batch-0.002
 Rim-0.002
Token insol
Token ID35831
Feature activation-1.43e-01

Pos logit contributions
owler+1.328
ynes+1.275
perty+1.207
apesh+1.108
perse+1.097
Neg logit contributions
CLASSIFIED-1.430
 Koen-1.352
KC-1.352
batch-1.333
 Organisation-1.296
Tokenuble
Token ID26664
Feature activation-8.16e-02

Pos logit contributions
CLASSIFIED+0.531
 Koen+0.501
KC+0.493
 Rim+0.480
batch+0.480
Neg logit contributions
owler-0.257
ynes-0.255
perty-0.233
perse-0.208
gow-0.198
Token,
Token ID11
Feature activation+6.32e-02

Pos logit contributions
CLASSIFIED+0.229
 Koen+0.214
batch+0.212
KC+0.212
 Organisation+0.200
Neg logit contributions
owler-0.212
ynes-0.208
perty-0.193
perse-0.181
apesh-0.177
Token given
Token ID1813
Feature activation+4.40e-03

Pos logit contributions
owler+0.165
ynes+0.162
perty+0.149
perse+0.137
apesh+0.135
Neg logit contributions
CLASSIFIED-0.176
batch-0.166
KC-0.163
 Koen-0.162
 Rim-0.154
Token
Token ID198
Feature activation+8.98e-01

Pos logit contributions
owler+0.012
ynes+0.011
perty+0.010
perse+0.010
gow+0.010
Neg logit contributions
CLASSIFIED-0.012
batch-0.011
 Koen-0.011
KC-0.011
 Rim-0.011
Token
Token ID198
Feature activation+6.77e-01

Pos logit contributions
owler+1.624
ynes+1.558
perse+1.329
gow+1.318
har+1.297
Neg logit contributions
CLASSIFIED-3.283
 Koen-2.950
 Ezek-2.890
batch-2.854
KC-2.841
Tokenthat
Token ID5562
Feature activation-8.04e-02

Pos logit contributions
owler+1.649
ynes+1.612
perty+1.500
perse+1.413
har+1.374
Neg logit contributions
CLASSIFIED-1.908
 Koen-1.893
 Rim-1.803
 Kenn-1.787
 Apost-1.783
Token the
Token ID262
Feature activation-9.52e-02

Pos logit contributions
CLASSIFIED+0.229
KC+0.212
batch+0.211
 Koen+0.210
 Kenn+0.200
Neg logit contributions
owler-0.208
ynes-0.203
perty-0.186
perse-0.173
gow-0.171
Token valves
Token ID41843
Feature activation-7.11e-02

Pos logit contributions
CLASSIFIED+0.267
KC+0.246
batch+0.244
 Koen+0.242
 Kenn+0.230
Neg logit contributions
owler-0.253
ynes-0.251
perty-0.223
gow-0.211
perse-0.205
Token are
Token ID389
Feature activation+1.21e-01

Pos logit contributions
CLASSIFIED+0.216
 Koen+0.200
KC+0.199
batch+0.198
 Rim+0.189
Neg logit contributions
owler-0.171
ynes-0.170
perty-0.155
perse-0.144
gow-0.143
Token than
Token ID621
Feature activation+1.05e-02

Pos logit contributions
CLASSIFIED+0.440
batch+0.400
KC+0.396
 Koen+0.396
 Parties+0.380
Neg logit contributions
owler-0.416
ynes-0.399
perty-0.371
gow-0.352
perse-0.349
Token anything
Token ID1997
Feature activation+2.42e-02

Pos logit contributions
owler+0.027
ynes+0.025
perty+0.023
perse+0.022
gow+0.021
Neg logit contributions
CLASSIFIED-0.030
batch-0.028
 Koen-0.028
KC-0.028
 Rim-0.027
Token.
Token ID13
Feature activation-1.85e-01

Pos logit contributions
owler+0.059
ynes+0.057
perty+0.053
gow+0.048
apesh+0.048
Neg logit contributions
CLASSIFIED-0.071
batch-0.068
 Koen-0.066
KC-0.065
 Organisation-0.064
Token
Token ID198
Feature activation-2.35e-01

Pos logit contributions
CLASSIFIED+0.541
batch+0.511
 Koen+0.493
KC+0.492
 flavours+0.480
Neg logit contributions
owler-0.447
ynes-0.429
perty-0.398
gow-0.382
perse-0.373
Token
Token ID198
Feature activation-1.93e-01

Pos logit contributions
CLASSIFIED+0.752
 Koen+0.703
batch+0.690
KC+0.677
 Rim+0.662
Neg logit contributions
owler-0.527
ynes-0.505
perty-0.444
perse-0.435
gow-0.433
TokenRELATED
Token ID20112
Feature activation+8.96e-01

Pos logit contributions
CLASSIFIED+0.539
 Koen+0.532
batch+0.513
 Kenn+0.505
 Rim+0.503
Neg logit contributions
owler-0.476
ynes-0.461
perty-0.431
gow-0.408
perse-0.399
Token:
Token ID25
Feature activation+3.55e-01

Pos logit contributions
owler+1.995
ynes+1.882
perty+1.781
gow+1.672
 Scrib+1.650
Neg logit contributions
CLASSIFIED-2.679
batch-2.535
 Koen-2.418
 flavours-2.374
KC-2.372
Token
Token ID198
Feature activation-9.49e-02

Pos logit contributions
owler+0.838
ynes+0.783
perty+0.738
 Scrib+0.705
gow+0.701
Neg logit contributions
CLASSIFIED-1.048
batch-0.979
 Koen-0.933
KC-0.929
 flavours-0.923
Token
Token ID198
Feature activation-9.13e-02

Pos logit contributions
CLASSIFIED+0.312
 Koen+0.290
batch+0.283
KC+0.278
 Ezek+0.273
Neg logit contributions
owler-0.206
ynes-0.197
perty-0.171
perse-0.170
gow-0.170
Token'
Token ID6
Feature activation-1.55e-01

Pos logit contributions
CLASSIFIED+0.259
 Koen+0.255
batch+0.247
 Kenn+0.241
 Rim+0.241
Neg logit contributions
owler-0.222
ynes-0.214
perty-0.200
gow-0.190
perse-0.184
TokenKing
Token ID15708
Feature activation+7.21e-02

Pos logit contributions
CLASSIFIED+0.461
 Koen+0.452
batch+0.444
 Rim+0.429
 Kenn+0.426
Neg logit contributions
owler-0.348
ynes-0.335
perty-0.313
gow-0.298
perse-0.290
Token why
Token ID1521
Feature activation+1.55e-01

Pos logit contributions
CLASSIFIED+0.250
batch+0.225
KC+0.221
 Koen+0.219
 Rim+0.207
Neg logit contributions
owler-0.310
ynes-0.310
perty-0.289
perse-0.272
apesh-0.270
Token go
Token ID467
Feature activation-3.68e-02

Pos logit contributions
owler+0.415
ynes+0.411
perty+0.375
perse+0.363
gow+0.358
Neg logit contributions
CLASSIFIED-0.421
 Koen-0.392
batch-0.390
KC-0.388
 Rim-0.368
Token that
Token ID326
Feature activation+2.33e-02

Pos logit contributions
CLASSIFIED+0.102
 Koen+0.095
batch+0.095
KC+0.093
 Rim+0.089
Neg logit contributions
owler-0.097
ynes-0.097
perty-0.091
gow-0.084
perse-0.083
Token one
Token ID530
Feature activation+8.72e-02

Pos logit contributions
owler+0.062
ynes+0.061
perty+0.058
gow+0.054
apesh+0.053
Neg logit contributions
CLASSIFIED-0.064
 Koen-0.058
KC-0.057
batch-0.057
 Rim-0.054
Token small
Token ID1402
Feature activation+1.80e-01

Pos logit contributions
owler+0.230
ynes+0.226
perty+0.210
gow+0.197
perse+0.190
Neg logit contributions
CLASSIFIED-0.240
 Koen-0.224
batch-0.219
KC-0.214
 Ezek-0.212
Token
Token ID198
Feature activation+8.95e-01

Pos logit contributions
owler+0.463
ynes+0.453
perty+0.424
gow+0.393
apesh+0.383
Neg logit contributions
CLASSIFIED-0.520
 Koen-0.473
KC-0.465
batch-0.458
 Parties-0.454
Token
Token ID198
Feature activation+6.88e-01

Pos logit contributions
owler+1.619
ynes+1.539
gow+1.322
perse+1.315
har+1.293
Neg logit contributions
CLASSIFIED-3.287
 Koen-2.964
 Ezek-2.901
KC-2.839
batch-2.839
Tokenstep
Token ID9662
Feature activation-2.57e-01

Pos logit contributions
owler+1.957
ynes+1.911
perty+1.805
har+1.725
gow+1.724
Neg logit contributions
CLASSIFIED-1.739
 Koen-1.678
 Ezek-1.580
 Kenn-1.557
 Parties-1.539
Token further
Token ID2252
Feature activation+1.66e-01

Pos logit contributions
CLASSIFIED+0.757
 Koen+0.700
batch+0.695
KC+0.691
 Rim+0.670
Neg logit contributions
owler-0.646
ynes-0.631
perty-0.589
gow-0.540
perse-0.539
Token and
Token ID290
Feature activation-2.52e-02

Pos logit contributions
owler+0.394
ynes+0.386
perty+0.359
perse+0.334
apesh+0.331
Neg logit contributions
CLASSIFIED-0.501
KC-0.461
 Koen-0.461
batch-0.459
 Organisation-0.441
Token eliminate
Token ID11005
Feature activation-1.59e-01

Pos logit contributions
CLASSIFIED+0.076
 Koen+0.069
batch+0.068
KC+0.068
 Rim+0.065
Neg logit contributions
owler-0.062
ynes-0.061
perty-0.057
perse-0.053
gow-0.053
Token}
Token ID92
Feature activation-3.63e-01

Pos logit contributions
owler+0.015
ynes+0.014
perty+0.013
perse+0.012
apesh+0.012
Neg logit contributions
CLASSIFIED-0.017
 Koen-0.016
batch-0.016
KC-0.016
 Rim-0.015
Token ->
Token ID4613
Feature activation-1.72e-02

Pos logit contributions
CLASSIFIED+1.014
batch+0.959
 Koen+0.959
KC+0.938
 Kenn+0.890
Neg logit contributions
owler-0.947
ynes-0.923
perty-0.848
perse-0.805
gow-0.784
Token "
Token ID366
Feature activation+8.98e-02

Pos logit contributions
CLASSIFIED+0.048
 Koen+0.046
batch+0.045
KC+0.045
 Organisation+0.043
Neg logit contributions
owler-0.044
ynes-0.043
perty-0.040
perse-0.038
gow-0.036
TokenE
Token ID36
Feature activation+1.21e-01

Pos logit contributions
owler+0.244
ynes+0.239
perty+0.218
gow+0.209
perse+0.206
Neg logit contributions
CLASSIFIED-0.233
 Koen-0.230
batch-0.219
 Rim-0.212
 Dion-0.211
Token",
Token ID1600
Feature activation+1.54e-01

Pos logit contributions
owler+0.416
ynes+0.415
perty+0.390
gow+0.368
perse+0.368
Neg logit contributions
CLASSIFIED-0.234
 Koen-0.222
batch-0.213
KC-0.202
 Kenn-0.198
Token {
Token ID1391
Feature activation+8.82e-01

Pos logit contributions
owler+0.397
ynes+0.388
perty+0.356
perse+0.338
apesh+0.326
Neg logit contributions
CLASSIFIED-0.427
batch-0.404
 Koen-0.403
KC-0.398
 Rim-0.378
Token2
Token ID17
Feature activation+1.43e-01

Pos logit contributions
owler+2.495
ynes+2.444
perty+2.242
perse+2.215
apesh+2.135
Neg logit contributions
CLASSIFIED-2.097
 Koen-2.058
batch-1.924
 Kenn-1.896
 Rim-1.895
Token,
Token ID11
Feature activation+6.75e-02

Pos logit contributions
owler+0.368
ynes+0.357
perse+0.315
gow+0.312
perty+0.309
Neg logit contributions
CLASSIFIED-0.401
 Koen-0.375
batch-0.365
KC-0.359
 Rim-0.354
Token 15
Token ID1315
Feature activation+6.59e-02

Pos logit contributions
owler+0.191
ynes+0.185
perty+0.171
perse+0.164
apesh+0.162
Neg logit contributions
CLASSIFIED-0.170
batch-0.156
 Koen-0.155
KC-0.153
 Rim-0.146
Token}
Token ID92
Feature activation-2.51e-01

Pos logit contributions
owler+0.147
ynes+0.139
perty+0.123
perse+0.118
gow+0.116
Neg logit contributions
CLASSIFIED-0.214
 Koen-0.202
batch-0.198
KC-0.196
 Rim-0.192
Token ->
Token ID4613
Feature activation-2.73e-02

Pos logit contributions
CLASSIFIED+0.712
 Koen+0.679
batch+0.676
KC+0.663
 Rim+0.638
Neg logit contributions
owler-0.636
ynes-0.617
perty-0.569
perse-0.536
gow-0.524
Token all
Token ID477
Feature activation-6.28e-02

Pos logit contributions
owler+0.024
ynes+0.023
perty+0.022
perse+0.019
apesh+0.019
Neg logit contributions
CLASSIFIED-0.034
batch-0.032
 Koen-0.031
KC-0.031
 Organisation-0.030
Token.
Token ID13
Feature activation-5.30e-02

Pos logit contributions
CLASSIFIED+0.178
batch+0.170
 Koen+0.167
KC+0.163
 Organisation+0.160
Neg logit contributions
owler-0.161
ynes-0.156
perty-0.148
perse-0.137
apesh-0.134
Token
Token ID198
Feature activation-6.68e-02

Pos logit contributions
CLASSIFIED+0.159
batch+0.151
 Koen+0.144
KC+0.143
 flavours+0.143
Neg logit contributions
owler-0.126
ynes-0.120
perty-0.111
perse-0.106
 Scrib-0.104
Token
Token ID198
Feature activation-8.61e-02

Pos logit contributions
CLASSIFIED+0.222
 Koen+0.205
batch+0.200
KC+0.198
 Ezek+0.194
Neg logit contributions
owler-0.144
ynes-0.139
perty-0.119
perse-0.119
gow-0.119
Token(
Token ID7
Feature activation-1.41e-02

Pos logit contributions
 Koen+0.234
CLASSIFIED+0.226
batch+0.217
 Kenn+0.215
 Bened+0.215
Neg logit contributions
owler-0.224
ynes-0.216
perty-0.204
perse-0.195
gow-0.191
Token UPDATE
Token ID35717
Feature activation+8.81e-01

Pos logit contributions
CLASSIFIED+0.037
 Koen+0.036
batch+0.035
 Rim+0.033
 Organisation+0.033
Neg logit contributions
owler-0.039
ynes-0.037
perty-0.035
perse-0.033
gow-0.033
Token:
Token ID25
Feature activation+4.35e-01

Pos logit contributions
owler+2.065
ynes+2.028
perty+1.801
 Scrib+1.777
perse+1.738
Neg logit contributions
CLASSIFIED-2.490
batch-2.405
 Koen-2.346
akin-2.268
 Organisation-2.259
Token Sherman
Token ID23198
Feature activation+5.63e-02

Pos logit contributions
owler+1.180
ynes+1.115
perty+1.046
 Scrib+1.008
perse+0.996
Neg logit contributions
CLASSIFIED-1.140
batch-1.076
 Koen-1.022
KC-1.006
 flavours-0.989
Token suffered
Token ID6989
Feature activation+7.23e-02

Pos logit contributions
owler+0.152
ynes+0.149
perty+0.139
gow+0.130
perse+0.130
Neg logit contributions
CLASSIFIED-0.153
batch-0.138
 Koen-0.137
KC-0.136
 Rim-0.131
Token a
Token ID257
Feature activation-1.03e-01

Pos logit contributions
owler+0.175
ynes+0.165
perty+0.157
perse+0.147
gow+0.142
Neg logit contributions
CLASSIFIED-0.218
batch-0.204
 Koen-0.203
KC-0.196
 Parties-0.191
Token rupt
Token ID31580
Feature activation+3.96e-01

Pos logit contributions
CLASSIFIED+0.307
batch+0.286
 Koen+0.284
KC+0.274
 Parties+0.270
Neg logit contributions
owler-0.258
ynes-0.242
perty-0.229
perse-0.213
gow-0.203
Token area
Token ID1989
Feature activation+1.20e-01

Pos logit contributions
CLASSIFIED+0.330
batch+0.303
KC+0.297
 Koen+0.295
 Parties+0.284
Neg logit contributions
owler-0.274
ynes-0.266
perty-0.249
gow-0.236
perse-0.231
Token.
Token ID13
Feature activation+5.59e-02

Pos logit contributions
owler+0.311
ynes+0.300
perty+0.289
perse+0.263
gow+0.262
Neg logit contributions
CLASSIFIED-0.338
batch-0.311
 Koen-0.306
KC-0.303
 Rim-0.288
Token
Token ID198
Feature activation-6.39e-02

Pos logit contributions
owler+0.143
ynes+0.138
perty+0.129
perse+0.120
gow+0.119
Neg logit contributions
CLASSIFIED-0.157
 Koen-0.150
batch-0.149
KC-0.147
 Rim-0.142
Token
Token ID198
Feature activation-8.75e-02

Pos logit contributions
CLASSIFIED+0.208
 Koen+0.194
batch+0.189
KC+0.187
 Rim+0.182
Neg logit contributions
owler-0.139
ynes-0.135
perty-0.116
gow-0.115
perse-0.115
TokenCor
Token ID10606
Feature activation+1.07e-01

Pos logit contributions
 Koen+0.248
CLASSIFIED+0.244
 Kenn+0.232
batch+0.230
 Rim+0.229
Neg logit contributions
owler-0.215
ynes-0.209
perty-0.192
gow-0.188
perse-0.185
Tokenrespond
Token ID5546
Feature activation+8.80e-01

Pos logit contributions
owler+0.203
ynes+0.197
perty+0.182
perse+0.168
apesh+0.160
Neg logit contributions
CLASSIFIED-0.384
 Koen-0.362
KC-0.356
batch-0.348
 Rim-0.343
Tokenents
Token ID658
Feature activation+2.27e-01

Pos logit contributions
owler+2.358
ynes+2.242
perty+1.998
perse+1.987
gow+1.916
Neg logit contributions
CLASSIFIED-2.601
 Koen-2.260
 Organisation-2.160
KC-2.156
 Bened-2.155
Token say
Token ID910
Feature activation-1.41e-02

Pos logit contributions
owler+0.525
ynes+0.502
perty+0.467
perse+0.437
gow+0.437
Neg logit contributions
CLASSIFIED-0.712
batch-0.654
 Koen-0.646
KC-0.629
 Rim-0.605
Token the
Token ID262
Feature activation-1.45e-01

Pos logit contributions
CLASSIFIED+0.041
batch+0.038
KC+0.037
 Koen+0.037
 Organisation+0.035
Neg logit contributions
owler-0.035
ynes-0.034
perty-0.032
perse-0.030
gow-0.030
Token mine
Token ID6164
Feature activation-5.65e-02

Pos logit contributions
CLASSIFIED+0.413
batch+0.381
 Koen+0.376
KC+0.374
 Rim+0.353
Neg logit contributions
owler-0.375
ynes-0.361
perty-0.337
perse-0.317
gow-0.314
Token may
Token ID743
Feature activation-1.44e-01

Pos logit contributions
CLASSIFIED+0.153
 Koen+0.143
batch+0.140
KC+0.138
 Kenn+0.133
Neg logit contributions
owler-0.156
ynes-0.146
perty-0.138
gow-0.133
perse-0.132
Token that
Token ID326
Feature activation+7.95e-02

Pos logit contributions
owler+0.747
ynes+0.728
perty+0.672
perse+0.627
gow+0.622
Neg logit contributions
CLASSIFIED-0.872
KC-0.801
 Koen-0.800
batch-0.793
 Organisation-0.765
Token its
Token ID663
Feature activation-7.07e-02

Pos logit contributions
owler+0.201
ynes+0.197
perty+0.179
perse+0.167
gow+0.166
Neg logit contributions
CLASSIFIED-0.230
KC-0.212
batch-0.210
 Koen-0.208
 Parties-0.200
Token role
Token ID2597
Feature activation-2.75e-01

Pos logit contributions
CLASSIFIED+0.203
batch+0.184
KC+0.184
 Koen+0.183
 Kenn+0.175
Neg logit contributions
ynes-0.182
owler-0.181
perty-0.164
gow-0.152
perse-0.149
Token was
Token ID373
Feature activation-1.47e-01

Pos logit contributions
CLASSIFIED+0.716
 Koen+0.668
batch+0.654
KC+0.650
 Rim+0.624
Neg logit contributions
owler-0.786
ynes-0.771
perty-0.710
perse-0.668
gow-0.660
Token to
Token ID284
Feature activation+5.94e-02

Pos logit contributions
CLASSIFIED+0.404
batch+0.389
 Koen+0.387
KC+0.382
 Rim+0.365
Neg logit contributions
owler-0.377
ynes-0.372
perty-0.351
perse-0.318
gow-0.313
Token
Token ID198
Feature activation+8.80e-01

Pos logit contributions
owler+0.133
ynes+0.133
perty+0.118
perse+0.113
gow+0.110
Neg logit contributions
CLASSIFIED-0.190
 Koen-0.177
batch-0.175
KC-0.173
 Organisation-0.168
Token
Token ID198
Feature activation+6.77e-01

