TOP ACTIVATIONS
MAX = 5.890

ton , Sam P anche vre ( Sam s
s o eu vre . It feels nothing like
left - right ) Gary Neville , Ben Thorn ley ,
s o eu vre , Manhattan d ut ifully
expansion of an o eu vre that mixes discomfort and que
the Moon , fighting Darth Vader and wearing the face of
cool character . CV : So what made you
Gerald Ford - class ( CV N 78 on ) has
. Budapest at Christmas ( December 20 - 27 , £
super powered . CV : What made Mid n
actions , known as " extra ordinary measures ," to keep
don t have Vita - Mix es , this
class carriers in service ( CV N 68 - 77 ),
of raw food prep sans Vita should take heart : it
beating out competitors like the PlayStation 4 and Wii U .
" will be appearing on PlayStation 4 and Xbox One any
on Twitter as an " extra level of safety ." It
ray , along with bonus DLC and a mini license plate
what 's on the D VR . Streaming lets you do
added borrowing , those " extra ordinary measures " will be

MIN ACTIVATIONS
MIN = -6.681

un successfully ) to spray anth rax spores over Tokyo .
is determined by how the carc ass is scored for things
, Liam , Stella , Hatt ie and Finn , and
lez al slide on the Cait lyn Jenner comparisons and
But the people scoring the carc asses are employees of the
they need to enter the predomin ately male - dominated programming
know : In the Atlanta Journal - Const itution 's published
hormone secret ed by the hypothal amus in response to stress
The United States is spir alling down into a basic
8 Great New Female Positive Ong o ings .
. My colleague Amer A ther was responsible for
Like elephants , mamm oths had two flesh y
aghetti Dinner at Clear Creek Aman a High School on April
law , he has st onew alled public interest groups ,
se us tied to the mast , sailing away from the
hide details of the massive backlog they were am assing as
v me storage driver . Amer has tested and deployed this
an alternative to The Ad vertis er , a different voice
said Sen . Kay Bailey Hutch ison ( R
) such as methane and aeros ols , as well as

INTERVAL 2.747 - 5.890
CONTAINS 0.492%

public b rom ance , Putin would much prefer a Trump
not just at or near v ort ons . So ,
type uses a new hyper visor called Nit ro . Nit
Apex has been built with VR in mind , for example
de N og ales Lep re - v ost and Edwin

INTERVAL -0.396 - 2.747
CONTAINS 71.650%

) { let prev _ state = self . copy _
you can continue following me on this j ourn y ,
must not modify the state of the original copy . Board
out of hand and the shit hits the fan . Luckily
USA State Ac ro Ac ro Ac

INTERVAL -3.538 - -0.396
CONTAINS 27.712%

mechanism had broken under the air loads allowing the wing tips
59 - 42 . But Mason earned the game
Italian firm En i received the largest fine - more than
, probably in China . This would mean co - operation
by the wide - ranging crackdown were 200 , 000 who

INTERVAL -6.681 - -3.538
CONTAINS 0.145%

about W ile E . Coy ote and about people who
so rapidly ? Though the boom in global commodity prices played
L ä nt inen , Sus anna Ha av ist o
. Ren owned dou jin video game maker Jun
a pot - add led Ober lin College freshman 's
Tokenton
Token ID1122
Feature activation-6.48e-01

Pos logit contributions
yond+0.214
swick+0.184
nance+0.176
le+0.166
hips+0.161
Neg logit contributions
ngth-0.341
orsi-0.322
riction-0.308
spection-0.307
ordinary-0.301
Token,
Token ID11
Feature activation-1.06e-01

Pos logit contributions
yond+0.855
swick+0.762
nance+0.739
hips+0.693
le+0.692
Neg logit contributions
ngth-0.763
orsi-0.709
riction-0.679
spection-0.678
ordinary-0.664
Token Sam
Token ID3409
Feature activation-5.66e-01

Pos logit contributions
yond+0.134
swick+0.120
nance+0.116
le+0.108
hips+0.108
Neg logit contributions
ngth-0.131
orsi-0.122
riction-0.117
spection-0.116
ordinary-0.115
Token P
Token ID350
Feature activation+9.41e-01

Pos logit contributions
yond+0.720
swick+0.641
nance+0.621
le+0.583
hips+0.583
Neg logit contributions
ngth-0.691
orsi-0.645
riction-0.620
spection-0.616
ordinary-0.607
Tokenanche
Token ID6362
Feature activation-1.09e+00

Pos logit contributions
ngth+1.115
orsi+1.045
riction+0.998
spection+0.989
ordinary+0.970
Neg logit contributions
yond-1.225
swick-1.096
nance-1.057
hips-0.992
le-0.989
Tokenvre
Token ID43933
Feature activation+5.89e+00

Pos logit contributions
yond+1.633
swick+1.481
nance+1.440
le+1.399
hips+1.371
Neg logit contributions
ngth-1.070
orsi-0.978
riction-0.942
spection-0.931
ordinary-0.916
Token (
Token ID357
Feature activation+5.38e-01

Pos logit contributions
ngth+6.241
orsi+5.677
spection+5.506
riction+5.291
ordinary+5.236
Neg logit contributions
yond-7.755
swick-6.896
nance-6.686
hips-6.315
gency-6.150
TokenSam
Token ID16305
Feature activation-4.85e-01