Pos logit contributions
owler+1.602
ynes+1.541
perse+1.319
gow+1.312
har+1.282
Neg logit contributions
CLASSIFIED-3.200
 Koen-2.887
 Ezek-2.818
batch-2.789
KC-2.773
Tokendestroy
Token ID41659
Feature activation-3.42e-01

Pos logit contributions
owler+1.788
ynes+1.741
perse+1.632
perty+1.604
har+1.558
Neg logit contributions
 Koen-1.815
CLASSIFIED-1.811
 Ezek-1.683
 Organisation-1.665
 Rim-1.663
Token itself
Token ID2346
Feature activation-1.94e-01

Pos logit contributions
CLASSIFIED+0.916
batch+0.881
 Koen+0.869
KC+0.861
 Rim+0.829
Neg logit contributions
owler-0.930
ynes-0.918
perty-0.833
perse-0.790
gow-0.764
Token in
Token ID287
Feature activation-1.19e-01

Pos logit contributions
CLASSIFIED+0.530
 Koen+0.496
KC+0.495
batch+0.490
 Organisation+0.466
Neg logit contributions
owler-0.526
ynes-0.524
perty-0.479
perse-0.452
gow-0.439
Token the
Token ID262
Feature activation-1.48e-01

Pos logit contributions
CLASSIFIED+0.334
batch+0.309
 Koen+0.309
KC+0.309
 Parties+0.290
Neg logit contributions
owler-0.313
ynes-0.306
perty-0.282
perse-0.265
gow-0.258
Token with
Token ID351
Feature activation+2.82e-01

Pos logit contributions
owler+0.378
ynes+0.351
perty+0.328
perse+0.302
apesh+0.302
Neg logit contributions
CLASSIFIED-0.412
batch-0.374
 Koen-0.365
KC-0.362
 Rim-0.348
Token no
Token ID645
Feature activation+2.24e-01

Pos logit contributions
owler+0.733
ynes+0.693
perty+0.645
perse+0.595
gow+0.583
Neg logit contributions
CLASSIFIED-0.819
 Koen-0.745
batch-0.745
KC-0.737
 Rim-0.712
Token sed
Token ID10081
Feature activation+3.67e-01

Pos logit contributions
owler+0.539
ynes+0.519
perty+0.472
perse+0.433
gow+0.431
Neg logit contributions
CLASSIFIED-0.679
batch-0.633
 Koen-0.630
KC-0.619
 Rim-0.604
Tokenative
Token ID876
Feature activation-3.01e-03

Pos logit contributions
owler+1.282
ynes+1.260
perty+1.167
gow+1.110
apesh+1.104
Neg logit contributions
CLASSIFIED-0.756
KC-0.657
batch-0.643
 Koen-0.641
 Rim-0.622
Token or
Token ID393
Feature activation+4.41e-02

Pos logit contributions
CLASSIFIED+0.010
batch+0.009
 Koen+0.009
KC+0.009
 Kenn+0.008
Neg logit contributions
owler-0.007
ynes-0.007
perty-0.006
perse-0.006
gow-0.005
Token muscle
Token ID8280
Feature activation+8.76e-01

Pos logit contributions
owler+0.103
ynes+0.097
perty+0.090
perse+0.082
gow+0.081
Neg logit contributions
CLASSIFIED-0.138
batch-0.130
 Koen-0.129
KC-0.127
 Parties-0.123
Token relax
Token ID8960
Feature activation+4.54e-01

Pos logit contributions
owler+1.812
ynes+1.753
perty+1.538
har+1.418
gow+1.396
Neg logit contributions
CLASSIFIED-2.882
 Koen-2.743
batch-2.674
KC-2.644
 Rim-2.602
Tokenant
Token ID415
Feature activation+5.71e-02

Pos logit contributions
owler+1.261
ynes+1.223
perty+1.101
perse+1.048
apesh+1.035
Neg logit contributions
CLASSIFIED-1.229
 Koen-1.141
batch-1.117
KC-1.089
 Rim-1.076
Token effects
Token ID3048
Feature activation+8.94e-02

Pos logit contributions
owler+0.128
ynes+0.122
perty+0.112
perse+0.101
gow+0.099
Neg logit contributions
CLASSIFIED-0.185
batch-0.172
 Koen-0.171
KC-0.168
 Kenn-0.164
Token for
Token ID329
Feature activation+7.39e-02

Pos logit contributions
owler+0.236
ynes+0.222
perty+0.211
perse+0.195
apesh+0.192
Neg logit contributions
CLASSIFIED-0.254
batch-0.234
 Koen-0.233
KC-0.227
 Rim-0.222
Token doses
Token ID16376
Feature activation+2.75e-01

Pos logit contributions
owler+0.204
ynes+0.194
perty+0.177
perse+0.170
gow+0.166
Neg logit contributions
CLASSIFIED-0.204
 Koen-0.185
batch-0.185
KC-0.182
 Rim-0.174
TokenDevelopment
Token ID41206
Feature activation-5.49e-02

Pos logit contributions
 Koen+0.861
CLASSIFIED+0.847
 Kenn+0.804
batch+0.800
 Rim+0.796
Neg logit contributions
owler-0.872
ynes-0.851
perty-0.801
gow-0.757
perse-0.755
Token of
Token ID286
Feature activation+1.33e-01

Pos logit contributions
CLASSIFIED+0.144
batch+0.137
 Koen+0.135
KC+0.133
 Rim+0.130
Neg logit contributions
ynes-0.147
owler-0.146
perty-0.135
gow-0.125
perse-0.125
Token the
Token ID262
Feature activation+1.93e-02

Pos logit contributions
owler+0.349
ynes+0.333
perty+0.314
gow+0.296
perse+0.295
Neg logit contributions
CLASSIFIED-0.364
batch-0.343
KC-0.340
 Koen-0.335
 Organisation-0.315
Token F
Token ID376
Feature activation-7.17e-02

Pos logit contributions
owler+0.052
ynes+0.050
perty+0.047
gow+0.044
perse+0.042
Neg logit contributions
CLASSIFIED-0.053
batch-0.049
KC-0.048
 Koen-0.048
akin-0.045
Token-
Token ID12
Feature activation+1.33e-02

Pos logit contributions
CLASSIFIED+0.190
 Koen+0.180
batch+0.178
 Organisation+0.170
 Rim+0.169
Neg logit contributions
owler-0.204
ynes-0.196
perty-0.180
perse-0.169
gow-0.166
Token35
Token ID2327
Feature activation+8.75e-01

Pos logit contributions
owler+0.043
ynes+0.042
perty+0.038
perse+0.037
har+0.036
Neg logit contributions
CLASSIFIED-0.029
 Koen-0.028
batch-0.026
KC-0.026
 Rim-0.026
Token fighter
Token ID10543
Feature activation+9.88e-02

Pos logit contributions
owler+2.300
ynes+2.203
perty+1.994
gow+1.842
apesh+1.841
Neg logit contributions
CLASSIFIED-2.320
batch-2.236
 Koen-2.220
KC-2.107
 Dion-2.065
Token jet
Token ID12644
Feature activation+3.89e-01

Pos logit contributions
owler+0.249
ynes+0.239
perty+0.216
perse+0.200
har+0.196
Neg logit contributions
CLASSIFIED-0.287
batch-0.269
 Koen-0.268
KC-0.261
 Ezek-0.255
Token will
Token ID481
Feature activation+6.34e-02

Pos logit contributions
owler+1.024
ynes+0.992
perty+0.894
apesh+0.834
gow+0.831
Neg logit contributions
CLASSIFIED-1.062
batch-0.996
 Koen-0.982
KC-0.954
 Bened-0.916
Token cost
Token ID1575
Feature activation+2.16e-01

Pos logit contributions
owler+0.134
ynes+0.131
perty+0.117
perse+0.110
gow+0.109
Neg logit contributions
CLASSIFIED-0.212
 Koen-0.198
batch-0.197
KC-0.194
 Rim-0.187
Token over
Token ID625
Feature activation+1.27e-01

Pos logit contributions
ynes+0.494
owler+0.489
perty+0.446
gow+0.408
perse+0.403
Neg logit contributions
CLASSIFIED-0.660
batch-0.624
 Koen-0.604
KC-0.591
OVA-0.574
Token also
Token ID635
Feature activation-2.42e-01

Pos logit contributions
owler+0.646
ynes+0.644
perty+0.582
perse+0.549
apesh+0.529
Neg logit contributions
CLASSIFIED-0.730
batch-0.675
 Koen-0.672
KC-0.669
 Rim-0.638
Token somewhat
Token ID6454
Feature activation-1.71e-01

Pos logit contributions
CLASSIFIED+0.688
 Koen+0.642
batch+0.640
KC+0.636
 Rim+0.609
Neg logit contributions
owler-0.615
ynes-0.609
perty-0.552
perse-0.526
gow-0.507
Token erratic
Token ID40583
Feature activation-2.86e-01

Pos logit contributions
CLASSIFIED+0.501
 Koen+0.470
batch+0.468
KC+0.463
 Rim+0.446
Neg logit contributions
ynes-0.418
owler-0.418
perty-0.373
perse-0.351
gow-0.341
Token and
Token ID290
Feature activation-3.85e-02

Pos logit contributions
CLASSIFIED+0.789
 Koen+0.742
batch+0.734
KC+0.728
 Organisation+0.697
Neg logit contributions
owler-0.758
ynes-0.745
perty-0.688
perse-0.639
gow-0.633
Token highly
Token ID4047
Feature activation-8.26e-02

Pos logit contributions
CLASSIFIED+0.113
 Koen+0.106
batch+0.106
KC+0.105
 Rim+0.101
Neg logit contributions
owler-0.094
ynes-0.093
perty-0.083
perse-0.079
apesh-0.076
Token
Token ID198
Feature activation+8.72e-01

Pos logit contributions
CLASSIFIED+0.245
batch+0.233
 Koen+0.232
KC+0.228
 Rim+0.222
Neg logit contributions
owler-0.200
ynes-0.196
perty-0.175
perse-0.165
gow-0.160
Token
Token ID198
Feature activation+6.39e-01

Pos logit contributions
owler+1.613
ynes+1.547
perse+1.319
gow+1.309
har+1.286
Neg logit contributions
CLASSIFIED-3.158
 Koen-2.850
 Ezek-2.782
batch-2.754
KC-2.753
Tokendependent
Token ID21186
Feature activation-3.11e-01

Pos logit contributions
owler+1.764
ynes+1.748
perty+1.569
perse+1.546
har+1.537
Neg logit contributions
 Koen-1.613
CLASSIFIED-1.587
 Ezek-1.515
 Rim-1.507
 Kenn-1.478
Token on
Token ID319
Feature activation-2.08e-01

Pos logit contributions
CLASSIFIED+0.768
 Koen+0.728
batch+0.716
KC+0.709
 Rim+0.683
Neg logit contributions
owler-0.905
ynes-0.892
perty-0.841
perse-0.791
gow-0.775
Token feedback
Token ID7538
Feature activation-7.50e-02

Pos logit contributions
CLASSIFIED+0.585
KC+0.545
batch+0.545
 Koen+0.544
 Rim+0.515
Neg logit contributions
owler-0.542
ynes-0.527
perty-0.484
perse-0.453
gow-0.443
Token.
Token ID13
Feature activation-4.07e-02

Pos logit contributions
CLASSIFIED+0.214
 Koen+0.202
batch+0.200
KC+0.195
 Kenn+0.190
Neg logit contributions
ynes-0.191
owler-0.188
perty-0.172
gow-0.160
perse-0.160
Token find
Token ID1064
Feature activation-1.98e-01

Pos logit contributions
owler+0.619
ynes+0.595
perty+0.552
perse+0.504
gow+0.489
Neg logit contributions
CLASSIFIED-0.974
batch-0.884
 Koen-0.882
KC-0.847
 Parties-0.839
Token it
Token ID340
Feature activation+1.11e-01

Pos logit contributions
CLASSIFIED+0.551
batch+0.544
 Koen+0.512
KC+0.509
 Parties+0.492
Neg logit contributions
owler-0.518
ynes-0.497
perty-0.456
perse-0.433
 Scrib-0.413
Token.
Token ID13
Feature activation+1.72e-01

Pos logit contributions
owler+0.275
ynes+0.260
perty+0.247
perse+0.228
apesh+0.220
Neg logit contributions
CLASSIFIED-0.320
batch-0.317
KC-0.302
 Koen-0.301
 Parties-0.288
Token
Token ID198
Feature activation+3.44e-01

Pos logit contributions
owler+0.402
ynes+0.382
perty+0.348
gow+0.330
perse+0.326
Neg logit contributions
CLASSIFIED-0.526
batch-0.500
 Koen-0.489
KC-0.475
akin-0.465
Token
Token ID198
Feature activation+2.30e-01

Pos logit contributions
owler+0.684
ynes+0.658
perse+0.571
gow+0.566
har+0.547
Neg logit contributions
CLASSIFIED-1.195
 Koen-1.097
batch-1.060
KC-1.051
 Ezek-1.048
TokenREAD
Token ID15675
Feature activation+8.72e-01

Pos logit contributions
owler+0.575
ynes+0.555
perty+0.507
gow+0.497
perse+0.485
Neg logit contributions
 Koen-0.659
CLASSIFIED-0.632
 Ezek-0.613
 Kenn-0.607
batch-0.605
Token MORE
Token ID12011
Feature activation+6.65e-01

Pos logit contributions
owler+1.524
ynes+1.503
perty+1.359
 Scrib+1.331
perse+1.330
Neg logit contributions
CLASSIFIED-2.801
 Koen-2.772
batch-2.765
 Rim-2.652
akin-2.649
Token:
Token ID25
Feature activation+7.37e-01

Pos logit contributions
owler+1.606
ynes+1.560
perty+1.450
gow+1.378
perse+1.353
Neg logit contributions
CLASSIFIED-1.869
batch-1.821
 Koen-1.799
 Organisation-1.707
KC-1.705
Token Calgary
Token ID17842
Feature activation-2.02e-01

Pos logit contributions
owler+2.071
ynes+1.925
perty+1.789
 Scrib+1.785
gow+1.761
Neg logit contributions
CLASSIFIED-1.857
batch-1.732
 Koen-1.670
akin-1.594
 flavours-1.562
Token police
Token ID1644
Feature activation+2.71e-01

Pos logit contributions
CLASSIFIED+0.575
batch+0.544
 Koen+0.532
KC+0.506
 Rim+0.497
Neg logit contributions
owler-0.522
ynes-0.504
perty-0.460
gow-0.434
perse-0.424
Token officer
Token ID3818
Feature activation+2.66e-01

Pos logit contributions
owler+0.675
ynes+0.639
perty+0.586
perse+0.567
apesh+0.553
Neg logit contributions
CLASSIFIED-0.783
batch-0.734
 Koen-0.716
KC-0.678
 Rim-0.674
Token butter
Token ID9215
Feature activation-2.10e-01

Pos logit contributions
CLASSIFIED+0.599
 Koen+0.556
batch+0.555
KC+0.542
 Kenn+0.518
Neg logit contributions
owler-0.621
ynes-0.607
perty-0.555
perse-0.527
gow-0.521
Token:
Token ID25
Feature activation+2.79e-02

Pos logit contributions
CLASSIFIED+0.571
 Koen+0.538
batch+0.531
KC+0.526
 Kenn+0.505
Neg logit contributions
owler-0.567
ynes-0.554
perty-0.514
perse-0.488
gow-0.474
Token
Token ID198
Feature activation-1.28e-01

Pos logit contributions
owler+0.071
ynes+0.069
perty+0.065
perse+0.060
gow+0.059
Neg logit contributions
CLASSIFIED-0.078
 Koen-0.076
batch-0.075
KC-0.074
 Rim-0.072
Token
Token ID198
Feature activation-1.01e-01

Pos logit contributions
CLASSIFIED+0.411
 Koen+0.385
batch+0.375
KC+0.372
 Rim+0.362
Neg logit contributions
owler-0.283
ynes-0.273
perty-0.238
perse-0.237
gow-0.234
TokenBl
Token ID3629
Feature activation+2.41e-01

Pos logit contributions
 Koen+0.277
CLASSIFIED+0.276
batch+0.256
 Kenn+0.256
 Rim+0.253
Neg logit contributions
owler-0.266
ynes-0.260
perty-0.236
perse-0.231
gow-0.228
Tokenend
Token ID437
Feature activation+8.66e-01

Pos logit contributions
owler+0.604
ynes+0.599
perty+0.526
perse+0.513
apesh+0.509
Neg logit contributions
CLASSIFIED-0.775
 Koen-0.706
KC-0.669
 Rim-0.665
 Ezek-0.661
Token,
Token ID11
Feature activation+1.31e-01

Pos logit contributions
ynes+2.117
owler+2.098
perty+1.822
perse+1.817
apesh+1.729
Neg logit contributions
CLASSIFIED-2.487
 Koen-2.343
KC-2.245
batch-2.243
 Organisation-2.200
Token adding
Token ID4375
Feature activation+2.33e-01

Pos logit contributions
owler+0.344
ynes+0.339
perty+0.304
perse+0.294
gow+0.280
Neg logit contributions
CLASSIFIED-0.366
 Koen-0.341
KC-0.336
batch-0.334
 Rim-0.322
Token more
Token ID517
Feature activation+2.58e-02

Pos logit contributions
owler+0.602
ynes+0.593
perty+0.533
perse+0.515
gow+0.495
Neg logit contributions
CLASSIFIED-0.655
 Koen-0.603
batch-0.593
KC-0.592
 Organisation-0.569
Token almond
Token ID26948
Feature activation-5.29e-01

Pos logit contributions
ynes+0.071
owler+0.071
perty+0.063
perse+0.062
gow+0.059
Neg logit contributions
CLASSIFIED-0.070
 Koen-0.063
batch-0.062
KC-0.062
 Rim-0.060
Token milk
Token ID7545
Feature activation-1.48e-02

Pos logit contributions
CLASSIFIED+1.337
 Koen+1.264
batch+1.245
KC+1.222
 Organisation+1.178
Neg logit contributions
owler-1.535
ynes-1.505
perty-1.385
perse-1.323
gow-1.299
Token 2010
Token ID3050
Feature activation-5.80e-02

Pos logit contributions
owler+0.112
ynes+0.108
perty+0.097
perse+0.096
gow+0.095
Neg logit contributions
CLASSIFIED-0.090
 Koen-0.084
batch-0.083
KC-0.081
 Rim-0.077
Tokenboys
Token ID13202
Feature activation+2.92e-02

Pos logit contributions
CLASSIFIED+0.155
 Koen+0.153
 Apost+0.141
batch+0.140
 Rim+0.140
Neg logit contributions
owler-0.160
ynes-0.159
perty-0.144
perse-0.142
gow-0.141
Token beware
Token ID40600
Feature activation+1.81e-01

Pos logit contributions
owler+0.090
ynes+0.089
perty+0.084
perse+0.080
gow+0.078
Neg logit contributions
CLASSIFIED-0.067
 Koen-0.064
batch-0.062
KC-0.061
 Rim-0.058
Token
Token ID198
Feature activation-3.44e-01

Pos logit contributions
owler+0.422
ynes+0.403
perty+0.374
perse+0.356
gow+0.349
Neg logit contributions
CLASSIFIED-0.546
batch-0.521
 Koen-0.519
KC-0.510
 Organisation-0.491
Token
Token ID198
Feature activation-3.01e-01

Pos logit contributions
CLASSIFIED+1.111
 Koen+1.034
batch+1.010
KC+0.999
 Rim+0.977
Neg logit contributions
owler-0.772
ynes-0.745
perty-0.651
perse-0.641
gow-0.640
TokenReviewer
Token ID35407
Feature activation-1.24e+00

Pos logit contributions
 Koen+0.822
CLASSIFIED+0.802
 Rim+0.762
 Dion+0.759
 Organisation+0.759
Neg logit contributions
owler-0.793
ynes-0.763
perty-0.719
gow-0.688
perse-0.685
Token:
Token ID25
Feature activation-1.15e-01

Pos logit contributions
CLASSIFIED+3.216
 Koen+3.084
batch+3.032
KC+2.978
 Rim+2.892
Neg logit contributions
owler-3.457
ynes-3.340
perty-3.126
perse-2.955
gow-2.928
Token j
Token ID474
Feature activation-6.55e-02

Pos logit contributions
CLASSIFIED+0.314
batch+0.298
 Koen+0.292
KC+0.288
 Organisation+0.277
Neg logit contributions
owler-0.311
ynes-0.297
perty-0.277
perse-0.262
gow-0.258
Tokenwt
Token ID46569
Feature activation+2.72e-01

Pos logit contributions
CLASSIFIED+0.175
 Koen+0.165
batch+0.156
 Organisation+0.155
KC+0.154
Neg logit contributions
owler-0.190
ynes-0.182
perty-0.169
perse-0.162
gow-0.160
Token0001
Token ID18005
Feature activation-1.97e-01

Pos logit contributions
owler+0.796
ynes+0.762
perty+0.702
gow+0.675
perse+0.672
Neg logit contributions
CLASSIFIED-0.705
 Koen-0.670
batch-0.635
 Rim-0.624
 Organisation-0.624
Token -
Token ID532
Feature activation-4.43e-01

Pos logit contributions
CLASSIFIED+0.500
 Koen+0.477
batch+0.471
KC+0.458
 Rim+0.449
Neg logit contributions
owler-0.565
ynes-0.545
perty-0.512
perse-0.482
gow-0.482
Token bad
Token ID2089
Feature activation-1.69e-02

Pos logit contributions
owler+0.215
ynes+0.198
perty+0.167
gow+0.160
perse+0.149
Neg logit contributions
CLASSIFIED-0.541
 Koen-0.516
batch-0.510
KC-0.509
 Kenn-0.490
Token idea
Token ID2126
Feature activation-2.58e-01

Pos logit contributions
CLASSIFIED+0.053
 Koen+0.048
batch+0.048
KC+0.047
 Bened+0.046
Neg logit contributions
owler-0.040
ynes-0.038
perty-0.035
perse-0.032
gow-0.032
Token.
Token ID13
Feature activation+1.91e-02

Pos logit contributions
CLASSIFIED+0.747
 Koen+0.693
batch+0.680
KC+0.668
 Rim+0.647
Neg logit contributions
owler-0.666
ynes-0.643
perty-0.568
perse-0.564
gow-0.558
Token
Token ID198
Feature activation-2.36e-01

Pos logit contributions
owler+0.053
ynes+0.051
perty+0.048
perse+0.045
gow+0.045
Neg logit contributions
CLASSIFIED-0.050
 Koen-0.048
batch-0.047
KC-0.047
 Rim-0.045
Token
Token ID198
Feature activation-2.50e-01

Pos logit contributions
CLASSIFIED+0.757
 Koen+0.705
batch+0.690
KC+0.682
 Rim+0.665
Neg logit contributions
owler-0.532
ynes-0.515
perty-0.449
perse-0.441
gow-0.440
TokenReviewer
Token ID35407
Feature activation-1.16e+00

Pos logit contributions
CLASSIFIED+0.688
 Koen+0.687
 Organisation+0.641
 Ezek+0.639
 Kenn+0.637
Neg logit contributions
owler-0.664
ynes-0.636
perty-0.586
gow-0.575
perse-0.565
Token:
Token ID25
Feature activation-1.01e-02

Pos logit contributions
CLASSIFIED+3.066
 Koen+2.930
batch+2.873
KC+2.826
 Rim+2.747
Neg logit contributions
owler-3.210
ynes-3.101
perty-2.891
perse-2.742
gow-2.715
Token Mike
Token ID4995
Feature activation-1.30e-01

Pos logit contributions
CLASSIFIED+0.027
batch+0.026
 Koen+0.025
KC+0.025
 Organisation+0.024
Neg logit contributions
owler-0.027
ynes-0.026
perty-0.024
perse-0.023
gow-0.023
TokenM
Token ID44
Feature activation-2.46e-02

Pos logit contributions
CLASSIFIED+0.326
batch+0.307
 Koen+0.307
KC+0.295
 Organisation+0.291
Neg logit contributions
owler-0.372
ynes-0.361
perty-0.340
gow-0.319
perse-0.318
Tokenanners
Token ID15672
Feature activation-2.18e-01

Pos logit contributions
CLASSIFIED+0.069
 Koen+0.068
batch+0.067
KC+0.064
 Rim+0.064
Neg logit contributions
owler-0.065
ynes-0.062
perty-0.057
perse-0.054
gow-0.053
Token -
Token ID532
Feature activation-5.46e-01

Pos logit contributions
CLASSIFIED+0.536
 Koen+0.517
batch+0.508
KC+0.493
 Rim+0.482
Neg logit contributions
owler-0.631
ynes-0.614
perty-0.579
perse-0.547
gow-0.542
Tokenos
Token ID418
Feature activation+1.45e-01

Pos logit contributions
owler+0.646
ynes+0.625
perty+0.560
perse+0.555
gow+0.552
Neg logit contributions
CLASSIFIED-0.632
 Koen-0.628
 Kenn-0.581
 Dion-0.580
KC-0.578
Token_
Token ID62
Feature activation+2.27e-01

Pos logit contributions
ynes+0.367
owler+0.363
perty+0.324
perse+0.323
gow+0.317
Neg logit contributions
CLASSIFIED-0.415
 Koen-0.403
KC-0.377
 Organisation-0.371
batch-0.368
Tokencache
Token ID23870
Feature activation+7.12e-02

Pos logit contributions
owler+0.633
ynes+0.611
perty+0.558
perse+0.545
gow+0.534
Neg logit contributions
CLASSIFIED-0.614
 Koen-0.584
KC-0.548
 Organisation-0.537
 Dion-0.537
Token();
Token ID9783
Feature activation+1.14e-01

Pos logit contributions
owler+0.188
ynes+0.186
perty+0.169
perse+0.164
apesh+0.156
Neg logit contributions
CLASSIFIED-0.193
 Koen-0.187
batch-0.179
KC-0.177
 Kenn-0.173
Token }
Token ID1782
Feature activation-9.95e-01

Pos logit contributions
owler+0.275
ynes+0.261
perty+0.233
perse+0.224
gow+0.223
Neg logit contributions
CLASSIFIED-0.340
 Koen-0.318
batch-0.313
KC-0.312
 Organisation-0.298
Token }
Token ID1782
Feature activation-1.12e+00

Pos logit contributions
CLASSIFIED+2.810
 Koen+2.696
batch+2.659
KC+2.620
 Rim+2.533
Neg logit contributions
owler-2.555
ynes-2.460
perty-2.285
perse-2.146
gow-2.114
Token
Token ID198
Feature activation-4.15e-01

Pos logit contributions
CLASSIFIED+3.165
 Koen+3.038
batch+2.997
KC+2.952
 Rim+2.857
Neg logit contributions
owler-2.882
ynes-2.772
perty-2.582
perse-2.419
gow-2.381
Token
Token ID198
Feature activation-2.75e-01

Pos logit contributions
CLASSIFIED+1.309
 Koen+1.270
batch+1.217
KC+1.197
 Ezek+1.191
Neg logit contributions
owler-0.932
ynes-0.885
perty-0.798
perse-0.771
gow-0.771
TokenOne
Token ID3198
Feature activation-7.55e-02

Pos logit contributions
 Koen+0.736
CLASSIFIED+0.722
 Kenn+0.687
 Dion+0.680
 Ezek+0.680
Neg logit contributions
owler-0.746
ynes-0.714
perty-0.670
gow-0.644
perse-0.631
Token feature
Token ID3895
Feature activation+6.90e-01

Pos logit contributions
CLASSIFIED+0.213
batch+0.199
 Koen+0.194
KC+0.189
 Rim+0.181
Neg logit contributions
owler-0.200
ynes-0.194
perty-0.184
perse-0.166
gow-0.166
Token of
Token ID286
Feature activation+2.42e-01

Pos logit contributions
owler+1.765
ynes+1.659
perty+1.598
gow+1.480
perse+1.435
Neg logit contributions
CLASSIFIED-1.983
batch-1.790
KC-1.756
 Koen-1.714
 Organisation-1.676
Token,
Token ID11
Feature activation+2.43e-02

Pos logit contributions
CLASSIFIED+0.275
 Koen+0.258
batch+0.253
KC+0.248
 Rim+0.240
Neg logit contributions
owler-0.243
ynes-0.236
perse-0.206
perty-0.206
gow-0.205
Token I
Token ID314
Feature activation-2.50e-02

Pos logit contributions
owler+0.062
ynes+0.060
perty+0.056
perse+0.052
gow+0.051
Neg logit contributions
CLASSIFIED-0.069
 Koen-0.066
batch-0.065
KC-0.064
 Rim-0.062
Token think
Token ID892
Feature activation-1.94e-01

Pos logit contributions
CLASSIFIED+0.078
 Koen+0.071
batch+0.071
KC+0.070
 Rim+0.069
Neg logit contributions
owler-0.061
ynes-0.058
perty-0.053
perse-0.050
gow-0.049
Token
Token ID198
Feature activation-1.48e-01

Pos logit contributions
CLASSIFIED+0.564
 Koen+0.539
batch+0.538
KC+0.529
 Rim+0.509
Neg logit contributions
owler-0.482
ynes-0.464
perty-0.430
perse-0.405
gow-0.397
Token
Token ID198
Feature activation-1.33e-01

Pos logit contributions
CLASSIFIED+0.482
 Koen+0.446
batch+0.437
KC+0.433
 Rim+0.421
Neg logit contributions
owler-0.328
ynes-0.317
perty-0.274
perse-0.272
gow-0.271
TokenReviewer
Token ID35407
Feature activation-1.09e+00

Pos logit contributions
CLASSIFIED+0.347
 Koen+0.345
batch+0.324
 Organisation+0.322
 Rim+0.320
Neg logit contributions
owler-0.363
ynes-0.351
perty-0.330
perse-0.315
gow-0.313
Token:
Token ID25
Feature activation+1.21e-01

Pos logit contributions
CLASSIFIED+2.879
 Koen+2.752
batch+2.700
KC+2.652
 Rim+2.581
Neg logit contributions
owler-3.007
ynes-2.903
perty-2.706
perse-2.568
gow-2.544
Token B
Token ID347
Feature activation-1.13e-01

Pos logit contributions
owler+0.327
ynes+0.312
perty+0.292
perse+0.275
gow+0.271
Neg logit contributions
CLASSIFIED-0.329
batch-0.313
 Koen-0.303
KC-0.301
 Organisation-0.289
Tokeniz
Token ID528
Feature activation-8.16e-03

Pos logit contributions
CLASSIFIED+0.301
 Koen+0.288
batch+0.285
 Rim+0.271
KC+0.268
Neg logit contributions
owler-0.313
ynes-0.306
perty-0.280
gow-0.262
perse-0.262
Tokenr
Token ID81
Feature activation+1.11e-01

Pos logit contributions
CLASSIFIED+0.020
 Koen+0.019
batch+0.018
KC+0.017
 Rim+0.017
Neg logit contributions
owler-0.025
ynes-0.024
perty-0.022
perse-0.021
gow-0.021
Token Pix
Token ID21642
Feature activation+5.74e-01

Pos logit contributions
owler+0.323
ynes+0.316
perty+0.296
perse+0.279
gow+0.278
Neg logit contributions
CLASSIFIED-0.279
 Koen-0.266
batch-0.260
 Rim-0.248
KC-0.245
TokenControl
Token ID15988
Feature activation-2.43e-01

Pos logit contributions
CLASSIFIED+1.049
batch+1.018
 Koen+1.015
KC+0.984
 Kenn+0.966
Neg logit contributions
owler-0.570
ynes-0.540
perty-0.499
perse-0.450
apesh-0.429
Token "
Token ID366
Feature activation-5.60e-01

Pos logit contributions
CLASSIFIED+0.727
batch+0.714
 Koen+0.691
KC+0.669
 Rim+0.655
Neg logit contributions
owler-0.582
ynes-0.546
perty-0.505
perse-0.488
apesh-0.455
Token40
Token ID1821
Feature activation-3.66e-01

Pos logit contributions
CLASSIFIED+1.370
 Koen+1.361
batch+1.288
KC+1.260
 Rim+1.259
Neg logit contributions
owler-1.614
ynes-1.594
perty-1.482
perse-1.393
gow-1.359
Token/
Token ID14
Feature activation-3.66e-01

Pos logit contributions
CLASSIFIED+0.984
 Koen+0.934
batch+0.933
KC+0.896
 Dion+0.875
Neg logit contributions
owler-0.991
ynes-0.963
perty-0.877
perse-0.838
gow-0.825
Token6000
Token ID43434
Feature activation-5.18e-01

Pos logit contributions
CLASSIFIED+0.869
 Koen+0.853
batch+0.790
KC+0.784
 Kenn+0.783
Neg logit contributions
owler-1.109
ynes-1.085
perty-0.991
perse-0.940
apesh-0.937
Token+
Token ID10
Feature activation-1.05e+00

Pos logit contributions
CLASSIFIED+1.225
batch+1.160
 Koen+1.142
KC+1.117
 Organisation+1.073
Neg logit contributions
owler-1.573
ynes-1.548
perty-1.418
perse-1.354
gow-1.339
Token30
Token ID1270
Feature activation-6.46e-02

Pos logit contributions
CLASSIFIED+2.376
 Koen+2.260
batch+2.190
KC+2.147
 Rim+2.074
Neg logit contributions
owler-3.342
ynes-3.253
perty-3.033
perse-2.883
gow-2.874
Token:
Token ID25
Feature activation-5.09e-01

Pos logit contributions
CLASSIFIED+0.152
batch+0.142
 Koen+0.141
KC+0.137
 Organisation+0.132
Neg logit contributions
owler-0.195
ynes-0.193
perty-0.176
perse-0.169
gow-0.167
Token20
Token ID1238
Feature activation-4.10e-01

Pos logit contributions
CLASSIFIED+1.189
 Koen+1.104
batch+1.084
KC+1.063
 Dion+1.017
Neg logit contributions
owler-1.568
ynes-1.517
perty-1.400
perse-1.350
gow-1.330
Token/
Token ID14
Feature activation-3.46e-01

Pos logit contributions
CLASSIFIED+1.014
batch+0.968
 Koen+0.957
KC+0.933
 Kenn+0.909
Neg logit contributions
owler-1.189
ynes-1.160
perty-1.080
perse-1.023
gow-0.996
Token3000
Token ID23924
Feature activation-4.31e-01

Pos logit contributions
CLASSIFIED+0.792
 Koen+0.764
batch+0.724
 Kenn+0.704
KC+0.704
Neg logit contributions
owler-1.072
ynes-1.066
perty-0.984
perse-0.915
gow-0.912
Tokeniff
Token ID733
Feature activation+1.19e-01

Pos logit contributions
owler+0.005
ynes+0.005
perty+0.004
perse+0.004
gow+0.004
Neg logit contributions
CLASSIFIED-0.006
 Koen-0.006
batch-0.006
KC-0.005
 Kenn-0.005
TokenTra
Token ID15721
Feature activation-8.94e-03

Pos logit contributions
owler+0.364
ynes+0.347
perty+0.325
gow+0.314
perse+0.311
Neg logit contributions
CLASSIFIED-0.274
 Koen-0.261
batch-0.254
KC-0.245
 Bened-0.242
Tokenx
Token ID87
Feature activation-7.81e-02

Pos logit contributions
CLASSIFIED+0.027
 Koen+0.024
batch+0.023
KC+0.023
 Organisation+0.023
Neg logit contributions
ynes-0.023
owler-0.023
perty-0.020
perse-0.020
apesh-0.020
Token
Token ID198
Feature activation+4.31e-02

Pos logit contributions
CLASSIFIED+0.232
 Koen+0.224
batch+0.223
KC+0.217
 Rim+0.209
Neg logit contributions
owler-0.187
ynes-0.179
perty-0.168
perse-0.155
gow-0.155
Token
Token ID198
Feature activation-4.18e-02

Pos logit contributions
owler+0.090
ynes+0.087
gow+0.074
perse+0.074
perty+0.073
Neg logit contributions
CLASSIFIED-0.146
 Koen-0.134
batch-0.131
KC-0.129
 Ezek-0.128
TokenReviewer
Token ID35407
Feature activation-1.05e+00

Pos logit contributions
 Koen+0.112
CLASSIFIED+0.111
 Organisation+0.105
 Bened+0.105
 Rim+0.104
Neg logit contributions
owler-0.111
ynes-0.106
perty-0.101
gow-0.096
perse-0.095
Token:
Token ID25
Feature activation-7.60e-02

Pos logit contributions
CLASSIFIED+2.798
 Koen+2.669
batch+2.613
KC+2.568
 Rim+2.501
Neg logit contributions
owler-2.868
ynes-2.767
perty-2.570
perse-2.446
gow-2.426
Token V
Token ID569
Feature activation-2.27e-01

Pos logit contributions
CLASSIFIED+0.208
batch+0.198
 Koen+0.193
KC+0.191
 Organisation+0.184
Neg logit contributions
owler-0.203
ynes-0.194
perty-0.182
perse-0.171
gow-0.169
Tokenthe
Token ID1169
Feature activation-2.55e-01

Pos logit contributions
CLASSIFIED+0.610
 Koen+0.593
batch+0.582
 Rim+0.559
 Organisation+0.558
Neg logit contributions
owler-0.622
ynes-0.605
perty-0.557
perse-0.521
gow-0.519
TokenHappy
Token ID25082
Feature activation-1.12e-01

Pos logit contributions
CLASSIFIED+0.664
 Koen+0.642
batch+0.622
KC+0.604
 Rim+0.599
Neg logit contributions
owler-0.717
ynes-0.694
perty-0.648
gow-0.613
perse-0.612
TokenL
Token ID43
Feature activation+1.14e-02

Pos logit contributions
CLASSIFIED+0.289
 Koen+0.279
batch+0.271
KC+0.263
 Rim+0.261
Neg logit contributions
owler-0.313
ynes-0.305
perty-0.282
perse-0.265
gow-0.265
Token 01
Token ID5534
Feature activation-1.60e-01

Pos logit contributions
CLASSIFIED+0.498
batch+0.467
 Koen+0.457
KC+0.448
akin+0.432
Neg logit contributions
owler-0.590
ynes-0.573
perty-0.530
perse-0.511
gow-0.503
Token:
Token ID25
Feature activation-6.06e-01

Pos logit contributions
CLASSIFIED+0.476
 Koen+0.436
batch+0.428
KC+0.419
 Rim+0.410
Neg logit contributions
owler-0.391
ynes-0.376
perty-0.338
gow-0.332
perse-0.332
Token44
Token ID2598
Feature activation-2.65e-01

Pos logit contributions
CLASSIFIED+1.464
 Koen+1.352
batch+1.300
KC+1.259
 Rim+1.245
Neg logit contributions
owler-1.825
ynes-1.765
perty-1.631
gow-1.597
perse-1.586
Token:
Token ID25
Feature activation-4.61e-01

Pos logit contributions
CLASSIFIED+0.777
batch+0.721
 Koen+0.720
KC+0.697
 Rim+0.677
Neg logit contributions
owler-0.648
ynes-0.622
perty-0.573
perse-0.554
gow-0.548
Token24
Token ID1731
Feature activation-3.02e-01

Pos logit contributions
CLASSIFIED+1.118
 Koen+1.026
batch+0.988
KC+0.956
 Rim+0.944
Neg logit contributions
owler-1.383
ynes-1.333
perty-1.232
gow-1.210
perse-1.201
Token #
Token ID1303
Feature activation-1.04e+00

Pos logit contributions
CLASSIFIED+0.911
batch+0.860
 Koen+0.852
KC+0.835
 Rim+0.807
Neg logit contributions
owler-0.704
ynes-0.667
perty-0.618
perse-0.586
gow-0.580
Token19
Token ID1129
Feature activation+9.40e-02

Pos logit contributions
CLASSIFIED+2.139
 Koen+2.038
batch+1.972
KC+1.940
 Rim+1.876
Neg logit contributions
owler-3.490
ynes-3.389
perty-3.202
perse-3.058
gow-3.042
Token edit
Token ID4370
Feature activation+9.97e-02

Pos logit contributions
owler+0.279
ynes+0.268
perty+0.255
perse+0.240
gow+0.236
Neg logit contributions
CLASSIFIED-0.227
batch-0.212
 Koen-0.206
KC-0.205
 Rim-0.193
Token,
Token ID11
Feature activation+1.29e-01

Pos logit contributions
owler+0.260
ynes+0.249
perty+0.232
perse+0.220
apesh+0.212
Neg logit contributions
CLASSIFIED-0.277
 Koen-0.261
batch-0.257
KC-0.253
 Rim-0.247
Token n
Token ID299
Feature activation+2.04e-01

Pos logit contributions
owler+0.352
ynes+0.335
perty+0.317
perse+0.298
gow+0.292
Neg logit contributions
CLASSIFIED-0.344
batch-0.326
 Koen-0.322
KC-0.313
 Rim-0.303
Tokenvm
Token ID14761
Feature activation+1.32e-01

Pos logit contributions
owler+0.573
ynes+0.556
perty+0.523
perse+0.498
gow+0.497
Neg logit contributions
CLASSIFIED-0.535
 Koen-0.518
batch-0.494
 Kenn-0.475
KC-0.475
Tokener
Token ID263
Feature activation+2.22e-01

Pos logit contributions
owler+0.477
ynes+0.464
perty+0.432
gow+0.411
perse+0.407
Neg logit contributions
CLASSIFIED-0.425
 Koen-0.387
batch-0.378
KC-0.368
 Ezek-0.361
Token magnet
Token ID19972
Feature activation-6.97e-03

Pos logit contributions
owler+0.424
ynes+0.399
perty+0.359
perse+0.332
gow+0.323
Neg logit contributions
CLASSIFIED-0.781
batch-0.741
 Koen-0.741
KC-0.723
 Kenn-0.701
Token?
Token ID30
Feature activation-1.93e-03

Pos logit contributions
CLASSIFIED+0.020
 Koen+0.020
batch+0.020
KC+0.019
 Rim+0.019
Neg logit contributions
owler-0.017
ynes-0.016
perty-0.015
perse-0.014
gow-0.014
Token
Token ID198
Feature activation-5.19e-02

Pos logit contributions
CLASSIFIED+0.005
 Koen+0.005
batch+0.005
KC+0.005
 Rim+0.005
Neg logit contributions
owler-0.005
ynes-0.005
perty-0.005
perse-0.004
gow-0.004
Token
Token ID198
Feature activation-4.66e-02

Pos logit contributions
CLASSIFIED+0.172
 Koen+0.158
batch+0.155
KC+0.153
 Ezek+0.150
Neg logit contributions
owler-0.113
ynes-0.109
perty-0.093
perse-0.093
gow-0.093
TokenReviewer
Token ID35407
Feature activation-1.02e+00