Pos logit contributions
ngth+0.608
orsi+0.564
riction+0.541
spection+0.539
ordinary+0.533
Neg logit contributions
yond-0.727
swick-0.653
nance-0.636
hips-0.595
le-0.594
Token
Token ID447
Feature activation+2.58e-01

Pos logit contributions
yond+0.630
swick+0.563
nance+0.546
le+0.514
hips+0.514
Neg logit contributions
ngth-0.577
orsi-0.538
riction-0.517
spection-0.514
ordinary-0.505
Token
Token ID247
Feature activation+1.94e-01

Pos logit contributions
ngth+0.310
orsi+0.289
riction+0.279
spection+0.277
ordinary+0.273
Neg logit contributions
yond-0.331
swick-0.296
nance-0.287
le-0.268
hips-0.268
Tokens
Token ID82
Feature activation-1.46e+00

Pos logit contributions
ngth+0.185
orsi+0.169
spection+0.162
riction+0.161
ordinary+0.157
Neg logit contributions
yond-0.296
swick-0.266
nance-0.261
hips-0.247
le-0.244
Token
Token ID447
Feature activation-1.66e-02

Pos logit contributions
yond+0.402
swick+0.363
nance+0.353
hips+0.331
le+0.331
Neg logit contributions
ngth-0.326
orsi-0.303
riction-0.289
spection-0.289
ordinary-0.283
Token
Token ID247
Feature activation+5.08e-02

Pos logit contributions
yond+0.019
swick+0.017
nance+0.016
le+0.015
hips+0.015
Neg logit contributions
ngth-0.023
orsi-0.021
riction-0.020
spection-0.020
ordinary-0.020
Tokens
Token ID82
Feature activation-1.45e+00

Pos logit contributions
ngth+0.052
orsi+0.047
riction+0.045
spection+0.045
ordinary+0.044
Neg logit contributions
yond-0.075
swick-0.068
nance-0.066
hips-0.063
le-0.062
Token o
Token ID267
Feature activation-1.12e+00

Pos logit contributions
yond+1.890
swick+1.684
nance+1.634
hips+1.554
le+1.552
Neg logit contributions
ngth-1.717
orsi-1.597
riction-1.529
spection-1.519
ordinary-1.489
Tokeneu
Token ID12496
Feature activation+1.59e+00

Pos logit contributions
yond+1.418
swick+1.261
nance+1.223
le+1.161
hips+1.147
Neg logit contributions
ngth-1.367
orsi-1.279
riction-1.226
spection-1.214
ordinary-1.198
Tokenvre
Token ID43933
Feature activation+5.61e+00

Pos logit contributions
ngth+0.955
orsi+0.820
spection+0.801
riction+0.772
ordinary+0.756
Neg logit contributions
yond-2.958
swick-2.762
nance-2.678
hips-2.627
le-2.542
Token.
Token ID13
Feature activation-8.13e-02

Pos logit contributions
ngth+5.456
orsi+4.964
spection+4.851
riction+4.730
ordinary+4.633
Neg logit contributions
yond-7.935
swick-7.342
nance-7.201
hips-6.514
gency-6.468
Token It
Token ID632
Feature activation+8.40e-02

Pos logit contributions
yond+0.095
swick+0.084
nance+0.080
le+0.076
hips+0.075
Neg logit contributions
ngth-0.108
orsi-0.101
riction-0.098
spection-0.097
ordinary-0.095
Token feels
Token ID5300
Feature activation+7.38e-01

Pos logit contributions
ngth+0.096
orsi+0.089
riction+0.086
spection+0.085
ordinary+0.084
Neg logit contributions
yond-0.113
swick-0.102
nance-0.099
le-0.093
hips-0.093
Token nothing
Token ID2147
Feature activation-5.09e-01

Pos logit contributions
ngth+0.864
orsi+0.803
riction+0.774
spection+0.768
ordinary+0.759
Neg logit contributions
yond-0.968
swick-0.872
nance-0.842
hips-0.788
le-0.787
Token like
Token ID588
Feature activation+1.94e-01

Pos logit contributions
yond+0.653
swick+0.585
nance+0.566
le+0.531
hips+0.531
Neg logit contributions
ngth-0.614
orsi-0.573
riction-0.551
spection-0.548
ordinary-0.540
Tokenleft
Token ID9464
Feature activation+1.72e+00

Pos logit contributions
ngth+0.701
orsi+0.651
riction+0.624
spection+0.620
ordinary+0.607
Neg logit contributions
yond-0.807
swick-0.723
nance-0.702
le-0.665
hips-0.662
Token-
Token ID12
Feature activation+2.25e-01

Pos logit contributions
ngth+1.601
orsi+1.493
riction+1.432
spection+1.409
ordinary+1.377
Neg logit contributions
yond-2.605
swick-2.365
nance-2.323
hips-2.193
gency-2.169
Tokenright
Token ID3506
Feature activation+2.16e+00

Pos logit contributions
ngth+0.323
orsi+0.305
riction+0.294
spection+0.293
ordinary+0.289
Neg logit contributions
yond-0.239
swick-0.207
nance-0.199
le-0.185
hips-0.185
Token)
Token ID8
Feature activation-1.07e+00