Pos logit contributions
 Koen+0.129
CLASSIFIED+0.128
 Organisation+0.121
 Rim+0.120
 Bened+0.120
Neg logit contributions
owler-0.120
ynes-0.115
perty-0.108
perse-0.102
gow-0.102
Token:
Token ID25
Feature activation+9.77e-02

Pos logit contributions
CLASSIFIED+2.729
 Koen+2.598
batch+2.544
KC+2.501
 Rim+2.436
Neg logit contributions
owler-2.771
ynes-2.674
perty-2.480
perse-2.365
gow-2.344
Token hey
Token ID17207
Feature activation+9.01e-02

Pos logit contributions
owler+0.263
ynes+0.251
perty+0.235
perse+0.221
gow+0.219
Neg logit contributions
CLASSIFIED-0.265
batch-0.251
 Koen-0.244
KC-0.242
 Organisation-0.233
Token_
Token ID62
Feature activation+2.96e-01

Pos logit contributions
owler+0.257
ynes+0.247
perty+0.229
gow+0.220
perse+0.219
Neg logit contributions
CLASSIFIED-0.235
 Koen-0.226
batch-0.217
KC-0.212
 Organisation-0.212
Tokenler
Token ID1754
Feature activation+1.28e-01

Pos logit contributions
owler+0.841
ynes+0.813
perty+0.749
gow+0.734
perse+0.728
Neg logit contributions
CLASSIFIED-0.779
 Koen-0.749
 Rim-0.697
 Organisation-0.695
batch-0.690
Tokenoy
Token ID726
Feature activation+7.11e-03

Pos logit contributions
owler+0.366
ynes+0.363
perty+0.333
gow+0.326
gew+0.311
Neg logit contributions
CLASSIFIED-0.342
 Koen-0.313
batch-0.300
 Organisation-0.294
 Parties-0.291
Token was
Token ID373
Feature activation+1.40e-01

Pos logit contributions
owler+0.152
ynes+0.147
perty+0.134
gow+0.128
perse+0.126
Neg logit contributions
CLASSIFIED-0.148
 Koen-0.140
batch-0.139
KC-0.137
 Rim-0.132
Token about
Token ID546
Feature activation-2.20e-02

Pos logit contributions
owler+0.371
ynes+0.356
perty+0.334
gow+0.313
perse+0.311
Neg logit contributions
CLASSIFIED-0.378
batch-0.358
 Koen-0.349
KC-0.345
 Organisation-0.332
Token homosexuality
Token ID19822
Feature activation+1.56e-01

Pos logit contributions
CLASSIFIED+0.061
batch+0.057
KC+0.057
 Koen+0.056
 Organisation+0.053
Neg logit contributions
owler-0.057
ynes-0.055
perty-0.052
perse-0.048
apesh-0.048
Token
Token ID198
Feature activation-7.12e-02

Pos logit contributions
owler+0.407
ynes+0.395
perty+0.374
perse+0.344
gow+0.340
Neg logit contributions
CLASSIFIED-0.429
batch-0.414
 Koen-0.406
KC-0.396
 Rim-0.382
Token
Token ID198
Feature activation-7.66e-02

Pos logit contributions
CLASSIFIED+0.218
 Koen+0.215
batch+0.208
KC+0.202
 Rim+0.202
Neg logit contributions
owler-0.162
ynes-0.157
perty-0.142
perse-0.136
gow-0.135
TokenReviewer
Token ID35407
Feature activation-1.01e+00

Pos logit contributions
 Koen+0.195
CLASSIFIED+0.192
batch+0.183
 Rim+0.181
 Organisation+0.181
Neg logit contributions
owler-0.213
ynes-0.206
perty-0.194
gow-0.185
perse-0.184
Token:
Token ID25
Feature activation+5.28e-02

Pos logit contributions
CLASSIFIED+2.707
 Koen+2.572
batch+2.546
KC+2.497
 Rim+2.416
Neg logit contributions
owler-2.787
ynes-2.683
perty-2.493
perse-2.363
gow-2.346
Token k
Token ID479
Feature activation-5.16e-02

Pos logit contributions
owler+0.142
ynes+0.135
perty+0.127
perse+0.120
gow+0.119
Neg logit contributions
CLASSIFIED-0.143
batch-0.135
 Koen-0.132
KC-0.131
 Organisation-0.126
Tokenimp
Token ID11011
Feature activation-8.73e-02

Pos logit contributions
CLASSIFIED+0.140
 Koen+0.132
batch+0.127
KC+0.127
 Organisation+0.124
Neg logit contributions
owler-0.146
ynes-0.142
perty-0.129
perse-0.123
apesh-0.122
Tokenunk
Token ID2954
Feature activation-1.18e-01

Pos logit contributions
CLASSIFIED+0.230
 Koen+0.215
batch+0.206
KC+0.202
 Rim+0.201
Neg logit contributions
owler-0.255
ynes-0.245
perty-0.228
perse-0.217
gow-0.216
Tokenrock
Token ID10823
Feature activation+2.41e-02

Pos logit contributions
CLASSIFIED+0.316
 Koen+0.296
batch+0.285
 Rim+0.279
KC+0.278
Neg logit contributions
owler-0.338
ynes-0.325
perty-0.299
gow-0.287
perse-0.284
Token are
Token ID389
Feature activation+9.89e-02

Pos logit contributions
owler+0.190
ynes+0.179
perty+0.161
gow+0.153
perse+0.152
Neg logit contributions
CLASSIFIED-0.275
 Koen-0.258
batch-0.255
KC-0.251
 Rim-0.242
Token Here
Token ID3423
Feature activation+6.81e-02

Pos logit contributions
owler+0.235
ynes+0.226
perty+0.211
perse+0.196
gow+0.194
Neg logit contributions
CLASSIFIED-0.295
 Koen-0.285
batch-0.282
KC-0.279
 Rim-0.270
Token....
Token ID1106
Feature activation-1.04e-01

Pos logit contributions
owler+0.151
ynes+0.143
perty+0.133
perse+0.123
gow+0.123
Neg logit contributions
CLASSIFIED-0.214
 Koen-0.211
batch-0.205
KC-0.205
 Organisation-0.198
Token
Token ID198
Feature activation+1.10e-01

Pos logit contributions
CLASSIFIED+0.271
 Koen+0.261
batch+0.258
KC+0.253
 Rim+0.245
Neg logit contributions
owler-0.285
ynes-0.276
perty-0.260
perse-0.243
gow-0.240
Token
Token ID198
Feature activation+2.62e-02

Pos logit contributions
owler+0.232
ynes+0.225
gow+0.192
perse+0.192
perty+0.189
Neg logit contributions
CLASSIFIED-0.370
 Koen-0.339
batch-0.331
KC-0.328
 Ezek-0.322
TokenReviewer
Token ID35407
Feature activation-1.01e+00

Pos logit contributions
owler+0.068
ynes+0.066
perty+0.061
perse+0.059
gow+0.058
Neg logit contributions
CLASSIFIED-0.072
 Koen-0.071
 Organisation-0.067
batch-0.067
 Rim-0.067
Token:
Token ID25
Feature activation+2.15e-01

Pos logit contributions
CLASSIFIED+2.703
 Koen+2.576
batch+2.524
KC+2.480
 Rim+2.415
Neg logit contributions
owler-2.762
ynes-2.667
perty-2.475
perse-2.359
gow-2.337
Token SAS
Token ID35516
Feature activation-1.31e-02

Pos logit contributions
owler+0.581
ynes+0.555
perty+0.519
perse+0.491
gow+0.483
Neg logit contributions
CLASSIFIED-0.578
batch-0.548
 Koen-0.529
KC-0.525
 Organisation-0.505
TokenK
Token ID42
Feature activation+5.02e-03

Pos logit contributions
CLASSIFIED+0.032
 Koen+0.031
batch+0.030
 Rim+0.029
KC+0.029
Neg logit contributions
owler-0.039
ynes-0.037
perty-0.035
gow-0.033
perse-0.033
TokenATCH
Token ID11417
Feature activation-2.13e-01

Pos logit contributions
owler+0.015
ynes+0.014
perty+0.013
gow+0.012
perse+0.012
Neg logit contributions
CLASSIFIED-0.012
 Koen-0.012
batch-0.012
 Rim-0.011
KC-0.011
TokenEW
Token ID6217
Feature activation-3.73e-02

Pos logit contributions
CLASSIFIED+0.538
batch+0.517
 Koen+0.517
 Rim+0.487
KC+0.483
Neg logit contributions
owler-0.601
ynes-0.584
perty-0.544
gow-0.512
apesh-0.506
Token_
Token ID62
Feature activation+2.38e-01

Pos logit contributions
CLASSIFIED+0.098
 Koen+0.096
batch+0.092
KC+0.092
 Organisation+0.089
Neg logit contributions
owler-0.086
ynes-0.084
perty-0.077
perse-0.074
gow-0.072
Tokenos
Token ID418
Feature activation+1.45e-01

Pos logit contributions
owler+0.646
ynes+0.625
perty+0.560
perse+0.555
gow+0.552
Neg logit contributions
CLASSIFIED-0.632
 Koen-0.628
 Kenn-0.581
 Dion-0.580
KC-0.578
Token_
Token ID62
Feature activation+2.27e-01

Pos logit contributions
ynes+0.367
owler+0.363
perty+0.324
perse+0.323
gow+0.317
Neg logit contributions
CLASSIFIED-0.415
 Koen-0.403
KC-0.377
 Organisation-0.371
batch-0.368
Tokencache
Token ID23870
Feature activation+7.12e-02

Pos logit contributions
owler+0.633
ynes+0.611
perty+0.558
perse+0.545
gow+0.534
Neg logit contributions
CLASSIFIED-0.614
 Koen-0.584
KC-0.548
 Organisation-0.537
 Dion-0.537
Token();
Token ID9783
Feature activation+1.14e-01

Pos logit contributions
owler+0.188
ynes+0.186
perty+0.169
perse+0.164
apesh+0.156
Neg logit contributions
CLASSIFIED-0.193
 Koen-0.187
batch-0.179
KC-0.177
 Kenn-0.173
Token }
Token ID1782
Feature activation-9.95e-01

Pos logit contributions
owler+0.275
ynes+0.261
perty+0.233
perse+0.224
gow+0.223
Neg logit contributions
CLASSIFIED-0.340
 Koen-0.318
batch-0.313
KC-0.312
 Organisation-0.298
Token }
Token ID1782
Feature activation-1.12e+00

Pos logit contributions
CLASSIFIED+2.810
 Koen+2.696
batch+2.659
KC+2.620
 Rim+2.533
Neg logit contributions
owler-2.555
ynes-2.460
perty-2.285
perse-2.146
gow-2.114
Token
Token ID198
Feature activation-4.15e-01

Pos logit contributions
CLASSIFIED+3.165
 Koen+3.038
batch+2.997
KC+2.952
 Rim+2.857
Neg logit contributions
owler-2.882
ynes-2.772
perty-2.582
perse-2.419
gow-2.381
Token
Token ID198
Feature activation-2.75e-01

Pos logit contributions
CLASSIFIED+1.309
 Koen+1.270
batch+1.217
KC+1.197
 Ezek+1.191
Neg logit contributions
owler-0.932
ynes-0.885
perty-0.798
perse-0.771
gow-0.771
TokenOne
Token ID3198
Feature activation-7.55e-02

Pos logit contributions
 Koen+0.736
CLASSIFIED+0.722
 Kenn+0.687
 Dion+0.680
 Ezek+0.680
Neg logit contributions
owler-0.746
ynes-0.714
perty-0.670
gow-0.644
perse-0.631
Token feature
Token ID3895
Feature activation+6.90e-01

Pos logit contributions
CLASSIFIED+0.213
batch+0.199
 Koen+0.194
KC+0.189
 Rim+0.181
Neg logit contributions
owler-0.200
ynes-0.194
perty-0.184
perse-0.166
gow-0.166
Token post
Token ID1281
Feature activation+3.20e-01

Pos logit contributions
CLASSIFIED+1.228
 Koen+1.167
batch+1.165
KC+1.159
 Rim+1.093
Neg logit contributions
owler-1.098
ynes-1.061
perty-0.991
gow-0.913
perse-0.906
Token-
Token ID12
Feature activation-1.44e-01

Pos logit contributions
owler+0.826
ynes+0.803
perty+0.746
gow+0.697
perse+0.684
Neg logit contributions
CLASSIFIED-0.895
 Koen-0.833
KC-0.825
batch-0.819
 Organisation-0.806
Tokenelection
Token ID14300
Feature activation-4.52e-01

Pos logit contributions
CLASSIFIED+0.330
 Koen+0.321
 Organisation+0.300
 Rim+0.299
 Dion+0.296
Neg logit contributions
owler-0.447
ynes-0.433
perty-0.406
gow-0.392
har-0.385
Token conflicts
Token ID12333
Feature activation-4.20e-01

Pos logit contributions
CLASSIFIED+1.254
 Koen+1.188
batch+1.181
KC+1.181
 Rim+1.110
Neg logit contributions
owler-1.182
ynes-1.146
perty-1.073
gow-0.995
perse-0.989
Token of
Token ID286
Feature activation-2.21e-01

Pos logit contributions
CLASSIFIED+1.086
batch+1.036
 Koen+1.021
KC+1.017
 Organisation+0.962
Neg logit contributions
owler-1.190
ynes-1.148
perty-1.089
perse-1.008
gow-0.985
Token interest
Token ID1393
Feature activation-9.90e-01

Pos logit contributions
CLASSIFIED+0.730
batch+0.711
 Koen+0.701
KC+0.696
 Rim+0.669
Neg logit contributions
owler-0.453
ynes-0.431
perty-0.411
perse-0.381
gow-0.357
Token like
Token ID588
Feature activation+7.84e-03

Pos logit contributions
CLASSIFIED+2.557
 Koen+2.445
batch+2.442
KC+2.399
 Rim+2.290
Neg logit contributions
owler-2.786
ynes-2.681
perty-2.532
perse-2.367
gow-2.343
Token the
Token ID262
Feature activation-2.10e-02

Pos logit contributions
owler+0.020
ynes+0.018
perty+0.018
gow+0.016
perse+0.016
Neg logit contributions
CLASSIFIED-0.022
batch-0.021
KC-0.021
 Koen-0.021
 Rim-0.020
Token ones
Token ID3392
Feature activation+3.21e-02

Pos logit contributions
CLASSIFIED+0.057
batch+0.054
KC+0.054
 Koen+0.053
 Rim+0.050
Neg logit contributions
owler-0.056
ynes-0.053
perty-0.051
 Scrib-0.046
gow-0.045
Token seen
Token ID1775
Feature activation-1.37e-01

Pos logit contributions
owler+0.087
ynes+0.082
perty+0.078
gow+0.070
perse+0.070
Neg logit contributions
CLASSIFIED-0.086
batch-0.083
 Koen-0.080
KC-0.080
 Organisation-0.078
Token in
Token ID287
Feature activation-1.87e-01

Pos logit contributions
CLASSIFIED+0.372
 Koen+0.356
batch+0.352
KC+0.350
 Organisation+0.337
Neg logit contributions
owler-0.368
ynes-0.351
perty-0.334
gow-0.311
perse-0.306
Token
Token ID198
Feature activation-2.04e-01

Pos logit contributions
owler+0.702
ynes+0.682
perty+0.645
perse+0.604
apesh+0.582
Neg logit contributions
CLASSIFIED-0.715
batch-0.689
 Koen-0.682
KC-0.674
 Rim-0.656
Token
Token ID198
Feature activation-2.90e-01

Pos logit contributions
CLASSIFIED+0.656
 Koen+0.611
batch+0.601
KC+0.592
 Rim+0.575
Neg logit contributions
owler-0.458
ynes-0.443
perty-0.388
perse-0.381
gow-0.378
Token1
Token ID16
Feature activation-3.30e-01

Pos logit contributions
CLASSIFIED+0.746
 Koen+0.737
batch+0.700
 Rim+0.686
 Organisation+0.682
Neg logit contributions
owler-0.814
ynes-0.792
perty-0.745
perse-0.705
gow-0.698
Token 2
Token ID362
Feature activation-7.20e-01

Pos logit contributions
CLASSIFIED+0.936
batch+0.865
 Koen+0.850
KC+0.825
 Rim+0.815
Neg logit contributions
owler-0.870
ynes-0.831
perty-0.780
perse-0.731
gow-0.723
Token 3
Token ID513
Feature activation-7.23e-01

Pos logit contributions
CLASSIFIED+1.603
 Koen+1.557
batch+1.508
KC+1.507
 Rim+1.438
Neg logit contributions
owler-2.255
ynes-2.202
perty-2.093
perse-1.968
gow-1.953
Token Next
Token ID7406
Feature activation-9.70e-01

Pos logit contributions
CLASSIFIED+1.779
 Koen+1.737
batch+1.705
KC+1.686
 Rim+1.629
Neg logit contributions
owler-2.078
ynes-2.013
perty-1.893
gow-1.797
perse-1.773
Token All
Token ID1439
Feature activation-4.71e-01

Pos logit contributions
CLASSIFIED+2.321
 Koen+2.184
KC+2.179
batch+2.176
 Rim+2.037
Neg logit contributions
owler-2.943
ynes-2.792
perty-2.627
perse-2.484
gow-2.482
Token<|endoftext|>
Token ID50256
Feature activation-5.86e-02

Pos logit contributions
CLASSIFIED+0.960
KC+0.873
 Koen+0.870
batch+0.869
 Kenn+0.804
Neg logit contributions
owler-1.612
ynes-1.503
perty-1.396
perse-1.370
gow-1.356
TokenRepublican
Token ID25777
Feature activation-3.14e-02

Pos logit contributions
 Koen+0.157
CLASSIFIED+0.155
batch+0.148
 Kenn+0.147
 Rim+0.146
Neg logit contributions
owler-0.154
ynes-0.150
perty-0.140
perse-0.133
gow-0.133
Token Sen
Token ID2311
Feature activation-5.23e-01

Pos logit contributions
CLASSIFIED+0.089
batch+0.082
 Koen+0.081
KC+0.078
OVA+0.075
Neg logit contributions
owler-0.082
ynes-0.080
perty-0.073
gow-0.069
perse-0.068
Token.
Token ID13
Feature activation-2.24e-01

Pos logit contributions
CLASSIFIED+1.536
batch+1.390
 Koen+1.359
KC+1.352
 Rim+1.308
Neg logit contributions
owler-1.387
ynes-1.325
perty-1.207
perse-1.150
gow-1.149
Token the
Token ID262
Feature activation-1.19e-01

Pos logit contributions
CLASSIFIED+0.124
batch+0.120
KC+0.116
 Koen+0.116
 Rim+0.110
Neg logit contributions
owler-0.106
ynes-0.105
perty-0.096
gow-0.088
perse-0.088
Token prime
Token ID6994
Feature activation-6.54e-01

Pos logit contributions
CLASSIFIED+0.361
batch+0.341
 Koen+0.336
KC+0.332
 Rim+0.311
Neg logit contributions
owler-0.282
ynes-0.276
perty-0.250
gow-0.235
perse-0.228
Token challenge
Token ID4427
Feature activation-4.16e-02

Pos logit contributions
CLASSIFIED+1.985
batch+1.906
 Koen+1.898
KC+1.873
 Rim+1.786
Neg logit contributions
owler-1.554
ynes-1.510
perty-1.385
gow-1.282
perse-1.280
Token Belfast
Token ID29713
Feature activation-5.77e-04

Pos logit contributions
CLASSIFIED+0.117
batch+0.111
 Koen+0.108
KC+0.108
 Rim+0.105
Neg logit contributions
owler-0.106
ynes-0.104
perty-0.098
gow-0.090
perse-0.089
TokenTe
Token ID6767
Feature activation-6.52e-02

Pos logit contributions
CLASSIFIED+0.001
 Koen+0.001
batch+0.001
KC+0.001
 Rim+0.001
Neg logit contributions
owler-0.002
ynes-0.002
perty-0.002
gow-0.001
perse-0.001
Tokenlegraph
Token ID16606
Feature activation-9.61e-01

Pos logit contributions
CLASSIFIED+0.202
 Koen+0.196
batch+0.188
KC+0.183
 Rim+0.182
Neg logit contributions
ynes-0.151
owler-0.148
perty-0.139
apesh-0.124
perse-0.123
Token.
Token ID13
Feature activation+5.60e-02

Pos logit contributions
CLASSIFIED+2.348
 Koen+2.262
batch+2.231
KC+2.192
 Rim+2.119
Neg logit contributions
owler-2.805
ynes-2.718
perty-2.568
perse-2.411
gow-2.388
Tokenco
Token ID1073
Feature activation+6.03e-02

Pos logit contributions
ynes+0.135
owler+0.133
perty+0.116
gow+0.112
perse+0.110
Neg logit contributions
CLASSIFIED-0.168
 Koen-0.160
batch-0.157
 Rim-0.151
KC-0.151
Token.
Token ID13
Feature activation-1.42e-01

Pos logit contributions
owler+0.159
ynes+0.158
perty+0.143
gow+0.137
perse+0.136
Neg logit contributions
CLASSIFIED-0.171
 Koen-0.159
batch-0.153
KC-0.152
 Rim-0.149
Tokenuk
Token ID2724
Feature activation-1.14e-01

Pos logit contributions
CLASSIFIED+0.375
 Koen+0.352
batch+0.339
 Rim+0.331
KC+0.329
Neg logit contributions
owler-0.401
ynes-0.398
perty-0.367
perse-0.349
gow-0.347
Token Dis
Token ID3167
Feature activation+2.18e-01

Pos logit contributions
CLASSIFIED+0.295
batch+0.276
 Koen+0.267
KC+0.266
akin+0.255
Neg logit contributions
owler-0.314
ynes-0.308
perty-0.287
gow-0.270
perse-0.264
Token lad
Token ID9717
Feature activation+1.11e-01

Pos logit contributions
CLASSIFIED+0.166
batch+0.158
KC+0.157
 Koen+0.156
 Rim+0.148
Neg logit contributions
owler-0.155
ynes-0.149
perty-0.141
perse-0.133
gow-0.128
Tokenen
Token ID268
Feature activation-3.26e-02

Pos logit contributions
owler+0.290
ynes+0.284
perty+0.258
gow+0.244
perse+0.244
Neg logit contributions
CLASSIFIED-0.311
 Koen-0.286
KC-0.284
batch-0.284
 Rim-0.274
Token with
Token ID351
Feature activation-2.02e-01

Pos logit contributions
CLASSIFIED+0.069
 Koen+0.066
batch+0.064
KC+0.064
 Rim+0.061
Neg logit contributions
owler-0.105
ynes-0.103
perty-0.097
perse-0.092
gow-0.092
Token exp
Token ID1033
Feature activation-9.94e-02

Pos logit contributions
CLASSIFIED+0.563
 Koen+0.524
batch+0.523
KC+0.522
 Rim+0.493
Neg logit contributions
owler-0.536
ynes-0.506
perty-0.477
perse-0.443
gow-0.439
Tokenlet
Token ID1616
Feature activation-4.18e-01

Pos logit contributions
CLASSIFIED+0.241
 Koen+0.207
batch+0.206
KC+0.201
 Kenn+0.194
Neg logit contributions
owler-0.328
ynes-0.321
perty-0.300
perse-0.279
apesh-0.275
Tokenives
Token ID1083
Feature activation-9.55e-01

Pos logit contributions
CLASSIFIED+1.250
 Koen+1.125
batch+1.112
KC+1.107
 Organisation+1.104
Neg logit contributions
ynes-1.082
owler-1.072
perty-0.972
apesh-0.921
gow-0.903
Token,
Token ID11
Feature activation-2.10e-01

Pos logit contributions
CLASSIFIED+2.445
 Koen+2.325
batch+2.310
KC+2.281
 Rim+2.173
Neg logit contributions
owler-2.729
ynes-2.637
perty-2.499
perse-2.325
gow-2.308
Token expressing
Token ID16621
Feature activation-3.11e-01

Pos logit contributions
CLASSIFIED+0.591
batch+0.559
KC+0.553
 Koen+0.551
 Rim+0.522
Neg logit contributions
owler-0.547
ynes-0.522
perty-0.496
gow-0.452
perse-0.451
Token dismay
Token ID29793
Feature activation-2.86e-01

Pos logit contributions
CLASSIFIED+0.966
batch+0.921
KC+0.910
 Koen+0.910
 Rim+0.869
Neg logit contributions
owler-0.726
ynes-0.673
perty-0.639
gow-0.590
perse-0.587
Token that
Token ID326
Feature activation-4.80e-02

Pos logit contributions
CLASSIFIED+0.792
 Koen+0.757
batch+0.746
KC+0.738
 Rim+0.708
Neg logit contributions
owler-0.765
ynes-0.739
perty-0.687
gow-0.642
perse-0.635
Token there
Token ID612
Feature activation-2.00e-02

Pos logit contributions
CLASSIFIED+0.139
batch+0.129
KC+0.128
 Koen+0.127
 Rim+0.121
Neg logit contributions
owler-0.123
ynes-0.114
perty-0.108
gow-0.101
perse-0.100
Token 5
Token ID642
Feature activation+7.53e-03

Pos logit contributions
CLASSIFIED+0.603
 Koen+0.572
KC+0.553
batch+0.552
 Rim+0.534
Neg logit contributions
owler-0.609
ynes-0.588
perty-0.531
gow-0.509
perse-0.499
Token);
Token ID1776
Feature activation-2.81e-01

Pos logit contributions
owler+0.021
ynes+0.020
perty+0.019
perse+0.018
gow+0.018
Neg logit contributions
CLASSIFIED-0.019
 Koen-0.019
batch-0.018
 Kenn-0.018
KC-0.017
Token ++
Token ID19969
Feature activation-1.66e-02

Pos logit contributions
CLASSIFIED+0.712
 Koen+0.675
batch+0.672
KC+0.658
 Kenn+0.630
Neg logit contributions
owler-0.789
ynes-0.758
perty-0.708
perse-0.669
gow-0.661
Tokencount
Token ID9127
Feature activation+4.61e-02

Pos logit contributions
CLASSIFIED+0.046
 Koen+0.046
KC+0.042
 Bened+0.042
 Dion+0.042
Neg logit contributions
owler-0.042
ynes-0.041
perty-0.037
perse-0.035
gow-0.035
Token;
Token ID26
Feature activation-4.78e-01

Pos logit contributions
owler+0.131
ynes+0.127
perty+0.115
perse+0.112
gow+0.108
Neg logit contributions
CLASSIFIED-0.116
 Koen-0.111
batch-0.108
KC-0.107
 Kenn-0.104
Token }
Token ID1782
Feature activation-9.55e-01

Pos logit contributions
CLASSIFIED+1.413
 Koen+1.341
batch+1.330
KC+1.310
 Rim+1.264
Neg logit contributions
owler-1.164
ynes-1.112
perty-1.014
perse-0.962
apesh-0.940
Token RAW
Token ID33782
Feature activation-5.35e-03

Pos logit contributions
CLASSIFIED+2.666
 Koen+2.558
batch+2.519
KC+2.485
 Rim+2.402
Neg logit contributions
owler-2.481
ynes-2.389
perty-2.217
perse-2.099
gow-2.050
Token_
Token ID62
Feature activation+1.60e-01

Pos logit contributions
CLASSIFIED+0.016
 Koen+0.016
batch+0.015
 Rim+0.015
 Organisation+0.015
Neg logit contributions
owler-0.012
ynes-0.012
perty-0.010
perse-0.010
gow-0.010
TokenASS
Token ID10705
Feature activation+1.14e-01

Pos logit contributions
owler+0.469
ynes+0.449
perty+0.421
perse+0.402
gow+0.399
Neg logit contributions
 Koen-0.377
CLASSIFIED-0.369
 Ezek-0.353
 Bened-0.352
 Dion-0.351
TokenERT
Token ID17395
Feature activation+1.08e-01

Pos logit contributions
owler+0.350
ynes+0.340
perty+0.316
gow+0.304
perse+0.303
Neg logit contributions
CLASSIFIED-0.256
 Koen-0.248
batch-0.240
KC-0.229
 Dion-0.229
Token(
Token ID7
Feature activation+1.78e-01

Pos logit contributions
owler+0.290
ynes+0.284
perty+0.263
perse+0.247
gow+0.245
Neg logit contributions
CLASSIFIED-0.284
 Koen-0.277
batch-0.271
KC-0.265
 Organisation-0.257
Token10
Token ID940
Feature activation-2.31e-01

Pos logit contributions
owler+0.376
ynes+0.369
perty+0.342
perse+0.332
gow+0.319
Neg logit contributions
CLASSIFIED-0.495
 Koen-0.481
 Rim-0.454
KC-0.450
 Kenn-0.449
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
CLASSIFIED+0.656
 Koen+0.618
batch+0.594
KC+0.583
 Rim+0.574
Neg logit contributions
owler-0.600
ynes-0.579
perty-0.531
perse-0.512
gow-0.503
Token13
Token ID1485
Feature activation-1.82e-01

Pos logit contributions
CLASSIFIED+0.654
 Koen+0.622
batch+0.602
KC+0.596
 Kenn+0.584
Neg logit contributions
owler-0.729
ynes-0.708
perty-0.668
gow-0.637
perse-0.637
Token71
Token ID4869
Feature activation-1.12e-01

Pos logit contributions
CLASSIFIED+0.405
 Koen+0.372
 Rim+0.348
batch+0.343
 Kenn+0.341
Neg logit contributions
owler-0.595
ynes-0.554
perty-0.550
perse-0.525
gow-0.509
Token/
Token ID14
Feature activation+1.74e-01

Pos logit contributions
CLASSIFIED+0.309
 Koen+0.286
KC+0.278
batch+0.275
 Rim+0.269
Neg logit contributions
owler-0.294
ynes-0.290
gow-0.259
perty-0.258
perse-0.257
Tokenjournal
Token ID24891
Feature activation-9.48e-01

Pos logit contributions
owler+0.374
ynes+0.374
perty+0.337
perse+0.335
har+0.324
Neg logit contributions
CLASSIFIED-0.558
 Koen-0.547
batch-0.520
 Rim-0.512
 Kenn-0.495
Token.
Token ID13
Feature activation-7.03e-02

Pos logit contributions
CLASSIFIED+2.537
 Koen+2.399
batch+2.320
KC+2.297
 Rim+2.247
Neg logit contributions
owler-2.633
ynes-2.538
perty-2.363
perse-2.258
gow-2.234
Tokenp
Token ID79
Feature activation-1.65e-01

Pos logit contributions
CLASSIFIED+0.184
 Koen+0.175
 Kenn+0.162
KC+0.160
 Rim+0.159
Neg logit contributions
owler-0.211
ynes-0.202
perse-0.188
gow-0.185
perty-0.184
Tokenone
Token ID505
Feature activation-7.72e-02

Pos logit contributions
CLASSIFIED+0.393
 Koen+0.373
batch+0.342
KC+0.341
 Organisation+0.340
Neg logit contributions
owler-0.513
ynes-0.513
perty-0.469
perse-0.455
gow-0.447
Token.
Token ID13
Feature activation-1.10e-01

Pos logit contributions
CLASSIFIED+0.231
 Koen+0.219
batch+0.208
 Ezek+0.205
 Organisation+0.204
Neg logit contributions
owler-0.191
ynes-0.185
perty-0.164
perse-0.160
gow-0.158
Token00
Token ID405
Feature activation-3.38e-02

Pos logit contributions
CLASSIFIED+0.260
 Koen+0.254
 Rim+0.236
 Kenn+0.235
batch+0.233
Neg logit contributions
owler-0.340
ynes-0.326
perty-0.299
perse-0.298
gow-0.295
Token,
Token ID11
Feature activation-2.22e-01

Pos logit contributions
CLASSIFIED+1.246
 Koen+1.211
batch+1.196
KC+1.167
 Rim+1.132
Neg logit contributions
owler-1.691
ynes-1.635
perty-1.553
perse-1.464
gow-1.452
Token Mikhail
Token ID42040
Feature activation-8.36e-03

Pos logit contributions
CLASSIFIED+0.573
batch+0.530
KC+0.511
 Koen+0.493
 Parties+0.474
Neg logit contributions
owler-0.629
ynes-0.606
perty-0.569
gow-0.538
perse-0.533
Token Al
Token ID978
Feature activation+2.99e-01

Pos logit contributions
CLASSIFIED+0.018
batch+0.016
KC+0.016
 Koen+0.016
 Rim+0.015
Neg logit contributions
owler-0.027
ynes-0.027
perty-0.025
gow-0.024
perse-0.024
Token"]
Token ID8973
Feature activation-4.85e-01

Pos logit contributions
owler+0.833
ynes+0.827
perty+0.766
perse+0.722
gow+0.717
Neg logit contributions
CLASSIFIED-0.821
 Koen-0.736
KC-0.725
batch-0.711
 Organisation-0.697
Token [
Token ID685
Feature activation+1.94e-01

Pos logit contributions
CLASSIFIED+1.559
 Koen+1.464
batch+1.459
KC+1.440
 Rim+1.387
Neg logit contributions
owler-1.069
ynes-1.018
perty-0.904
perse-0.881
gow-0.871
TokenResult
Token ID23004
Feature activation-9.35e-01

Pos logit contributions
owler+0.493
ynes+0.472
perty+0.441
perse+0.414
gow+0.413
Neg logit contributions
CLASSIFIED-0.545
 Koen-0.523
batch-0.518
KC-0.497
 Rim-0.497
Token "
Token ID366
Feature activation-5.10e-01

Pos logit contributions
CLASSIFIED+2.493
 Koen+2.396
batch+2.359
KC+2.319
 Rim+2.238
Neg logit contributions
owler-2.543
ynes-2.458
perty-2.280
perse-2.166
gow-2.140
Token1
Token ID16
Feature activation-6.03e-01

Pos logit contributions
CLASSIFIED+1.336
 Koen+1.300
batch+1.235
 Rim+1.200
 Dion+1.194
Neg logit contributions
owler-1.388
ynes-1.382
perty-1.223
gow-1.220
perse-1.181
Token/
Token ID14
Feature activation-4.81e-01

Pos logit contributions
CLASSIFIED+1.654
batch+1.570
 Koen+1.552
KC+1.505
 Rim+1.460
Neg logit contributions
owler-1.617
ynes-1.557
perty-1.416
gow-1.360
perse-1.346
Token2
Token ID17
Feature activation-8.81e-01

Pos logit contributions
CLASSIFIED+1.151
 Koen+1.116
batch+1.042
 Rim+1.029
 Bened+1.014
Neg logit contributions
owler-1.453
ynes-1.434
perty-1.283
gow-1.266
apesh-1.244
Token-
Token ID12
Feature activation-4.62e-01

Pos logit contributions
CLASSIFIED+2.430
 Koen+2.279
batch+2.268
KC+2.234
 Rim+2.133
Neg logit contributions
owler-2.352
ynes-2.292
perty-2.090
gow-1.950
perse-1.946
Token.
Token ID13
Feature activation+3.64e-02

Pos logit contributions
CLASSIFIED+0.213
batch+0.201
 Koen+0.199
KC+0.195
 Rim+0.185
Neg logit contributions
owler-0.200
ynes-0.191
perty-0.177
perse-0.167
gow-0.161
Token
Token ID198
Feature activation+3.35e-02

Pos logit contributions
owler+0.094
ynes+0.089
perty+0.081
 Scrib+0.080
gow+0.079
Neg logit contributions
CLASSIFIED-0.099
batch-0.095
 Koen-0.092
KC-0.091
 flavours-0.090
Token
Token ID198
Feature activation-2.46e-02

Pos logit contributions
owler+0.070
ynes+0.068
perse+0.058
gow+0.058
perty+0.058
Neg logit contributions
CLASSIFIED-0.113
 Koen-0.104
batch-0.102
KC-0.100
 Ezek-0.099
TokenIs
Token ID3792
Feature activation-7.64e-02

Pos logit contributions
 Koen+0.069
CLASSIFIED+0.067
batch+0.064
 Rim+0.064
 Kenn+0.063
Neg logit contributions
owler-0.063
ynes-0.060
perty-0.056
gow-0.053
perse-0.053
Token teacher
Token ID4701
Feature activation-1.21e-01

Pos logit contributions
CLASSIFIED+0.209
 Koen+0.203
batch+0.201
KC+0.199
 Rim+0.191
Neg logit contributions
owler-0.202
ynes-0.191
perty-0.177
perse-0.169
gow-0.167
Token turnover
Token ID25079
Feature activation-9.25e-01

Pos logit contributions
CLASSIFIED+0.363
 Koen+0.353
batch+0.352
KC+0.348
 Rim+0.338
Neg logit contributions
owler-0.287
ynes-0.281
perty-0.254
perse-0.234
gow-0.230
Token high
Token ID1029
Feature activation-2.63e-01

Pos logit contributions
CLASSIFIED+2.601
 Koen+2.507
batch+2.503
KC+2.439
 Rim+2.360
Neg logit contributions
owler-2.392
ynes-2.324
perty-2.144
perse-2.013
gow-1.994
Token?
Token ID30
Feature activation-1.14e-01

Pos logit contributions
CLASSIFIED+0.760
 Koen+0.733
batch+0.726
KC+0.715
 Rim+0.686
Neg logit contributions
owler-0.669
ynes-0.635
perty-0.590
perse-0.554
gow-0.550
Token
Token ID198
Feature activation-1.38e-01

Pos logit contributions
CLASSIFIED+0.340
batch+0.326
 Koen+0.318
KC+0.314
 flavours+0.303
Neg logit contributions
owler-0.275
ynes-0.269
perty-0.239
gow-0.227
perse-0.226
Token
Token ID198
Feature activation-1.41e-01

Pos logit contributions
CLASSIFIED+0.447
 Koen+0.418
batch+0.410
KC+0.402
 Rim+0.393
Neg logit contributions
owler-0.306
ynes-0.295
perty-0.257
perse-0.253
gow-0.253
TokenP
Token ID47
Feature activation+3.03e-02

Pos logit contributions
 Koen+0.397
CLASSIFIED+0.386
batch+0.375
 Rim+0.367
 Kenn+0.365
Neg logit contributions
owler-0.360
ynes-0.347
perty-0.317
gow-0.307
perse-0.305
Token United
Token ID1578
Feature activation-2.30e-01

Pos logit contributions
CLASSIFIED+0.846
batch+0.799
 Koen+0.765
KC+0.764
 flavours+0.727
Neg logit contributions
owler-0.804
ynes-0.788
perty-0.748
perse-0.702
gow-0.701
Token States
Token ID1829
Feature activation-3.54e-01

Pos logit contributions
CLASSIFIED+0.421
 Koen+0.405
batch+0.394
KC+0.386
 Rim+0.370
Neg logit contributions
owler-0.811
ynes-0.788
perty-0.752
perse-0.714
gow-0.708
Token 228
Token ID29041
Feature activation+1.08e-01

Pos logit contributions
CLASSIFIED+0.907
batch+0.845
 Koen+0.825
KC+0.824
akin+0.772
Neg logit contributions
owler-0.993
ynes-0.963
perty-0.908
perse-0.858
gow-0.854
Token65
Token ID2996
Feature activation-9.85e-02

Pos logit contributions
owler+0.321
ynes+0.309
perty+0.287
gow+0.282
perse+0.279
Neg logit contributions
CLASSIFIED-0.253
batch-0.231
KC-0.225
 Koen-0.225
akin-0.220
Token Posts
Token ID12043
Feature activation-8.49e-01

Pos logit contributions
CLASSIFIED+0.264
batch+0.247
 Koen+0.243
KC+0.240
akin+0.228
Neg logit contributions
owler-0.264
ynes-0.256
perty-0.233
gow-0.227
perse-0.226
Token #
Token ID1303
Feature activation-9.16e-01

Pos logit contributions
CLASSIFIED+2.136
 Koen+2.108
batch+2.041
KC+2.001
 Rim+1.979
Neg logit contributions
owler-2.393
ynes-2.321
perty-2.166
perse-2.048
gow-2.021
Token13
Token ID1485
Feature activation+9.09e-02

Pos logit contributions
CLASSIFIED+2.210
 Koen+2.108
batch+2.050
KC+2.020
 Rim+1.958
Neg logit contributions
owler-2.743
ynes-2.638
perty-2.494
perse-2.366
gow-2.353
Token On
Token ID1550
Feature activation-4.44e-01

Pos logit contributions
owler+0.268
ynes+0.258
perty+0.245
perse+0.232
gow+0.228
Neg logit contributions
CLASSIFIED-0.221
batch-0.208
KC-0.200
 Koen-0.199
 Rim-0.187
Token September
Token ID2693
Feature activation-2.75e-01

Pos logit contributions
CLASSIFIED+1.232
batch+1.165
KC+1.153
 Koen+1.152
 Dion+1.090
Neg logit contributions
owler-1.165
ynes-1.108
perty-1.058
gow-0.991
apesh-0.968
Token 20
Token ID1160
Feature activation-2.91e-01

Pos logit contributions
CLASSIFIED+0.660
 Koen+0.627
batch+0.627
KC+0.616
 Rim+0.589
Neg logit contributions
owler-0.818
ynes-0.791
perty-0.748
perse-0.707
gow-0.696
Token 2013
Token ID2211
Feature activation-4.99e-01

Pos logit contributions
CLASSIFIED+0.686
batch+0.630
 Koen+0.621
KC+0.613
 Kenn+0.580
Neg logit contributions
owler-0.890
ynes-0.854
perty-0.800
gow-0.771
perse-0.767
Token is
Token ID318
Feature activation+7.20e-02

Pos logit contributions
owler+0.792
ynes+0.768
perty+0.696
gow+0.670
perse+0.667
Neg logit contributions
CLASSIFIED-0.768
batch-0.715
KC-0.711
 Koen-0.700
 Rim-0.669
Token a
Token ID257
Feature activation+9.18e-02

Pos logit contributions
owler+0.186
ynes+0.174
perty+0.167
perse+0.156
gow+0.151
Neg logit contributions
CLASSIFIED-0.200
batch-0.189
KC-0.189
 Koen-0.186
 Organisation-0.180
Token quick
Token ID2068
Feature activation+1.38e-02

Pos logit contributions
owler+0.243
ynes+0.232
perty+0.214
perse+0.199
gow+0.195
Neg logit contributions
CLASSIFIED-0.254
batch-0.243
 Koen-0.237
KC-0.235
 Parties-0.228
Token and
Token ID290
Feature activation+8.60e-02

Pos logit contributions
owler+0.037
ynes+0.035
perty+0.032
gow+0.030
apesh+0.029
Neg logit contributions
CLASSIFIED-0.039
KC-0.037
 Koen-0.036
 Parties-0.035
batch-0.035
Token fast
Token ID3049
Feature activation-2.37e-01

Pos logit contributions
owler+0.217
ynes+0.206
perty+0.196
gow+0.179
apesh+0.178
Neg logit contributions
CLASSIFIED-0.255
batch-0.234
KC-0.232
 Koen-0.230
 Organisation-0.223
Token slot
Token ID10852
Feature activation+6.94e-01