Pos logit contributions
ngth+2.211
orsi+2.066
spection+1.951
riction+1.949
ordinary+1.918
Neg logit contributions
yond-3.083
swick-2.776
nance-2.708
gency-2.549
hips-2.541
Token Gary
Token ID10936
Feature activation-2.01e+00

Pos logit contributions
yond+1.318
swick+1.161
nance+1.129
le+1.070
hips+1.064
Neg logit contributions
ngth-1.355
orsi-1.265
riction-1.219
spection-1.211
ordinary-1.186
Token Neville
Token ID35840
Feature activation+5.51e+00

Pos logit contributions
yond+2.916
swick+2.653
nance+2.569
le+2.487
hips+2.444
Neg logit contributions
ngth-2.079
orsi-1.919
riction-1.816
spection-1.798
ordinary-1.757
Token,
Token ID11
Feature activation-3.25e-01

Pos logit contributions
ngth+5.376
orsi+5.074
spection+4.864
ordinary+4.817
riction+4.799
Neg logit contributions
yond-7.649
swick-6.917
nance-6.747
gency-6.406
hips-6.213
Token Ben
Token ID3932
Feature activation-4.36e-01

Pos logit contributions
yond+0.406
swick+0.360
nance+0.349
le+0.328
hips+0.327
Neg logit contributions
ngth-0.405
orsi-0.378
riction-0.364
spection-0.362
ordinary-0.356
Token Thorn
Token ID31422
Feature activation-5.75e-01

Pos logit contributions
yond+0.564
swick+0.503
nance+0.488
hips+0.458
le+0.458
Neg logit contributions
ngth-0.521
orsi-0.487
riction-0.468
spection-0.464
ordinary-0.457
Tokenley
Token ID1636
Feature activation+1.07e+00

Pos logit contributions
yond+0.633
swick+0.552
nance+0.533
hips+0.492
le+0.490
Neg logit contributions
ngth-0.799
orsi-0.753
riction-0.727
spection-0.724
ordinary-0.715
Token,
Token ID11
Feature activation-2.09e-01

Pos logit contributions
ngth+1.145
orsi+1.067
spection+1.016
riction+1.011
ordinary+1.002
Neg logit contributions
yond-1.502
swick-1.339
nance-1.305
gency-1.231
hips-1.220
Token
Token ID447
Feature activation+4.37e-01

Pos logit contributions
yond+0.012
swick+0.011
nance+0.010
hips+0.010
le+0.010
Neg logit contributions
ngth-0.008
orsi-0.007
spection-0.007
riction-0.007
ordinary-0.006
Token
Token ID247
Feature activation+6.09e-01

Pos logit contributions
ngth+0.586
orsi+0.544
riction+0.518
spection+0.516
ordinary+0.510
Neg logit contributions
yond-0.513
swick-0.445
nance-0.432
le-0.417
hips-0.413
Tokens
Token ID82
Feature activation-1.24e+00

Pos logit contributions
ngth+0.540
orsi+0.490
spection+0.484
riction+0.471
ordinary+0.459
Neg logit contributions
yond-0.963
swick-0.878
nance-0.863
hips-0.807
le-0.791
Token o
Token ID267
Feature activation-6.70e-01

Pos logit contributions
yond+1.710
swick+1.536
nance+1.491
le+1.418
hips+1.413
Neg logit contributions
ngth-1.390
orsi-1.289
riction-1.232
spection-1.219
ordinary-1.199
Tokeneu
Token ID12496
Feature activation+2.13e+00

Pos logit contributions
yond+0.855
swick+0.762
nance+0.738
le+0.697
hips+0.693
Neg logit contributions
ngth-0.814
orsi-0.760
riction-0.729
spection-0.724
ordinary-0.713
Tokenvre
Token ID43933
Feature activation+5.43e+00

Pos logit contributions
ngth+1.564
orsi+1.393
riction+1.288
spection+1.244
ordinary+1.226
Neg logit contributions
yond-3.774
swick-3.460
nance-3.409
le-3.291
hips-3.226
Token,
Token ID11
Feature activation-7.63e-02

Pos logit contributions
ngth+5.101
orsi+4.687
spection+4.519
riction+4.382
ordinary+4.241
Neg logit contributions
yond-7.781
swick-7.230
nance-7.113
hips-6.444
gency-6.371
Token Manhattan
Token ID13458
Feature activation-9.27e-01

Pos logit contributions
yond+0.100
swick+0.089
nance+0.087
le+0.082
hips+0.082
Neg logit contributions
ngth-0.090
orsi-0.084
riction-0.081
spection-0.080
ordinary-0.079
Token d
Token ID288
Feature activation+1.99e+00

Pos logit contributions
yond+1.182
swick+1.056
nance+1.022
le+0.970
hips+0.965
Neg logit contributions
ngth-1.123
orsi-1.046
riction-1.011
spection-0.999
ordinary-0.983
Tokenut
Token ID315
Feature activation+2.78e-01

Pos logit contributions
ngth+1.993
orsi+1.857
riction+1.761
spection+1.743
ordinary+1.717
Neg logit contributions
yond-2.940
swick-2.673
nance-2.599
le-2.456
hips-2.450
Tokenifully
Token ID17049
Feature activation+1.42e+00

Pos logit contributions
ngth+0.379
orsi+0.356
riction+0.343
spection+0.341
ordinary+0.336
Neg logit contributions
yond-0.315
swick-0.276
nance-0.267
le-0.249
hips-0.248
Token expansion
Token ID7118
Feature activation-8.91e-01