Pos logit contributions
CLASSIFIED+0.652
KC+0.610
 Koen+0.597
batch+0.592
 Parties+0.583
Neg logit contributions
owler-0.660
ynes-0.620
perty-0.559
gow-0.538
apesh-0.524
Token receiver
Token ID9733
Feature activation-1.84e-01

Pos logit contributions
owler+2.029
ynes+1.788
perty+1.668
gow+1.574
apesh+1.557
Neg logit contributions
CLASSIFIED-1.812
batch-1.665
KC-1.662
 Koen-1.634
 Parties-1.613
Token who
Token ID508
Feature activation+4.76e-02

Pos logit contributions
CLASSIFIED+0.503
batch+0.458
KC+0.456
 Koen+0.449
 Parties+0.438
Neg logit contributions
owler-0.517
ynes-0.475
perty-0.453
gow-0.423
perse-0.420
Token was
Token ID373
Feature activation-6.99e-02

Pos logit contributions
owler+0.133
ynes+0.125
perty+0.117
gow+0.111
perse+0.110
Neg logit contributions
CLASSIFIED-0.129
batch-0.117
KC-0.116
 Koen-0.115
 Organisation-0.111
Token also
Token ID635
Feature activation+2.63e-02

Pos logit contributions
CLASSIFIED+0.194
batch+0.183
KC+0.182
 Koen+0.179
 Organisation+0.171
Neg logit contributions
owler-0.183
ynes-0.170
perty-0.167
apesh-0.152
perse-0.151
Token pursued
Token ID19189
Feature activation+8.04e-02

Pos logit contributions
owler+0.069
ynes+0.064
perty+0.062
perse+0.057
apesh+0.057
Neg logit contributions
CLASSIFIED-0.073
batch-0.069
KC-0.068
 Koen-0.067
 Organisation-0.065
Token the
Token ID262
Feature activation-4.41e-02

Pos logit contributions
CLASSIFIED+0.695
batch+0.660
 Koen+0.654
KC+0.645
 Organisation+0.613
Neg logit contributions
owler-0.652
ynes-0.625
perty-0.580
perse-0.563
gow-0.544
Token J
Token ID449
Feature activation-1.59e-01

Pos logit contributions
CLASSIFIED+0.117
batch+0.110
 Koen+0.108
KC+0.107
 Organisation+0.101
Neg logit contributions
owler-0.120
ynes-0.115
perty-0.106
perse-0.102
gow-0.101
Token on
Token ID319
Feature activation-8.85e-02

Pos logit contributions
CLASSIFIED+0.406
 Koen+0.392
batch+0.387
KC+0.378
 Rim+0.368
Neg logit contributions
owler-0.447
ynes-0.434
perty-0.404
perse-0.381
gow-0.377
Token their
Token ID511
Feature activation-2.39e-01

Pos logit contributions
CLASSIFIED+0.153
batch+0.146
 Koen+0.135
KC+0.135
 Organisation+0.132
Neg logit contributions
owler-0.317
ynes-0.309
perty-0.292
 Scrib-0.282
perse-0.280
Token entire
Token ID2104
Feature activation-2.62e-01

Pos logit contributions
CLASSIFIED+0.634
batch+0.593
 Koen+0.578
KC+0.571
 Organisation+0.548
Neg logit contributions
owler-0.652
ynes-0.644
perty-0.593
perse-0.559
apesh-0.555
Token stretch
Token ID7539
Feature activation+5.73e-01

Pos logit contributions
CLASSIFIED+0.728
batch+0.682
 Koen+0.662
KC+0.654
 Organisation+0.629
Neg logit contributions
owler-0.685
ynes-0.671
perty-0.623
gow-0.585
perse-0.581
Token,
Token ID11
Feature activation+5.78e-02

Pos logit contributions
owler+1.510
ynes+1.488
perty+1.353
gow+1.280
perse+1.276
Neg logit contributions
CLASSIFIED-1.552
batch-1.476
 Koen-1.430
KC-1.412
 Organisation-1.357
Token and
Token ID290
Feature activation-6.19e-02

Pos logit contributions
owler+0.144
ynes+0.137
perty+0.125
perse+0.116
gow+0.115
Neg logit contributions
CLASSIFIED-0.168
batch-0.162
 Koen-0.161
KC-0.157
 Organisation-0.153
Token one
Token ID530
Feature activation-1.30e-01

Pos logit contributions
CLASSIFIED+0.171
batch+0.161
 Koen+0.157
KC+0.155
 Organisation+0.152
Neg logit contributions
owler-0.167
ynes-0.159
perty-0.145
gow-0.139
perse-0.138
Token of
Token ID286
Feature activation-6.37e-02

Pos logit contributions
CLASSIFIED+0.340
batch+0.321
 Koen+0.311
KC+0.306
 Organisation+0.293
Neg logit contributions
owler-0.371
ynes-0.357
perty-0.334
perse-0.315
gow-0.312
Token the
Token ID262
Feature activation+4.23e-02

Pos logit contributions
CLASSIFIED+0.170
batch+0.163
 Koen+0.161
KC+0.159
 Organisation+0.155
Neg logit contributions
owler-0.172
ynes-0.163
perty-0.154
perse-0.146
gow-0.142
Token,
Token ID11
Feature activation+9.13e-02

Pos logit contributions
owler+0.304
ynes+0.295
perty+0.272
gow+0.263
perse+0.253
Neg logit contributions
CLASSIFIED-0.315
KC-0.291
 Koen-0.289
batch-0.288
 Organisation-0.272
Token the
Token ID262
Feature activation+8.36e-02

Pos logit contributions
owler+0.247
ynes+0.237
perty+0.221
perse+0.209
gow+0.208
Neg logit contributions
CLASSIFIED-0.248
batch-0.229
 Koen-0.225
KC-0.223
 Parties-0.210
Token first
Token ID717
Feature activation+4.22e-02

Pos logit contributions
owler+0.227
ynes+0.217
perty+0.206
gow+0.194
perse+0.189
Neg logit contributions
CLASSIFIED-0.227
batch-0.209
 Koen-0.208
KC-0.204
akin-0.193
Token African
Token ID5510
Feature activation+4.79e-01

Pos logit contributions
owler+0.070
ynes+0.067
perty+0.060
gow+0.054
perse+0.052
Neg logit contributions
CLASSIFIED-0.157
 Koen-0.150
batch-0.149
KC-0.148
 Parties-0.143
Token-
Token ID12
Feature activation-9.11e-02

Pos logit contributions
owler+1.144
ynes+1.108
perty+1.028
gow+0.952
perse+0.943
Neg logit contributions
CLASSIFIED-1.406
 Koen-1.361
batch-1.343
KC-1.332
 Kenn-1.258
TokenAmerican
Token ID7437
Feature activation+5.19e-01

Pos logit contributions
CLASSIFIED+0.309
 Koen+0.308
batch+0.295
KC+0.293
 Dion+0.287
Neg logit contributions
owler-0.177
ynes-0.172
perty-0.148
perse-0.142
gow-0.140
Token woman
Token ID2415
Feature activation+2.30e-01

Pos logit contributions
owler+1.283
ynes+1.237
perty+1.167
gow+1.099
perse+1.062
Neg logit contributions
CLASSIFIED-1.512
batch-1.391
 Koen-1.389
KC-1.362
 Parties-1.302
Token elected
Token ID7018
Feature activation+3.17e-02

Pos logit contributions
owler+0.579
ynes+0.555
perty+0.521
gow+0.490
perse+0.481
Neg logit contributions
CLASSIFIED-0.664
 Koen-0.615
batch-0.614
KC-0.601
 Rim-0.575
Token to
Token ID284
Feature activation+1.18e-01

Pos logit contributions
owler+0.081
ynes+0.078
perty+0.074
gow+0.070
perse+0.069
Neg logit contributions
CLASSIFIED-0.089
 Koen-0.086
batch-0.084
KC-0.081
 Parties-0.079
Token Congress
Token ID3162
Feature activation+1.07e-01

Pos logit contributions
owler+0.309
ynes+0.293
perty+0.280
perse+0.263
gow+0.260
Neg logit contributions
CLASSIFIED-0.328
batch-0.313
 Koen-0.310
KC-0.298
 Rim-0.289
Token.[
Token ID3693
Feature activation-2.83e-01

Pos logit contributions
owler+0.252
ynes+0.247
perty+0.231
gow+0.216
perse+0.212
Neg logit contributions
CLASSIFIED-0.325
 Koen-0.305
batch-0.304
KC-0.302
 Rim-0.286
Tokenitions
Token ID1756
Feature activation-1.01e-01

Pos logit contributions
CLASSIFIED+0.633
 Koen+0.614
batch+0.596
KC+0.589
 Organisation+0.565
Neg logit contributions
ynes-0.678
owler-0.674
perty-0.614
perse-0.582
gow-0.578
Token of
Token ID286
Feature activation-8.47e-02

Pos logit contributions
CLASSIFIED+0.275
batch+0.258
 Koen+0.252
KC+0.252
 Rim+0.243
Neg logit contributions
owler-0.268
ynes-0.260
perty-0.245
gow-0.228
perse-0.227
Token any
Token ID597
Feature activation-1.95e-01

Pos logit contributions
CLASSIFIED+0.229
batch+0.219
 Koen+0.216
KC+0.216
 Rim+0.206
Neg logit contributions
owler-0.227
ynes-0.213
perty-0.204
perse-0.192
apesh-0.186
Token deal
Token ID1730
Feature activation+1.09e-01

Pos logit contributions
CLASSIFIED+0.554
batch+0.530
 Koen+0.522
KC+0.519
 Rim+0.489
Neg logit contributions
owler-0.499
ynes-0.477
perty-0.444
gow-0.419
perse-0.411
Token to
Token ID284
Feature activation-2.48e-01

Pos logit contributions
owler+0.285
ynes+0.278
perty+0.258
apesh+0.240
perse+0.240
Neg logit contributions
CLASSIFIED-0.297
batch-0.290
KC-0.276
 Koen-0.268
 Rim-0.259
Token save
Token ID3613
Feature activation+4.47e-01

Pos logit contributions
CLASSIFIED+0.752
 Koen+0.708
batch+0.707
KC+0.689
 Rim+0.667
Neg logit contributions
owler-0.587
ynes-0.572
perty-0.525
perse-0.495
gow-0.487
Token the
Token ID262
Feature activation-1.74e-01

Pos logit contributions
owler+1.090
ynes+1.050
perty+0.967
perse+0.885
apesh+0.871
Neg logit contributions
CLASSIFIED-1.292
batch-1.232
 Koen-1.232
KC-1.222
 Organisation-1.164
Token Def
Token ID2896
Feature activation+1.13e-01

Pos logit contributions
CLASSIFIED+0.533
batch+0.506
 Koen+0.501
KC+0.497
 Rim+0.468
Neg logit contributions
owler-0.414
ynes-0.392
perty-0.365
perse-0.332
gow-0.329
Tokenerred
Token ID17436
Feature activation+3.46e-01

Pos logit contributions
owler+0.266
ynes+0.251
perty+0.215
gow+0.209
har+0.204
Neg logit contributions
CLASSIFIED-0.357
batch-0.340
 Koen-0.335
KC-0.330
 Kenn-0.327
Token Action
Token ID7561
Feature activation-3.35e-01

Pos logit contributions
owler+0.973
ynes+0.910
perty+0.830
 Scrib+0.794
har+0.792
Neg logit contributions
CLASSIFIED-0.876
KC-0.856
batch-0.841
 Koen-0.834
akin-0.784
Token for
Token ID329
Feature activation+5.68e-02

Pos logit contributions
CLASSIFIED+0.886
 Koen+0.840
batch+0.836
KC+0.834
 Rim+0.785
Neg logit contributions
owler-0.919
ynes-0.887
perty-0.826
perse-0.763
gow-0.751
Token explains
Token ID6688
Feature activation-3.49e-01

Pos logit contributions
owler+0.071
ynes+0.070
perty+0.065
perse+0.063
gow+0.062
Neg logit contributions
CLASSIFIED-0.044
batch-0.040
 Koen-0.040
KC-0.039
 Rim-0.037
Token.
Token ID13
Feature activation-3.35e-04

Pos logit contributions
CLASSIFIED+0.843
 Koen+0.813
batch+0.802
KC+0.787
 Rim+0.761
Neg logit contributions
owler-1.028
ynes-0.996
perty-0.942
perse-0.885
gow-0.876
Token
Token ID198
Feature activation+1.60e-01

Pos logit contributions
CLASSIFIED+0.001
batch+0.001
 Koen+0.001
KC+0.001
 flavours+0.001
Neg logit contributions
owler-0.001
ynes-0.001
perty-0.001
gow-0.001
perse-0.001
Token
Token ID198
Feature activation+1.19e-01

Pos logit contributions
owler+0.330
ynes+0.319
perse+0.272
gow+0.272
perty+0.265
Neg logit contributions
CLASSIFIED-0.551
 Koen-0.504
batch-0.490
KC-0.486
 Ezek-0.481
TokenSetting
Token ID34149
Feature activation+1.23e-02

Pos logit contributions
owler+0.283
ynes+0.273
perty+0.247
gow+0.238
perse+0.234
Neg logit contributions
 Koen-0.351
CLASSIFIED-0.350
batch-0.329
 Ezek-0.327
 Kenn-0.327
Token aside
Token ID7263
Feature activation+4.90e-01

Pos logit contributions
owler+0.032
ynes+0.031
perty+0.028
gow+0.027
apesh+0.026
Neg logit contributions
CLASSIFIED-0.034
KC-0.033
 Koen-0.032
batch-0.032
 Kenn-0.030
Token the
Token ID262
Feature activation+1.27e-01

Pos logit contributions
owler+1.273
ynes+1.202
perty+1.145
perse+1.051
gow+1.050
Neg logit contributions
CLASSIFIED-1.376
KC-1.300
batch-1.273
 Koen-1.266
 Organisation-1.206
Token drama
Token ID10512
Feature activation+1.02e-01

Pos logit contributions
owler+0.339
ynes+0.323
perty+0.305
gow+0.278
apesh+0.275
Neg logit contributions
CLASSIFIED-0.352
KC-0.329
batch-0.328
 Koen-0.324
 Organisation-0.302
Token of
Token ID286
Feature activation+2.91e-02

Pos logit contributions
owler+0.278
ynes+0.273
perty+0.251
perse+0.235
gow+0.233
Neg logit contributions
CLASSIFIED-0.270
batch-0.255
 Koen-0.252
KC-0.250
 Organisation-0.239
Token tsun
Token ID28798
Feature activation+7.60e-02

Pos logit contributions
owler+0.078
ynes+0.074
perty+0.071
perse+0.066
apesh+0.064
Neg logit contributions
CLASSIFIED-0.079
KC-0.075
 Koen-0.075
batch-0.073
 Organisation-0.070
Tokenam
Token ID321
Feature activation+4.19e-02

Pos logit contributions
owler+0.170
ynes+0.165
perty+0.150
apesh+0.139
perse+0.135
Neg logit contributions
CLASSIFIED-0.249
 Koen-0.237
KC-0.229
batch-0.228
 Organisation-0.221
Token |
Token ID930
Feature activation-1.33e-01

Pos logit contributions
CLASSIFIED+0.503
 Koen+0.477
batch+0.470
KC+0.458
 Rim+0.447
Neg logit contributions
owler-0.532
ynes-0.518
perty-0.475
perse-0.453
gow-0.438
Token prev
Token ID8654
Feature activation+7.57e-02

Pos logit contributions
CLASSIFIED+0.366
 Koen+0.347
batch+0.346
KC+0.343
 Rim+0.328
Neg logit contributions
owler-0.351
ynes-0.337
perty-0.311
perse-0.292
apesh-0.283
Token_
Token ID62
Feature activation-3.24e-01

Pos logit contributions
owler+0.196
ynes+0.189
perty+0.176
perse+0.165
gow+0.162
Neg logit contributions
CLASSIFIED-0.211
 Koen-0.204
batch-0.200
KC-0.198
 Rim-0.192
Tokenstate
Token ID5219
Feature activation+1.60e-01

Pos logit contributions
CLASSIFIED+1.094
 Koen+1.066
KC+1.028
batch+1.020
 Rim+1.009
Neg logit contributions
owler-0.656
ynes-0.632
perty-0.576
perse-0.531
gow-0.521
Token:
Token ID25
Feature activation-2.51e-01

Pos logit contributions
owler+0.435
ynes+0.424
perty+0.394
perse+0.371
gow+0.359
Neg logit contributions
CLASSIFIED-0.417
 Koen-0.397
batch-0.393
KC-0.385
 Rim-0.376
Token Option
Token ID16018
Feature activation+1.27e-01

Pos logit contributions
CLASSIFIED+0.564
batch+0.520
 Koen+0.519
KC+0.516
 Dion+0.485
Neg logit contributions
owler-0.794
ynes-0.762
perty-0.723
perse-0.679
gow-0.672
Token<
Token ID27
Feature activation+4.21e-01

Pos logit contributions
owler+0.337
ynes+0.326
perty+0.306
perse+0.286
gow+0.281
Neg logit contributions
CLASSIFIED-0.341
 Koen-0.330
batch-0.325
KC-0.320
 Rim-0.310
TokenBoard
Token ID29828
Feature activation+2.37e-01

Pos logit contributions
owler+1.054
ynes+1.007
perty+0.943
perse+0.866
gow+0.854
Neg logit contributions
CLASSIFIED-1.191
 Koen-1.131
batch-1.112
KC-1.098
 Bened-1.073
Token>,
Token ID22330
Feature activation+3.00e-01

Pos logit contributions
owler+0.699
ynes+0.673
perty+0.642
perse+0.603
gow+0.592
Neg logit contributions
CLASSIFIED-0.562
 Koen-0.541
batch-0.535
KC-0.523
 Dion-0.501
Token //
Token ID3373
Feature activation-4.48e-01

Pos logit contributions
owler+0.729
ynes+0.691
perty+0.629
perse+0.593
gow+0.576
Neg logit contributions
CLASSIFIED-0.875
 Koen-0.833
batch-0.820
KC-0.817
 Rim-0.785
Token The
Token ID383
Feature activation+3.12e-01

Pos logit contributions
CLASSIFIED+1.122
 Koen+1.067
KC+1.057
batch+1.055
 Rim+0.998
Neg logit contributions
owler-1.293
ynes-1.232
perty-1.160
perse-1.086
gow-1.077
Token also
Token ID635
Feature activation+1.03e-01

Pos logit contributions
CLASSIFIED+0.014
 Koen+0.013
KC+0.013
batch+0.013
 Rim+0.012
Neg logit contributions
owler-0.011
ynes-0.011
perty-0.010
perse-0.009
gow-0.009
Token let
Token ID1309
Feature activation+2.38e-01

Pos logit contributions
owler+0.243
ynes+0.229
perty+0.209
perse+0.202
gow+0.201
Neg logit contributions
CLASSIFIED-0.326
 Koen-0.301
batch-0.298
KC-0.297
 Rim-0.287
Token you
Token ID345
Feature activation-2.29e-01

Pos logit contributions
owler+0.662
ynes+0.626
perty+0.586
apesh+0.544
perse+0.543
Neg logit contributions
CLASSIFIED-0.627
batch-0.591
 Koen-0.582
KC-0.581
 Kenn-0.547
Token see
Token ID766
Feature activation-1.69e-01

Pos logit contributions
CLASSIFIED+0.695
 Koen+0.652
batch+0.643
KC+0.640
 Rim+0.614
Neg logit contributions
owler-0.557
ynes-0.536
perty-0.493
gow-0.464
perse-0.459
Token if
Token ID611
Feature activation+1.23e-01

Pos logit contributions
CLASSIFIED+0.442
 Koen+0.408
batch+0.406
KC+0.405
 Rim+0.378
Neg logit contributions
owler-0.478
ynes-0.453
perty-0.424
perse-0.404
gow-0.400
Token something
Token ID1223
Feature activation+3.53e-02

Pos logit contributions
owler+0.319
ynes+0.303
perty+0.282
perse+0.265
gow+0.264
Neg logit contributions
CLASSIFIED-0.345
batch-0.328
KC-0.320
 Koen-0.319
 Organisation-0.299
Token is
Token ID318
Feature activation+4.55e-02

Pos logit contributions
owler+0.098
ynes+0.095
perty+0.087
gow+0.083
apesh+0.082
Neg logit contributions
CLASSIFIED-0.094
batch-0.087
 Koen-0.085
KC-0.084
 Kenn-0.080
Token biased
Token ID21925
Feature activation-2.64e-01

Pos logit contributions
owler+0.116
ynes+0.112
perty+0.104
perse+0.096
gow+0.096
Neg logit contributions
CLASSIFIED-0.128
batch-0.123
 Koen-0.120
KC-0.119
 Rim-0.113
Token or
Token ID393
Feature activation+1.08e-01

Pos logit contributions
CLASSIFIED+0.724
batch+0.674
 Koen+0.674
KC+0.670
 Rim+0.630
Neg logit contributions
owler-0.715
ynes-0.694
perty-0.639
apesh-0.604
perse-0.601
Token even
Token ID772
Feature activation-1.26e-01

Pos logit contributions
owler+0.276
ynes+0.261
perty+0.234
perse+0.228
gow+0.224
Neg logit contributions
CLASSIFIED-0.310
batch-0.295
KC-0.290
 Koen-0.289
 Rim-0.276
Token just
Token ID655
Feature activation+2.25e-01

Pos logit contributions
CLASSIFIED+0.377
batch+0.360
KC+0.352
 Koen+0.351
 Rim+0.336
Neg logit contributions
owler-0.305
ynes-0.293
perty-0.263
perse-0.252
gow-0.248
Token
Token ID198
Feature activation+2.82e-02