Pos logit contributions
ngth+0.650
orsi+0.608
riction+0.587
spection+0.585
ordinary+0.580
Neg logit contributions
yond-0.663
swick-0.592
nance-0.573
hips-0.536
le-0.535
Token of
Token ID286
Feature activation+8.21e-01

Pos logit contributions
yond+1.002
swick+0.886
nance+0.860
le+0.788
hips+0.781
Neg logit contributions
ngth-1.218
orsi-1.146
riction-1.108
spection-1.104
ordinary-1.093
Token an
Token ID281
Feature activation+3.38e-01

Pos logit contributions
ngth+1.022
orsi+0.954
spection+0.921
riction+0.921
ordinary+0.909
Neg logit contributions
yond-1.017
swick-0.904
nance-0.878
hips-0.821
le-0.815
Token o
Token ID267
Feature activation-1.15e+00

Pos logit contributions
ngth+0.443
orsi+0.417
riction+0.403
spection+0.401
ordinary+0.397
Neg logit contributions
yond-0.396
swick-0.350
nance-0.338
hips-0.315
le-0.314
Tokeneu
Token ID12496
Feature activation+1.73e+00

Pos logit contributions
yond+1.769
swick+1.607
nance+1.565
le+1.498
hips+1.489
Neg logit contributions
ngth-1.108
orsi-1.016
riction-0.963
spection-0.953
ordinary-0.933
Tokenvre
Token ID43933
Feature activation+5.33e+00

Pos logit contributions
ngth+1.037
orsi+0.897
spection+0.860
riction+0.824
ordinary+0.819
Neg logit contributions
yond-3.238
swick-3.012
nance-2.926
hips-2.880
le-2.779
Token that
Token ID326
Feature activation+1.87e-02

Pos logit contributions
ngth+6.497
orsi+6.060
spection+5.875
ordinary+5.823
riction+5.759
Neg logit contributions
yond-6.221
swick-5.684
nance-5.527
hips-4.959
gency-4.868
Token mixes
Token ID33237
Feature activation+2.52e-02

Pos logit contributions
ngth+0.024
orsi+0.022
riction+0.021
spection+0.021
ordinary+0.021
Neg logit contributions
yond-0.023
swick-0.020
nance-0.020
hips-0.019
le-0.019
Token discomfort
Token ID23597
Feature activation-6.99e-02

Pos logit contributions
ngth+0.029
orsi+0.027
riction+0.026
spection+0.026
ordinary+0.026
Neg logit contributions
yond-0.034
swick-0.030
nance-0.029
hips-0.027
le-0.027
Token and
Token ID290
Feature activation-4.95e-03

Pos logit contributions
yond+0.083
swick+0.074
nance+0.071
hips+0.066
le+0.066
Neg logit contributions
ngth-0.091
orsi-0.085
riction-0.082
spection-0.082
ordinary-0.080
Token que
Token ID8358
Feature activation-5.92e-01

Pos logit contributions
yond+0.007
swick+0.006
nance+0.006
le+0.006
hips+0.006
Neg logit contributions
ngth-0.005
orsi-0.005
riction-0.005
spection-0.005
ordinary-0.005
Token the
Token ID262
Feature activation-2.88e-01

Pos logit contributions
yond+0.194
swick+0.173
nance+0.168
le+0.158
hips+0.158
Neg logit contributions
ngth-0.173
orsi-0.161
riction-0.154
spection-0.153
ordinary-0.151
Token Moon
Token ID6869
Feature activation-8.64e-01

Pos logit contributions
yond+0.363
swick+0.323
nance+0.313
le+0.297
hips+0.295
Neg logit contributions
ngth-0.357
orsi-0.330
riction-0.319
spection-0.316
ordinary-0.311
Token,
Token ID11
Feature activation-2.23e-01

Pos logit contributions
yond+1.109
swick+0.991
nance+0.963
hips+0.911
le+0.910
Neg logit contributions
ngth-1.046
orsi-0.969
riction-0.933
spection-0.923
ordinary-0.914
Token fighting
Token ID4330
Feature activation-8.16e-02

Pos logit contributions
yond+0.274
swick+0.242
nance+0.235
le+0.221
hips+0.220
Neg logit contributions
ngth-0.283
orsi-0.264
riction-0.255
spection-0.253
ordinary-0.249
Token Darth
Token ID31152
Feature activation+1.18e+00

Pos logit contributions
yond+0.101
swick+0.090
nance+0.087
le+0.082
hips+0.082
Neg logit contributions
ngth-0.102
orsi-0.095
riction-0.092
spection-0.091
ordinary-0.090
Token Vader
Token ID27403
Feature activation+5.23e+00

Pos logit contributions
ngth+0.710
orsi+0.611
riction+0.568
spection+0.560
ordinary+0.537
Neg logit contributions
yond-2.223
swick-2.060
nance-2.021
hips-1.933
le-1.925
Token and
Token ID290
Feature activation+4.67e-02

Pos logit contributions
ngth+5.659
orsi+5.413
spection+5.198
riction+5.126
ordinary+5.032
Neg logit contributions
yond-6.781
swick-6.193
nance-5.931
gency-5.579
hips-5.450
Token wearing
Token ID5762
Feature activation-7.30e-01