Pos logit contributions
owler+0.122
ynes+0.117
perty+0.109
perse+0.100
gow+0.100
Neg logit contributions
CLASSIFIED-0.156
batch-0.149
 Koen-0.146
KC-0.145
 Rim-0.138
Token
Token ID198
Feature activation-9.29e-03

Pos logit contributions
owler+0.061
ynes+0.059
perty+0.051
perse+0.050
gow+0.050
Neg logit contributions
CLASSIFIED-0.093
 Koen-0.086
batch-0.084
KC-0.083
 Ezek-0.081
TokenV
Token ID53
Feature activation-1.43e-02

Pos logit contributions
CLASSIFIED+0.024
 Koen+0.024
batch+0.023
 Rim+0.022
 Kenn+0.022
Neg logit contributions
owler-0.025
ynes-0.025
perty-0.023
gow-0.022
perse-0.022
Tokenad
Token ID324
Feature activation+4.58e-01

Pos logit contributions
CLASSIFIED+0.040
batch+0.038
 Koen+0.038
 Organisation+0.036
 Parties+0.036
Neg logit contributions
owler-0.038
ynes-0.037
perty-0.034
apesh-0.031
gow-0.031
Tokenim
Token ID320
Feature activation+3.09e-01

Pos logit contributions
owler+1.266
ynes+1.243
perty+1.144
har+1.099
apesh+1.070
Neg logit contributions
CLASSIFIED-1.282
 Koen-1.145
KC-1.129
batch-1.102
 Kenn-1.067
Token And
Token ID843
Feature activation+1.71e-01

Pos logit contributions
owler+0.928
ynes+0.889
perty+0.867
gow+0.814
perse+0.793
Neg logit contributions
CLASSIFIED-0.737
 Koen-0.683
batch-0.680
KC-0.680
 Kenn-0.626
Tokenrey
Token ID4364
Feature activation+2.82e-01

Pos logit contributions
owler+0.423
ynes+0.407
perty+0.374
gow+0.361
har+0.346
Neg logit contributions
CLASSIFIED-0.525
 Koen-0.489
batch-0.468
KC-0.466
 Kenn-0.460
Tokenuk
Token ID2724
Feature activation+1.47e-01

Pos logit contributions
owler+0.739
ynes+0.722
gow+0.646
perty+0.641
har+0.609
Neg logit contributions
CLASSIFIED-0.854
 Koen-0.746
 Rim-0.717
batch-0.716
KC-0.715
Token,
Token ID11
Feature activation+1.34e-01

Pos logit contributions
owler+0.398
ynes+0.396
perty+0.367
gow+0.345
apesh+0.341
Neg logit contributions
CLASSIFIED-0.382
 Koen-0.362
batch-0.357
KC-0.354
 Rim-0.340
Token owner
Token ID4870
Feature activation+1.21e-01

Pos logit contributions
owler+0.357
ynes+0.351
perty+0.334
apesh+0.302
gow+0.302
Neg logit contributions
CLASSIFIED-0.362
batch-0.339
 Koen-0.330
KC-0.327
 Rim-0.310
Token of
Token ID286
Feature activation+6.33e-02

Pos logit contributions
owler+0.391
ynes+0.381
perty+0.362
perse+0.342
gow+0.339
Neg logit contributions
CLASSIFIED-0.258
 Koen-0.247
batch-0.244
KC-0.238
 Rim-0.229
Token on
Token ID319
Feature activation+5.81e-02

Pos logit contributions
owler+0.222
ynes+0.213
perty+0.200
perse+0.189
apesh+0.187
Neg logit contributions
CLASSIFIED-0.222
batch-0.211
 Koen-0.210
KC-0.208
 Rim-0.196
Token his
Token ID465
Feature activation+1.29e-01

Pos logit contributions
owler+0.147
ynes+0.139
perty+0.133
perse+0.122
gow+0.119
Neg logit contributions
CLASSIFIED-0.163
batch-0.159
KC-0.155
 Koen-0.155
 Parties-0.146
Token own
Token ID898
Feature activation+7.76e-02

Pos logit contributions
owler+0.303
ynes+0.301
perty+0.282
perse+0.254
apesh+0.251
Neg logit contributions
CLASSIFIED-0.379
batch-0.373
 Koen-0.362
KC-0.360
 Bened-0.340
Token.
Token ID13
Feature activation-8.82e-02

Pos logit contributions
owler+0.202
ynes+0.193
perty+0.185
perse+0.171
apesh+0.166
Neg logit contributions
CLASSIFIED-0.209
batch-0.205
 Koen-0.201
KC-0.197
 Rim-0.188
Token We
Token ID775
Feature activation-1.01e-01

Pos logit contributions
CLASSIFIED+0.237
batch+0.226
KC+0.216
 Koen+0.216
 flavours+0.208
Neg logit contributions
owler-0.232
ynes-0.222
perty-0.209
gow-0.198
perse-0.195
Token taught
Token ID7817
Feature activation+3.00e-01

Pos logit contributions
CLASSIFIED+0.267
 Koen+0.247
batch+0.246
KC+0.242
 Rim+0.231
Neg logit contributions
owler-0.288
ynes-0.277
perty-0.260
gow-0.244
perse-0.244
Token him
Token ID683
Feature activation+9.20e-02

Pos logit contributions
owler+0.685
ynes+0.662
perty+0.626
perse+0.562
gow+0.552
Neg logit contributions
CLASSIFIED-0.917
batch-0.881
 Koen-0.855
KC-0.848
 Organisation-0.810
Token how
Token ID703
Feature activation+1.53e-01

Pos logit contributions
owler+0.241
ynes+0.234
perty+0.223
perse+0.205
gow+0.202
Neg logit contributions
CLASSIFIED-0.251
batch-0.238
 Koen-0.235
KC-0.232
 Rim-0.219
Token to
Token ID284
Feature activation+2.57e-01

Pos logit contributions
owler+0.427
ynes+0.414
perty+0.394
perse+0.367
gow+0.363
Neg logit contributions
CLASSIFIED-0.393
 Koen-0.379
batch-0.377
KC-0.369
 Rim-0.355
Token ask
Token ID1265
Feature activation+2.99e-01

Pos logit contributions
owler+0.594
ynes+0.568
perty+0.526
perse+0.497
gow+0.493
Neg logit contributions
CLASSIFIED-0.799
 Koen-0.751
batch-0.744
KC-0.725
 Bened-0.699
Token for
Token ID329
Feature activation-2.21e-01

Pos logit contributions
owler+0.774
ynes+0.761
perty+0.731
perse+0.683
apesh+0.669
Neg logit contributions
CLASSIFIED-0.804
batch-0.773
KC-0.739
 Koen-0.737
 Rim-0.696
Token who
Token ID508
Feature activation-4.82e-03

Pos logit contributions
owler+0.259
ynes+0.242
perty+0.235
perse+0.219
gow+0.209
Neg logit contributions
CLASSIFIED-0.239
batch-0.232
KC-0.218
 Koen-0.216
 Parties-0.210
Token allowed
Token ID3142
Feature activation+7.38e-02

Pos logit contributions
CLASSIFIED+0.013
batch+0.012
 Koen+0.011
KC+0.011
 Organisation+0.011
Neg logit contributions
owler-0.014
ynes-0.013
perty-0.012
gow-0.011
perse-0.011
Token just
Token ID655
Feature activation+4.83e-03

Pos logit contributions
owler+0.189
ynes+0.183
perty+0.172
perse+0.159
gow+0.155
Neg logit contributions
CLASSIFIED-0.213
batch-0.198
KC-0.191
 Koen-0.190
 Parties-0.184
Token two
Token ID734
Feature activation-3.12e-01

Pos logit contributions
owler+0.012
ynes+0.012
perty+0.011
perse+0.010
gow+0.010
Neg logit contributions
CLASSIFIED-0.014
batch-0.013
KC-0.013
 Koen-0.012
 Organisation-0.012
Token receptions
Token ID35401
Feature activation-9.01e-02

Pos logit contributions
CLASSIFIED+0.742
batch+0.695
 Koen+0.683
KC+0.660
 Rim+0.638
Neg logit contributions
owler-0.955
ynes-0.924
perty-0.886
gow-0.819
perse-0.816
Token for
Token ID329
Feature activation+3.77e-02

Pos logit contributions
CLASSIFIED+0.249
batch+0.232
 Koen+0.227
KC+0.225
 Rim+0.217
Neg logit contributions
owler-0.241
ynes-0.230
perty-0.223
gow-0.203
perse-0.203
Token 11
Token ID1367
Feature activation-2.43e-01

Pos logit contributions
owler+0.105
ynes+0.100
perty+0.095
perse+0.088
gow+0.088
Neg logit contributions
CLASSIFIED-0.101
batch-0.093
 Koen-0.090
KC-0.089
 Parties-0.085
Token yards
Token ID5695
Feature activation-2.92e-01

Pos logit contributions
CLASSIFIED+0.555
batch+0.520
 Koen+0.518
KC+0.487
 Parties+0.478
Neg logit contributions
owler-0.760
ynes-0.739
perty-0.698
gow-0.653
perse-0.651
Token vs
Token ID3691
Feature activation+8.85e-03

Pos logit contributions
CLASSIFIED+0.796
 Koen+0.741
batch+0.738
KC+0.730
 Organisation+0.700
Neg logit contributions
owler-0.798
ynes-0.760
perty-0.733
apesh-0.671
perse-0.670
Token.
Token ID13
Feature activation-4.66e-02

Pos logit contributions
owler+0.025
ynes+0.024
perty+0.023
perse+0.022
gow+0.021
Neg logit contributions
CLASSIFIED-0.022
batch-0.021
 Koen-0.021
KC-0.021
 Rim-0.020
Token Seattle
Token ID7312
Feature activation-6.89e-02

Pos logit contributions
CLASSIFIED+0.127
batch+0.122
 Koen+0.113
KC+0.111
 Parties+0.109
Neg logit contributions
owler-0.126
ynes-0.119
perty-0.112
perse-0.105
apesh-0.104
Token jointly
Token ID26913
Feature activation-2.95e-02

Pos logit contributions
owler+0.276
ynes+0.271
perty+0.257
gow+0.244
apesh+0.242
Neg logit contributions
CLASSIFIED-0.292
batch-0.263
 Koen-0.258
KC-0.257
 Rim-0.241
Token owns
Token ID12216
Feature activation+4.72e-02

Pos logit contributions
CLASSIFIED+0.083
batch+0.075
KC+0.074
 Koen+0.073
 Rim+0.069
Neg logit contributions
owler-0.078
ynes-0.075
perty-0.072
gow-0.068
apesh-0.067
Token four
Token ID1440
Feature activation-6.79e-02

Pos logit contributions
owler+0.124
ynes+0.122
perty+0.117
gow+0.106
perse+0.105
Neg logit contributions
CLASSIFIED-0.129
batch-0.123
KC-0.118
 Koen-0.116
 Kenn-0.109
Token numbered
Token ID25840
Feature activation-1.61e-01

Pos logit contributions
CLASSIFIED+0.179
batch+0.167
KC+0.159
 Koen+0.159
 Parties+0.150
Neg logit contributions
owler-0.185
ynes-0.184
perty-0.175
gow-0.160
apesh-0.158
Token Ontario
Token ID10553
Feature activation-2.39e-01

Pos logit contributions
CLASSIFIED+0.425
batch+0.400
KC+0.382
 Koen+0.381
 Organisation+0.356
Neg logit contributions
owler-0.441
ynes-0.425
perty-0.412
gow-0.376
perse-0.373
Token real
Token ID1103
Feature activation-4.50e-01

Pos logit contributions
CLASSIFIED+0.606
batch+0.572
 Koen+0.563
KC+0.553
 Rim+0.519
Neg logit contributions
owler-0.674
ynes-0.654
perty-0.625
gow-0.576
apesh-0.565
Token estate
Token ID7964
Feature activation+8.79e-02

Pos logit contributions
CLASSIFIED+1.198
batch+1.128
 Koen+1.115
KC+1.090
 Rim+1.056
Neg logit contributions
owler-1.244
ynes-1.217
perty-1.155
gow-1.084
apesh-1.061
Token holding
Token ID4769
Feature activation-2.60e-01

Pos logit contributions
owler+0.225
ynes+0.220
perty+0.212
gow+0.201
apesh+0.198
Neg logit contributions
CLASSIFIED-0.246
batch-0.223
 Koen-0.217
KC-0.213
20439-0.201
Token companies
Token ID2706
Feature activation-3.09e-01

Pos logit contributions
CLASSIFIED+0.703
batch+0.653
 Koen+0.631
KC+0.621
 Kenn+0.589
Neg logit contributions
owler-0.692
ynes-0.672
perty-0.647
gow-0.603
apesh-0.593
Token with
Token ID351
Feature activation-7.53e-02

Pos logit contributions
CLASSIFIED+0.873
batch+0.815
 Koen+0.791
KC+0.775
 Kenn+0.738
Neg logit contributions
owler-0.795
ynes-0.778
perty-0.754
gow-0.684
apesh-0.678
Token his
Token ID465
Feature activation-4.65e-02

Pos logit contributions
CLASSIFIED+0.212
batch+0.195
KC+0.191
 Koen+0.189
 Parties+0.176
Neg logit contributions
owler-0.196
ynes-0.193
perty-0.184
gow-0.167
apesh-0.165
Token may
Token ID743
Feature activation-4.82e-01

Pos logit contributions
CLASSIFIED+0.363
batch+0.339
 Koen+0.338
KC+0.331
 Rim+0.315
Neg logit contributions
owler-0.415
ynes-0.406
perty-0.375
perse-0.355
gow-0.355
Token or
Token ID393
Feature activation-1.67e-01

Pos logit contributions
CLASSIFIED+1.411
 Koen+1.340
batch+1.325
KC+1.300
 Rim+1.255
Neg logit contributions
owler-1.208
ynes-1.172
perty-1.070
gow-1.026
perse-1.025
Token may
Token ID743
Feature activation-1.48e-01

Pos logit contributions
CLASSIFIED+0.461
 Koen+0.418
batch+0.417
KC+0.412
 Rim+0.396
Neg logit contributions
owler-0.462
ynes-0.455
perty-0.408
apesh-0.390
gow-0.389
Token not
Token ID407
Feature activation-1.09e-01

Pos logit contributions
CLASSIFIED+0.400
 Koen+0.372
batch+0.365
KC+0.357
 Rim+0.347
Neg logit contributions
owler-0.409
ynes-0.397
perty-0.356
perse-0.352
gow-0.351
Token have
Token ID423
Feature activation-8.45e-02

Pos logit contributions
CLASSIFIED+0.338
 Koen+0.318
batch+0.314
KC+0.310
 Organisation+0.299
Neg logit contributions
owler-0.258
ynes-0.253
perty-0.227
perse-0.216
gow-0.216
Token been
Token ID587
Feature activation-3.31e-01

Pos logit contributions
CLASSIFIED+0.233
batch+0.224
 Koen+0.221
KC+0.220
 Rim+0.209
Neg logit contributions
owler-0.220
ynes-0.212
perty-0.196
gow-0.184
perse-0.183
Token used
Token ID973
Feature activation-2.28e-01

Pos logit contributions
CLASSIFIED+0.834
batch+0.806
 Koen+0.790
KC+0.768
 Rim+0.741
Neg logit contributions
owler-0.935
ynes-0.911
perty-0.852
gow-0.808
apesh-0.808
Token before
Token ID878
Feature activation+1.32e-01

Pos logit contributions
CLASSIFIED+0.610
 Koen+0.586
batch+0.572
KC+0.570
 Rim+0.545
Neg logit contributions
ynes-0.611
owler-0.610
perty-0.564
perse-0.528
gow-0.526
Token
Token ID784
Feature activation-3.91e-02

Pos logit contributions
owler+0.338
ynes+0.331
perty+0.314
apesh+0.289
gow+0.285
Neg logit contributions
CLASSIFIED-0.367
 Koen-0.342
KC-0.341
batch-0.340
 Parties-0.318
Token and
Token ID290
Feature activation-9.19e-02

Pos logit contributions
CLASSIFIED+0.107
batch+0.101
KC+0.101
 Koen+0.101
 Rim+0.095
Neg logit contributions
owler-0.103
ynes-0.099
perty-0.093
perse-0.088
gow-0.087
Token change
Token ID1487
Feature activation-1.88e-02

Pos logit contributions
CLASSIFIED+0.273
batch+0.255
 Koen+0.255
KC+0.252
 Rim+0.239
Neg logit contributions
owler-0.225
ynes-0.216
perty-0.200
perse-0.192
gow-0.190
Tokenus
Token ID385
Feature activation+2.98e-01

Pos logit contributions
CLASSIFIED+0.098
 Koen+0.096
batch+0.090
 Kenn+0.089
 Bened+0.087
Neg logit contributions
owler-0.105
ynes-0.103
perty-0.094
gow-0.090
perse-0.089
Token/
Token ID14
Feature activation+2.41e-01

Pos logit contributions
owler+0.771
ynes+0.721
gow+0.673
perty+0.668
perse+0.651
Neg logit contributions
CLASSIFIED-0.839
 Koen-0.800
batch-0.760
KC-0.743
 Ezek-0.735
Tokenblog
Token ID14036
Feature activation+1.62e-01

Pos logit contributions
owler+0.656
ynes+0.614
perty+0.587
gow+0.562
perse+0.558
Neg logit contributions
CLASSIFIED-0.665
 Koen-0.650
 Rim-0.598
 Ezek-0.590
 Bened-0.587
Token/
Token ID14
Feature activation+2.05e-01

Pos logit contributions
owler+0.485
ynes+0.471
perty+0.445
perse+0.419
gow+0.416
Neg logit contributions
CLASSIFIED-0.387
 Koen-0.374
batch-0.362
KC-0.357
 Rim-0.347
Tokenpower
Token ID6477
Feature activation-2.49e-02

Pos logit contributions
owler+0.615
ynes+0.580
perty+0.562
gow+0.531
perse+0.530
Neg logit contributions
CLASSIFIED-0.502
 Koen-0.483
 Rim-0.444
KC-0.444
 Kenn-0.439
Token-
Token ID12
Feature activation-1.50e-01

Pos logit contributions
CLASSIFIED+0.064
 Koen+0.062
KC+0.060
batch+0.059
 Rim+0.058
Neg logit contributions
owler-0.070
ynes-0.068
perty-0.064
perse-0.060
gow-0.060
Tokenbi
Token ID8482
Feature activation-2.47e-01

Pos logit contributions
CLASSIFIED+0.371
 Koen+0.360
KC+0.342
 Rim+0.332
batch+0.331
Neg logit contributions
owler-0.445
ynes-0.430
perty-0.403
perse-0.382
gow-0.381
Token-
Token ID12
Feature activation-2.85e-01

Pos logit contributions
CLASSIFIED+0.642
 Koen+0.617
batch+0.602
KC+0.596
 Rim+0.577
Neg logit contributions
owler-0.694
ynes-0.667
perty-0.634
gow-0.589
perse-0.589
Tokendesktop
Token ID41375
Feature activation-2.18e-01

Pos logit contributions
CLASSIFIED+0.812
 Koen+0.786
KC+0.739
 Rim+0.732
 Dion+0.724
Neg logit contributions
owler-0.760
ynes-0.715
perty-0.672
perse-0.635
gow-0.633
Token-
Token ID12
Feature activation-2.79e-01

Pos logit contributions
CLASSIFIED+0.585
 Koen+0.557
batch+0.541
KC+0.538
 Rim+0.520
Neg logit contributions
owler-0.599
ynes-0.574
perty-0.545
gow-0.507
perse-0.505
Tokense
Token ID325
Feature activation+9.84e-02

Pos logit contributions
CLASSIFIED+0.756
 Koen+0.731
KC+0.685
 Rim+0.676
batch+0.673
Neg logit contributions
owler-0.778
ynes-0.732
perty-0.696
gow-0.657
perse-0.657
Token Britain
Token ID5491
Feature activation+8.16e-02

Pos logit contributions
CLASSIFIED+0.324
batch+0.306
KC+0.295
 Koen+0.294
 Rim+0.277
Neg logit contributions
owler-0.284
ynes-0.275
perty-0.260
gow-0.241
perse-0.233
Token cannot
Token ID2314
Feature activation-1.65e-01

Pos logit contributions
owler+0.213
ynes+0.209
perty+0.198
gow+0.188
apesh+0.181
Neg logit contributions
CLASSIFIED-0.225
batch-0.209
 Koen-0.205
KC-0.201
 Rim-0.192
Token start
Token ID923
Feature activation-1.77e-01

Pos logit contributions
CLASSIFIED+0.511
 Koen+0.473
batch+0.466
KC+0.462
 Rim+0.442
Neg logit contributions
owler-0.391
ynes-0.383
perty-0.351
gow-0.333
perse-0.329
Token formal
Token ID8766
Feature activation-7.45e-02

Pos logit contributions
CLASSIFIED+0.497
batch+0.473
 Koen+0.469
KC+0.465
 Bened+0.433
Neg logit contributions
owler-0.449
ynes-0.442
perty-0.417
gow-0.382
perse-0.379
Token trade
Token ID3292
Feature activation-1.23e-01

Pos logit contributions
CLASSIFIED+0.216
batch+0.204
 Koen+0.204
KC+0.199
 Bened+0.191
Neg logit contributions
ynes-0.183
owler-0.182
perty-0.167
gow-0.157
perse-0.154
Token negotiations
Token ID9825
Feature activation-5.33e-01