Pos logit contributions
ngth+0.057
orsi+0.054
riction+0.051
spection+0.051
ordinary+0.050
Neg logit contributions
yond-0.059
swick-0.053
nance-0.051
le-0.048
hips-0.048
Token the
Token ID262
Feature activation+5.58e-02

Pos logit contributions
yond+0.973
swick+0.873
nance+0.843
le+0.803
hips+0.800
Neg logit contributions
ngth-0.851
orsi-0.789
riction-0.754
spection-0.750
ordinary-0.735
Token face
Token ID1986
Feature activation-6.14e-01

Pos logit contributions
ngth+0.069
orsi+0.064
riction+0.062
spection+0.062
ordinary+0.061
Neg logit contributions
yond-0.070
swick-0.062
nance-0.060
le-0.057
hips-0.057
Token of
Token ID286
Feature activation+7.37e-01

Pos logit contributions
yond+0.714
swick+0.628
nance+0.610
hips+0.565
le+0.560
Neg logit contributions
ngth-0.811
orsi-0.764
riction-0.738
spection-0.736
ordinary-0.727
Token cool
Token ID3608
Feature activation+2.25e+00

Pos logit contributions
yond+0.010
swick+0.009
nance+0.009
le+0.009
hips+0.009
Neg logit contributions
ngth-0.009
orsi-0.008
riction-0.008
spection-0.008
ordinary-0.007
Token character
Token ID2095
Feature activation+1.45e+00

Pos logit contributions
ngth+2.619
orsi+2.482
riction+2.391
spection+2.387
ordinary+2.360
Neg logit contributions
yond-2.904
swick-2.610
nance-2.523
hips-2.356
le-2.340
Token.
Token ID13
Feature activation+4.83e-02

Pos logit contributions
ngth+1.752
orsi+1.638
riction+1.576
spection+1.569
ordinary+1.543
Neg logit contributions
yond-1.861
swick-1.663
nance-1.612
le-1.509
hips-1.508
Token
Token ID198
Feature activation+9.00e-02

Pos logit contributions
ngth+0.065
orsi+0.061
riction+0.059
spection+0.058
ordinary+0.058
Neg logit contributions
yond-0.055
swick-0.049
nance-0.047
le-0.044
hips-0.044
Token
Token ID198
Feature activation+6.71e-02

Pos logit contributions
ngth+0.137
orsi+0.124
riction+0.118
spection+0.116
ordinary+0.112
Neg logit contributions
yond-0.098
swick-0.084
le-0.081
nance-0.080
hips-0.078
TokenCV
Token ID33538
Feature activation+5.09e+00

Pos logit contributions
ngth+0.048
orsi+0.042
riction+0.039
spection+0.038
ordinary+0.037
Neg logit contributions
yond-0.120
swick-0.111
nance-0.108
le-0.104
hips-0.104
Token:
Token ID25
Feature activation-6.39e-01

Pos logit contributions
ngth+5.186
orsi+4.891
spection+4.694
riction+4.673
ordinary+4.640
Neg logit contributions
yond-7.208
swick-6.553
nance-6.375
hips-5.951
le-5.927
Token So
Token ID1406
Feature activation+3.82e-01

Pos logit contributions
yond+0.728
swick+0.651
nance+0.613
le+0.593
hips+0.589
Neg logit contributions
ngth-0.873
orsi-0.815
riction-0.787
spection-0.773
ordinary-0.760
Token what
Token ID644
Feature activation+3.91e-01

Pos logit contributions
ngth+0.450
orsi+0.418
riction+0.399
spection+0.397
ordinary+0.390
Neg logit contributions
yond-0.507
swick-0.450
nance-0.438
le-0.418
hips-0.417
Token made
Token ID925
Feature activation-8.64e-01

Pos logit contributions
ngth+0.473
orsi+0.438
riction+0.422
spection+0.419
ordinary+0.411
Neg logit contributions
yond-0.503
swick-0.447
nance-0.434
le-0.413
hips-0.410
Token you
Token ID345
Feature activation-4.67e-01

Pos logit contributions
yond+1.127
swick+1.006
nance+0.977
le+0.932
hips+0.927
Neg logit contributions
ngth-1.018
orsi-0.957
riction-0.909
spection-0.907
ordinary-0.887
Token Gerald
Token ID27027
Feature activation-2.28e+00

Pos logit contributions
ngth+0.183
orsi+0.171
riction+0.165
spection+0.164
ordinary+0.161
Neg logit contributions
yond-0.192
swick-0.171
nance-0.166
le-0.156
hips-0.156
Token Ford
Token ID8092
Feature activation-1.73e-01

Pos logit contributions
yond+2.485
swick+2.177
nance+2.126
le+2.018
hips+1.998
Neg logit contributions
ngth-3.207
orsi-2.964
spection-2.849
riction-2.848
ordinary-2.829
Token-
Token ID12
Feature activation-7.65e-01

Pos logit contributions
yond+0.223
swick+0.199
nance+0.193
le+0.182
hips+0.182
Neg logit contributions
ngth-0.208
orsi-0.193
riction-0.186
spection-0.184
ordinary-0.181
Tokenclass
Token ID4871
Feature activation+7.08e-01

Pos logit contributions
yond+1.226
swick+1.120
nance+1.094
le+1.053
hips+1.048
Neg logit contributions
ngth-0.683
orsi-0.622
riction-0.586
spection-0.578
ordinary-0.564
Token (
Token ID357
Feature activation+1.42e-01

Pos logit contributions
ngth+0.922
orsi+0.866
riction+0.835
spection+0.832
ordinary+0.820
Neg logit contributions
yond-0.836
swick-0.740
nance-0.710
le-0.663
hips-0.660
TokenCV
Token ID33538
Feature activation+5.08e+00

Pos logit contributions
ngth+0.115
orsi+0.104
riction+0.098
spection+0.096
ordinary+0.094
Neg logit contributions
yond-0.238
swick-0.218
nance-0.213
le-0.205
hips-0.204
TokenN
Token ID45
Feature activation+3.06e-01

Pos logit contributions
ngth+4.843
orsi+4.595
GS+4.484
UV+4.421
LV+4.399
Neg logit contributions
yond-7.111
swick-6.469
nance-6.323
hips-5.956
gency-5.937
Token 78
Token ID8699
Feature activation+3.89e-02

Pos logit contributions
ngth+0.352
orsi+0.325
riction+0.312
spection+0.308
ordinary+0.302
Neg logit contributions
yond-0.415
swick-0.372
nance-0.361
le-0.344
hips-0.342
Token on
Token ID319
Feature activation-1.65e-01

Pos logit contributions
ngth+0.041
orsi+0.038
spection+0.036
riction+0.036
ordinary+0.035
Neg logit contributions
yond-0.056
swick-0.050
nance-0.049
hips-0.046
le-0.046
Token)
Token ID8
Feature activation-1.47e+00

Pos logit contributions
yond+0.212
swick+0.189
nance+0.183
le+0.173
hips+0.172
Neg logit contributions
ngth-0.200
orsi-0.186
riction-0.179
spection-0.177
ordinary-0.175
Token has
Token ID468
Feature activation+1.03e+00

Pos logit contributions
yond+1.843
swick+1.638
nance+1.594
le+1.506
hips+1.501
Neg logit contributions
ngth-1.822
orsi-1.698
riction-1.641
spection-1.619
ordinary-1.599
Token.
Token ID13
Feature activation+1.16e-01

Pos logit contributions
ngth+0.647
orsi+0.604
riction+0.581
spection+0.575
ordinary+0.567
Neg logit contributions
yond-0.636
swick-0.565
nance-0.546
le-0.515
hips-0.515
Token Budapest
Token ID40959
Feature activation+1.49e-01

Pos logit contributions
ngth+0.151
orsi+0.141
riction+0.136
spection+0.135
ordinary+0.133
Neg logit contributions
yond-0.138
swick-0.123
nance-0.118
le-0.111
hips-0.111
Token at
Token ID379
Feature activation-6.20e-01

Pos logit contributions
ngth+0.185
orsi+0.173
riction+0.166
spection+0.165
ordinary+0.163
Neg logit contributions
yond-0.186
swick-0.165
nance-0.160
le-0.150
hips-0.150
Token Christmas
Token ID6786
Feature activation+1.36e+00

Pos logit contributions
yond+0.793
swick+0.708
nance+0.685
le+0.649
hips+0.644
Neg logit contributions
ngth-0.752
orsi-0.700
riction-0.674
spection-0.669
ordinary-0.659
Token (
Token ID357
Feature activation+5.46e-01

Pos logit contributions
ngth+1.657
orsi+1.552
riction+1.492
spection+1.486
ordinary+1.469
Neg logit contributions
yond-1.724
swick-1.534
nance-1.489
hips-1.391
le-1.386
TokenDecember
Token ID20588
Feature activation+5.04e+00

Pos logit contributions
ngth+0.520
orsi+0.476
riction+0.453
spection+0.449
ordinary+0.440
Neg logit contributions
yond-0.839
swick-0.763
nance-0.744
hips-0.707
le-0.707
Token 20
Token ID1160
Feature activation-8.50e-01

Pos logit contributions
ngth+5.063
orsi+4.788
spection+4.619
ordinary+4.584
riction+4.574
Neg logit contributions
yond-7.045
swick-6.492
nance-6.217
hips-5.782
gency-5.744
Token-
Token ID12
Feature activation+5.52e-02

Pos logit contributions
yond+1.147
swick+1.030
nance+0.999
le+0.949
hips+0.945
Neg logit contributions
ngth-0.970
orsi-0.901
riction-0.862
spection-0.853
ordinary-0.841
Token27
Token ID1983
Feature activation+4.87e-01

Pos logit contributions
ngth+0.060
orsi+0.056
riction+0.054
spection+0.053
ordinary+0.052
Neg logit contributions
yond-0.077
swick-0.069
nance-0.067
le-0.064
hips-0.064
Token,
Token ID11
Feature activation-2.65e-01

Pos logit contributions
ngth+0.527
orsi+0.488
riction+0.467
spection+0.465
ordinary+0.456
Neg logit contributions
yond-0.686
swick-0.619
nance-0.602
hips-0.567
le-0.567
Token £
Token ID4248
Feature activation+3.47e+00

Pos logit contributions
yond+0.345
swick+0.308
nance+0.299
le+0.284
hips+0.283
Neg logit contributions
ngth-0.316
orsi-0.293
riction-0.281
spection-0.278
ordinary-0.274
Token super
Token ID2208
Feature activation+9.19e-01