Pos logit contributions
CLASSIFIED+0.387
batch+0.377
 Koen+0.373
KC+0.366
 Rim+0.351
Neg logit contributions
ynes-0.268
owler-0.262
perty-0.238
perse-0.213
gow-0.213
Token until
Token ID1566
Feature activation-1.29e-01

Pos logit contributions
CLASSIFIED+1.421
batch+1.311
 Koen+1.290
KC+1.287
 Rim+1.198
Neg logit contributions
owler-1.472
ynes-1.467
perty-1.356
perse-1.280
apesh-1.270
Token it
Token ID340
Feature activation-7.08e-02

Pos logit contributions
CLASSIFIED+0.363
batch+0.340
KC+0.331
 Koen+0.329
OVA+0.311
Neg logit contributions
owler-0.332
ynes-0.329
perty-0.308
gow-0.279
perse-0.273
Token leaves
Token ID5667
Feature activation+1.61e-01

Pos logit contributions
CLASSIFIED+0.186
batch+0.166
 Koen+0.164
KC+0.163
 Rim+0.155
Neg logit contributions
ynes-0.202
owler-0.201
perty-0.189
gow-0.177
perse-0.175
Token the
Token ID262
Feature activation+1.38e-01

Pos logit contributions
owler+0.393
ynes+0.391
perty+0.369
gow+0.326
perse+0.325
Neg logit contributions
CLASSIFIED-0.471
batch-0.448
 Koen-0.438
KC-0.431
akin-0.411
Token bloc
Token ID24003
Feature activation+5.52e-01

Pos logit contributions
owler+0.334
ynes+0.326
perty+0.298
perse+0.270
gow+0.269
Neg logit contributions
CLASSIFIED-0.414
batch-0.396
 Koen-0.387
KC-0.380
 Dion-0.361
Token week
Token ID1285
Feature activation+1.66e-01

Pos logit contributions
owler+0.067
ynes+0.063
perty+0.061
gow+0.056
perse+0.056
Neg logit contributions
CLASSIFIED-0.059
batch-0.054
 Koen-0.053
KC-0.052
 Parties-0.051
Token should
Token ID815
Feature activation+2.80e-02

Pos logit contributions
owler+0.444
ynes+0.425
perty+0.401
perse+0.374
gow+0.367
Neg logit contributions
CLASSIFIED-0.454
batch-0.428
 Koen-0.418
KC-0.413
 Organisation-0.402
Token be
Token ID307
Feature activation-1.71e-03

Pos logit contributions
owler+0.066
ynes+0.065
perty+0.059
gow+0.056
perse+0.056
Neg logit contributions
CLASSIFIED-0.087
 Koen-0.080
batch-0.080
KC-0.078
 Organisation-0.077
Token a
Token ID257
Feature activation+9.98e-02

Pos logit contributions
CLASSIFIED+0.005
batch+0.005
KC+0.005
 Koen+0.004
 Parties+0.004
Neg logit contributions
owler-0.004
ynes-0.004
perty-0.004
perse-0.004
gow-0.003
Token tougher
Token ID20516
Feature activation+4.52e-02

Pos logit contributions
owler+0.250
ynes+0.246
perty+0.225
perse+0.210
gow+0.203
Neg logit contributions
CLASSIFIED-0.287
batch-0.271
 Koen-0.266
KC-0.262
 Parties-0.253
Token task
Token ID4876
Feature activation-4.22e-01

Pos logit contributions
owler+0.112
ynes+0.109
perty+0.102
gow+0.096
perse+0.094
Neg logit contributions
CLASSIFIED-0.132
 Koen-0.122
batch-0.122
KC-0.118
 Parties-0.117
Token,
Token ID11
Feature activation+4.35e-02

Pos logit contributions
CLASSIFIED+1.164
batch+1.080
 Koen+1.076
KC+1.050
 Organisation+1.021
Neg logit contributions
owler-1.132
ynes-1.091
perty-1.032
gow-0.967
perse-0.966
Token as
Token ID355
Feature activation-1.43e-01

Pos logit contributions
owler+0.115
ynes+0.110
perty+0.104
perse+0.096
apesh+0.092
Neg logit contributions
CLASSIFIED-0.121
batch-0.116
KC-0.110
 Koen-0.108
 Organisation-0.105
Token I
Token ID314
Feature activation-1.46e-01

Pos logit contributions
CLASSIFIED+0.409
batch+0.392
 Koen+0.374
KC+0.374
 Organisation+0.362
Neg logit contributions
owler-0.370
ynes-0.351
perty-0.328
perse-0.310
gow-0.296
Token expect
Token ID1607
Feature activation+8.67e-02

Pos logit contributions
CLASSIFIED+0.458
 Koen+0.428
batch+0.421
KC+0.410
 Rim+0.404
Neg logit contributions
owler-0.356
ynes-0.342
perty-0.317
perse-0.293
gow-0.289
Token Peterson
Token ID18914
Feature activation+2.10e-01

Pos logit contributions
owler+0.217
ynes+0.207
perty+0.195
perse+0.181
gow+0.175
Neg logit contributions
CLASSIFIED-0.255
batch-0.241
 Koen-0.231
KC-0.230
 Organisation-0.224
Token.
Token ID13
Feature activation+2.08e-01

Pos logit contributions
owler+0.300
ynes+0.290
perty+0.255
gow+0.255
perse+0.255
Neg logit contributions
CLASSIFIED-0.341
 Koen-0.316
batch-0.305
KC-0.298
 Ezek-0.294
TokenHeight
Token ID23106
Feature activation+1.84e-01

Pos logit contributions
owler+0.725
ynes+0.704
perty+0.671
gow+0.640
perse+0.640
Neg logit contributions
CLASSIFIED-0.376
 Koen-0.373
batch-0.349
KC-0.336
 Kenn-0.328
Token)))
Token ID22305
Feature activation+5.96e-02

Pos logit contributions
owler+0.472
ynes+0.460
perty+0.427
perse+0.398
gow+0.390
Neg logit contributions
CLASSIFIED-0.512
 Koen-0.499
batch-0.485
KC-0.478
 Rim-0.464
Token )
Token ID1267
Feature activation-2.82e-01

Pos logit contributions
owler+0.158
ynes+0.151
perty+0.139
perse+0.135
gow+0.128
Neg logit contributions
CLASSIFIED-0.164
 Koen-0.157
batch-0.152
KC-0.150
 Kenn-0.146
Token }
Token ID1782
Feature activation-5.96e-01

Pos logit contributions
CLASSIFIED+0.780
 Koen+0.752
batch+0.730
KC+0.723
 Kenn+0.699
Neg logit contributions
owler-0.747
ynes-0.715
perty-0.663
perse-0.638
gow-0.605
Token }
Token ID1782
Feature activation-7.48e-01

Pos logit contributions
CLASSIFIED+1.837
 Koen+1.759
batch+1.731
KC+1.714
 Kenn+1.651
Neg logit contributions
owler-1.401
ynes-1.339
perty-1.228
perse-1.160
gow-1.115
Token Catch
Token ID25750
Feature activation-5.35e-01

Pos logit contributions
CLASSIFIED+2.227
 Koen+2.129
batch+2.094
KC+2.073
 Kenn+1.997
Neg logit contributions
owler-1.841
ynes-1.761
perty-1.631
perse-1.533
gow-1.485
Token {
Token ID1391
Feature activation+2.97e-01

Pos logit contributions
CLASSIFIED+1.449
 Koen+1.370
batch+1.355
KC+1.325
 Kenn+1.285
Neg logit contributions
owler-1.466
ynes-1.390
perty-1.305
perse-1.240
gow-1.184
Token Write
Token ID19430
Feature activation+8.51e-02

Pos logit contributions
owler+0.696
ynes+0.650
perty+0.607
perse+0.584
apesh+0.548
Neg logit contributions
CLASSIFIED-0.890
 Koen-0.852
batch-0.845
KC-0.825
 Kenn-0.801
Token-
Token ID12
Feature activation-2.33e-01

Pos logit contributions
owler+0.210
ynes+0.202
perty+0.180
perse+0.176
gow+0.174
Neg logit contributions
CLASSIFIED-0.250
 Koen-0.234
batch-0.225
KC-0.223
 Ezek-0.222
TokenWarning
Token ID20361
Feature activation-8.07e-03

Pos logit contributions
CLASSIFIED+0.563
 Koen+0.554
 Dion+0.523
 Kenn+0.521
batch+0.517
Neg logit contributions
owler-0.686
ynes-0.649
perty-0.614
perse-0.585
gow-0.576
Token1
Token ID16
Feature activation-2.75e-02

Pos logit contributions
owler+0.563
ynes+0.545
perty+0.513
perse+0.503
apesh+0.478
Neg logit contributions
CLASSIFIED-0.429
 Koen-0.418
KC-0.386
batch-0.383
 Kenn-0.380
Token =
Token ID796
Feature activation-2.51e-01

Pos logit contributions
CLASSIFIED+0.057
 Koen+0.055
batch+0.052
KC+0.051
 Kenn+0.050
Neg logit contributions
owler-0.091
ynes-0.089
perty-0.084
perse-0.081
gow-0.079
Token New
Token ID968
Feature activation-1.31e-01

Pos logit contributions
CLASSIFIED+0.679
 Koen+0.652
batch+0.633
KC+0.633
 Kenn+0.605
Neg logit contributions
owler-0.683
ynes-0.645
perty-0.607
perse-0.579
gow-0.564
Token-
Token ID12
Feature activation-1.51e-01

Pos logit contributions
CLASSIFIED+0.373
 Koen+0.354
batch+0.342
KC+0.337
 Kenn+0.329
Neg logit contributions
owler-0.337
ynes-0.321
perty-0.291
perse-0.283
gow-0.283
TokenObject
Token ID10267
Feature activation-2.36e-01

Pos logit contributions
CLASSIFIED+0.410
 Koen+0.402
batch+0.372
 Rim+0.372
 Kenn+0.372
Neg logit contributions
owler-0.397
ynes-0.380
gow-0.341
perty-0.341
perse-0.334
Token System
Token ID4482
Feature activation-7.15e-01

Pos logit contributions
CLASSIFIED+0.517
 Koen+0.494
batch+0.481
KC+0.481
 Kenn+0.445
Neg logit contributions
owler-0.759
ynes-0.725
perty-0.687
perse-0.651
gow-0.650
Token.
Token ID13
Feature activation+2.87e-03

Pos logit contributions
CLASSIFIED+1.877
 Koen+1.788
batch+1.740
KC+1.711
 Rim+1.662
Neg logit contributions
owler-1.989
ynes-1.922
perty-1.783
perse-1.710
gow-1.696
TokenDraw
Token ID25302
Feature activation+9.03e-02

Pos logit contributions
owler+0.006
ynes+0.006
perty+0.005
perse+0.005
gow+0.005
Neg logit contributions
CLASSIFIED-0.009
 Koen-0.009
batch-0.009
KC-0.009
 Kenn-0.009
Tokening
Token ID278
Feature activation+2.52e-01

Pos logit contributions
owler+0.291
ynes+0.282
gow+0.259
perse+0.256
perty+0.255
Neg logit contributions
CLASSIFIED-0.206
 Koen-0.191
KC-0.174
 Ezek-0.173
batch-0.170
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
owler+0.616
ynes+0.584
perse+0.527
gow+0.522
perty+0.520
Neg logit contributions
CLASSIFIED-0.729
 Koen-0.695
batch-0.666
KC-0.656
 flavours-0.651
TokenRect
Token ID45474
Feature activation+2.30e-01

Pos logit contributions
owler+0.228
ynes+0.217
perty+0.199
perse+0.191
gow+0.188
Neg logit contributions
 Koen-0.336
CLASSIFIED-0.328
 Kenn-0.314
KC-0.312
 Dion-0.311
Token M
Token ID337
Feature activation-4.69e-02

Pos logit contributions
CLASSIFIED+0.928
 Koen+0.887
batch+0.879
KC+0.869
 Rim+0.825
Neg logit contributions
owler-1.007
ynes-0.994
perty-0.921
perse-0.873
apesh-0.859
TokenATE
Token ID6158
Feature activation+4.59e-01

Pos logit contributions
CLASSIFIED+0.151
 Koen+0.148
batch+0.144
KC+0.141
 Rim+0.138
Neg logit contributions
owler-0.096
ynes-0.094
perty-0.084
gow-0.081
apesh-0.078
Token 16
Token ID1467
Feature activation-1.48e-01

Pos logit contributions
owler+1.203
ynes+1.181
perty+1.077
gow+1.004
perse+1.003
Neg logit contributions
CLASSIFIED-1.215
 Koen-1.161
KC-1.133
batch-1.127
 Rim-1.089
Token.
Token ID13
Feature activation+2.51e-02

Pos logit contributions
CLASSIFIED+0.404
 Koen+0.385
batch+0.378
KC+0.366
 Rim+0.358
Neg logit contributions
owler-0.390
ynes-0.379
perty-0.347
perse-0.327
gow-0.323
Token04
Token ID3023
Feature activation+7.90e-03

Pos logit contributions
owler+0.077
ynes+0.077
perty+0.071
perse+0.069
gow+0.068
Neg logit contributions
CLASSIFIED-0.055
 Koen-0.052
KC-0.050
batch-0.050
 Rim-0.048
Token+
Token ID10
Feature activation-6.83e-01

Pos logit contributions
owler+0.021
ynes+0.021
perty+0.019
perse+0.018
gow+0.018
Neg logit contributions
CLASSIFIED-0.021
 Koen-0.020
batch-0.019
KC-0.019
 Ezek-0.018
Token at
Token ID379
Feature activation+6.82e-02

Pos logit contributions
CLASSIFIED+1.739
 Koen+1.664
batch+1.628
KC+1.611
 Rim+1.547
Neg logit contributions
owler-1.956
ynes-1.894
perty-1.767
perse-1.672
gow-1.653
Token all
Token ID477
Feature activation-1.07e-01

Pos logit contributions
owler+0.165
ynes+0.159
perty+0.144
apesh+0.138
gow+0.138
Neg logit contributions
CLASSIFIED-0.202
 Koen-0.189
batch-0.188
KC-0.184
 Organisation-0.178
Token,
Token ID11
Feature activation+9.60e-02

Pos logit contributions
CLASSIFIED+0.280
 Koen+0.273
batch+0.268
KC+0.262
 Rim+0.255
Neg logit contributions
owler-0.290
ynes-0.276
perty-0.258
perse-0.245
apesh-0.243
Token I
Token ID314
Feature activation+7.27e-02

Pos logit contributions
owler+0.247
ynes+0.236
perty+0.221
perse+0.202
gow+0.201
Neg logit contributions
CLASSIFIED-0.272
batch-0.259
KC-0.249
 Koen-0.249
 Organisation-0.238
Token
Token ID447
Feature activation-1.30e-01

Pos logit contributions
owler+0.193
ynes+0.184
perty+0.174
perse+0.161
gow+0.158
Neg logit contributions
CLASSIFIED-0.207
 Koen-0.194
batch-0.191
KC-0.185
 Rim-0.181
Token will
Token ID481
Feature activation+1.08e-01

Pos logit contributions
owler+0.163
ynes+0.155
perty+0.143
perse+0.133
gow+0.132
Neg logit contributions
CLASSIFIED-0.172
batch-0.164
 Koen-0.163
KC-0.157
 Rim-0.154
Token see
Token ID766
Feature activation+9.62e-02

Pos logit contributions
owler+0.266
ynes+0.255
perty+0.232
perse+0.219
gow+0.219
Neg logit contributions
CLASSIFIED-0.332
 Koen-0.307
batch-0.306
KC-0.298
 Rim-0.291
Token if
Token ID611
Feature activation+1.42e-01

Pos logit contributions
owler+0.256
ynes+0.243
perty+0.228
perse+0.213
gow+0.211
Neg logit contributions
CLASSIFIED-0.270
batch-0.254
 Koen-0.243
KC-0.242
 Parties-0.235
Token he
Token ID339
Feature activation+1.22e-01

Pos logit contributions
owler+0.365
ynes+0.349
perty+0.323
perse+0.303
gow+0.298
Neg logit contributions
CLASSIFIED-0.408
batch-0.387
 Koen-0.373
KC-0.369
 Parties-0.364
Token can
Token ID460
Feature activation+8.95e-02

Pos logit contributions
owler+0.334
ynes+0.320
perty+0.293
perse+0.283
apesh+0.277
Neg logit contributions
CLASSIFIED-0.336
 Koen-0.318
batch-0.313
KC-0.303
 Organisation-0.299
Token serve
Token ID4691
Feature activation-7.44e-01

Pos logit contributions
owler+0.219
ynes+0.208
perty+0.193
perse+0.184
gow+0.180
Neg logit contributions
CLASSIFIED-0.272
 Koen-0.255
batch-0.247
 Organisation-0.242
KC-0.241
Token as
Token ID355
Feature activation+6.95e-02

Pos logit contributions
CLASSIFIED+2.010
batch+1.913
 Koen+1.879
KC+1.833
 Organisation+1.787
Neg logit contributions
owler-2.045
ynes-1.962
perty-1.826
perse-1.722
gow-1.686
Token an
Token ID281
Feature activation+6.30e-03

Pos logit contributions
owler+0.179
ynes+0.169
perty+0.159
perse+0.149
gow+0.147
Neg logit contributions
CLASSIFIED-0.197
batch-0.189
 Koen-0.183
KC-0.179
 Parties-0.178
Token upgrade
Token ID8515
Feature activation+3.27e-01

Pos logit contributions
owler+0.018
ynes+0.017
perty+0.015
apesh+0.014
perse+0.014
Neg logit contributions
CLASSIFIED-0.017
batch-0.016
 Koen-0.016
KC-0.015
 Parties-0.015
Token,
Token ID11
Feature activation-5.04e-02

Pos logit contributions
owler+0.787
ynes+0.727
perty+0.666
gow+0.634
perse+0.624
Neg logit contributions
CLASSIFIED-1.003
batch-0.933
 Koen-0.933
KC-0.913
 Parties-0.907
Token and
Token ID290
Feature activation-1.16e-01

Pos logit contributions
CLASSIFIED+0.133
batch+0.127
KC+0.122
 Koen+0.121
 Parties+0.117
Neg logit contributions
owler-0.141
ynes-0.134
perty-0.126
perse-0.117
apesh-0.115
Token band
Token ID4097
Feature activation+1.66e-02

Pos logit contributions
CLASSIFIED+0.737
batch+0.673
 Koen+0.656
KC+0.647
 Organisation+0.623
Neg logit contributions
owler-0.811
ynes-0.795
perty-0.742
perse-0.707
gow-0.693
Tokenaged
Token ID1886
Feature activation+1.09e-01

Pos logit contributions
owler+0.037
ynes+0.037
perty+0.033
gow+0.031
har+0.031
Neg logit contributions
CLASSIFIED-0.053
batch-0.050
 Koen-0.050
KC-0.047
 Rim-0.046
Token children
Token ID1751
Feature activation-1.62e-01

Pos logit contributions
owler+0.334
ynes+0.331
perty+0.306
gow+0.291
perse+0.288
Neg logit contributions
CLASSIFIED-0.256
batch-0.242
KC-0.229
 Koen-0.226
 Organisation-0.213
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
CLASSIFIED+0.455
batch+0.417
KC+0.410
 Koen+0.407
 Organisation+0.387
Neg logit contributions
owler-0.427
ynes-0.423
perty-0.393
perse-0.362
gow-0.360
Token They
Token ID1119
Feature activation-1.19e-01

Pos logit contributions
CLASSIFIED+0.361
batch+0.344
KC+0.332
 Koen+0.331
 flavours+0.319
Neg logit contributions
owler-0.327
ynes-0.314
perty-0.288
perse-0.274
gow-0.272
Token stare
Token ID24170
Feature activation-7.90e-01

Pos logit contributions
CLASSIFIED+0.368
 Koen+0.341
batch+0.335
KC+0.332
 Rim+0.316
Neg logit contributions
owler-0.289
ynes-0.280
perty-0.259
perse-0.243
gow-0.241
Token at
Token ID379
Feature activation-1.99e-01

Pos logit contributions
CLASSIFIED+2.177
 Koen+2.047
batch+2.031
KC+2.006
 Rim+1.920
Neg logit contributions
owler-2.118
ynes-2.062
perty-1.918
perse-1.794
gow-1.771
Token Sullivan
Token ID18501
Feature activation+1.51e-01

Pos logit contributions
CLASSIFIED+0.549
batch+0.514
KC+0.506
 Koen+0.504
 Organisation+0.477
Neg logit contributions
owler-0.534
ynes-0.517
perty-0.486
perse-0.457
gow-0.441
Token,
Token ID11
Feature activation-4.93e-02

Pos logit contributions
owler+0.387
ynes+0.383
perty+0.356
gow+0.329
perse+0.326
Neg logit contributions
CLASSIFIED-0.426
KC-0.388
batch-0.387
 Koen-0.387
 Organisation-0.373
Token some
Token ID617
Feature activation+1.07e-02

Pos logit contributions
CLASSIFIED+0.138
batch+0.129
KC+0.125
 Koen+0.125
 Organisation+0.118
Neg logit contributions
owler-0.130
ynes-0.127
perty-0.118
perse-0.111
gow-0.108
Token with
Token ID351
Feature activation-3.17e-01

Pos logit contributions
owler+0.029
ynes+0.028
perty+0.026
perse+0.025
gow+0.025
Neg logit contributions
CLASSIFIED-0.029
batch-0.028
KC-0.027
 Koen-0.027
 Rim-0.025