Pos logit contributions
ngth+0.165
orsi+0.154
riction+0.147
spection+0.146
ordinary+0.143
Neg logit contributions
yond-0.177
swick-0.158
nance-0.153
le-0.145
hips-0.144
Token powered
Token ID13232
Feature activation+5.84e-01

Pos logit contributions
ngth+1.095
orsi+1.016
riction+0.981
spection+0.976
ordinary+0.964
Neg logit contributions
yond-1.190
swick-1.064
nance-1.033
le-0.968
hips-0.968
Token.
Token ID13
Feature activation+2.07e-01

Pos logit contributions
ngth+0.700
orsi+0.653
riction+0.627
spection+0.623
ordinary+0.612
Neg logit contributions
yond-0.755
swick-0.673
nance-0.653
le-0.615
hips-0.615
Token
Token ID198
Feature activation+3.88e-01

Pos logit contributions
ngth+0.293
orsi+0.276
riction+0.267
spection+0.264
ordinary+0.259
Neg logit contributions
yond-0.224
swick-0.196
nance-0.188
le-0.177
hips-0.176
Token
Token ID198
Feature activation+3.40e-01

Pos logit contributions
ngth+0.578
orsi+0.526
riction+0.501
spection+0.491
ordinary+0.478
Neg logit contributions
yond-0.429
swick-0.369
le-0.354
nance-0.353
hips-0.344
TokenCV
Token ID33538
Feature activation+5.01e+00

Pos logit contributions
ngth+0.391
orsi+0.362
riction+0.346
spection+0.344
ordinary+0.337
Neg logit contributions
yond-0.460
swick-0.412
nance-0.398
le-0.380
hips-0.379
Token:
Token ID25
Feature activation-6.88e-01

Pos logit contributions
ngth+4.388
GS+4.127
orsi+4.125
EMBER+4.046
riction+3.978
Neg logit contributions
yond-7.368
swick-6.922
nance-6.730
eous-6.197
hips-6.192
Token What
Token ID1867
Feature activation+3.30e-01

Pos logit contributions
yond+0.772
swick+0.688
nance+0.647
le+0.627
hips+0.623
Neg logit contributions
ngth-0.952
orsi-0.892
riction-0.860
spection-0.845
ordinary-0.830
Token made
Token ID925
Feature activation-1.09e+00

Pos logit contributions
ngth+0.394
orsi+0.366
riction+0.351
spection+0.349
ordinary+0.342
Neg logit contributions
yond-0.428
swick-0.381
nance-0.370
le-0.352
hips-0.350
Token Mid
Token ID7215
Feature activation-9.38e-01

Pos logit contributions
yond+1.414
swick+1.262
nance+1.226
le+1.175
hips+1.165
Neg logit contributions
ngth-1.290
orsi-1.212
spection-1.149
riction-1.148
ordinary-1.123
Tokenn
Token ID77
Feature activation-9.10e-02

Pos logit contributions
yond+0.962
swick+0.835
nance+0.805
le+0.776
hips+0.733
Neg logit contributions
ngth-1.412
orsi-1.315
 Pwr-1.252
riction-1.251
UGE-1.235
Token actions
Token ID4028
Feature activation-7.22e-02

Pos logit contributions
ngth+0.913
orsi+0.861
riction+0.827
spection+0.827
ordinary+0.823
Neg logit contributions
yond-0.908
swick-0.812
nance-0.786
hips-0.731
le-0.722
Token,
Token ID11
Feature activation+3.09e-01

Pos logit contributions
yond+0.093
swick+0.083
nance+0.080
le+0.075
hips+0.075
Neg logit contributions
ngth-0.087
orsi-0.081
riction-0.078
spection-0.078
ordinary-0.076
Token known
Token ID1900
Feature activation+8.73e-02

Pos logit contributions
ngth+0.365
orsi+0.340
riction+0.327
spection+0.325
ordinary+0.320
Neg logit contributions
yond-0.404
swick-0.362
nance-0.350
le-0.329
hips-0.329
Token as
Token ID355
Feature activation-8.52e-02

Pos logit contributions
ngth+0.109
orsi+0.103
riction+0.099
spection+0.099
ordinary+0.098
Neg logit contributions
yond-0.106
swick-0.094
nance-0.092
hips-0.085
le-0.084
Token "
Token ID366
Feature activation-1.68e+00

Pos logit contributions
yond+0.102
swick+0.091
nance+0.088
hips+0.082
le+0.081
Neg logit contributions
ngth-0.109
orsi-0.103
riction-0.099
spection-0.099
ordinary-0.098
Tokenextra
Token ID26086
Feature activation+5.01e+00

Pos logit contributions
yond+2.351
swick+2.110
nance+2.052
le+1.987
hips+1.947
Neg logit contributions
ngth-1.853
orsi-1.702
riction-1.629
spection-1.606
ordinary-1.551
Tokenordinary
Token ID35947
Feature activation+1.69e+00

Pos logit contributions
ngth+2.106
ordinary+1.990
orsi+1.726
spection+1.649
riction+1.502
Neg logit contributions
yond-9.943
swick-9.420
nance-9.196
hips-8.979
eous-8.638
Token measures
Token ID5260
Feature activation+1.42e+00

Pos logit contributions
ngth+1.781
orsi+1.704
ordinary+1.627
spection+1.612
riction+1.602
Neg logit contributions
yond-2.372
swick-2.156
nance-2.081
hips-1.953
le-1.929
Token,"
Token ID553
Feature activation-1.86e+00

Pos logit contributions
ngth+1.794
orsi+1.705
riction+1.649
spection+1.643
ordinary+1.613
Neg logit contributions
yond-1.689
swick-1.511
nance-1.460
le-1.334
hips-1.319
Token to
Token ID284
Feature activation+7.63e-02

Pos logit contributions
yond+2.294
swick+2.015
nance+1.955
le+1.872
hips+1.852
Neg logit contributions
ngth-2.354
orsi-2.175
riction-2.105
spection-2.096
ordinary-2.049
Token keep
Token ID1394
Feature activation-6.46e-02

Pos logit contributions
ngth+0.092
orsi+0.085
riction+0.082
spection+0.082
ordinary+0.080
Neg logit contributions
yond-0.099
swick-0.088
nance-0.086
le-0.081
hips-0.081
Token don
Token ID836
Feature activation-1.60e+00

Pos logit contributions
ngth+0.380
orsi+0.355
riction+0.341
spection+0.338
ordinary+0.333
Neg logit contributions
yond-0.400
swick-0.356
nance-0.345
le-0.324
hips-0.324
Token
Token ID447
Feature activation+6.94e-01

Pos logit contributions
yond+1.928
swick+1.704
nance+1.654
le+1.652
hips+1.610
Neg logit contributions
ngth-2.165
orsi-1.951
riction-1.860
spection-1.813
 Pwr-1.768
Token
Token ID247
Feature activation+8.68e-01

Pos logit contributions
ngth+1.054
orsi+0.984
riction+0.952
spection+0.949
ordinary+0.937
Neg logit contributions
yond-0.683
swick-0.580
nance-0.561
le-0.533
hips-0.531
Tokent
Token ID83
Feature activation+5.21e-01

Pos logit contributions
ngth+1.219
orsi+1.147
riction+1.110
spection+1.106
ordinary+1.091
Neg logit contributions
yond-0.942
swick-0.822
nance-0.790
hips-0.731
le-0.730
Token have
Token ID423
Feature activation+8.91e-01

Pos logit contributions
ngth+0.652
orsi+0.610
riction+0.588
spection+0.584
ordinary+0.576
Neg logit contributions
yond-0.644
swick-0.573
nance-0.554
le-0.519
hips-0.518
Token Vita
Token ID24113
Feature activation+5.00e+00

Pos logit contributions
ngth+0.989
orsi+0.918
riction+0.880
spection+0.874
ordinary+0.864
Neg logit contributions
yond-1.223
swick-1.102
nance-1.069
hips-1.008
le-1.005
Token-
Token ID12
Feature activation-2.80e-01

Pos logit contributions
ngth+5.763
orsi+5.290
riction+5.086
spection+5.063
ordinary+5.025
Neg logit contributions
yond-6.406
swick-5.802
nance-5.599
hips-5.287
gency-5.186
TokenMix
Token ID35608
Feature activation-3.64e-01

Pos logit contributions
yond+0.384
swick+0.345
nance+0.335
le+0.318
hips+0.317
Neg logit contributions
ngth-0.313
orsi-0.291
riction-0.278
spection-0.276
ordinary-0.271
Tokenes
Token ID274
Feature activation-7.01e-01

Pos logit contributions
yond+0.488
swick+0.438
nance+0.424
hips+0.399
le+0.398
Neg logit contributions
ngth-0.420
orsi-0.390
riction-0.375
spection-0.373
ordinary-0.366
Token,
Token ID11
Feature activation-9.11e-02

Pos logit contributions
yond+0.913
swick+0.816
nance+0.792
le+0.748
hips+0.747
Neg logit contributions
ngth-0.832
orsi-0.776
riction-0.744
spection-0.739
ordinary-0.728
Token this
Token ID428
Feature activation-2.89e-01

Pos logit contributions
yond+0.117
swick+0.104
nance+0.101
le+0.095
hips+0.095
Neg logit contributions
ngth-0.110
orsi-0.103
riction-0.099
spection-0.098
ordinary-0.097
Tokenclass
Token ID4871
Feature activation+8.59e-01

Pos logit contributions
yond+0.777
swick+0.710
nance+0.694
le+0.667
hips+0.664
Neg logit contributions
ngth-0.429
orsi-0.390
riction-0.368
spection-0.363
ordinary-0.356
Token carriers
Token ID16651
Feature activation-5.69e-01

Pos logit contributions
ngth+1.016
orsi+0.948
riction+0.911
spection+0.908
ordinary+0.892
Neg logit contributions
yond-1.119
swick-1.003
nance-0.967
le-0.911
hips-0.907
Token in
Token ID287
Feature activation-4.01e-01

Pos logit contributions
yond+0.692
swick+0.610
nance+0.592
hips+0.563
le+0.559
Neg logit contributions
ngth-0.730
orsi-0.681
riction-0.657
spection-0.650
ordinary-0.643
Token service
Token ID2139
Feature activation+1.74e-01

Pos logit contributions
yond+0.513
swick+0.455
nance+0.444
le+0.419
hips+0.418
Neg logit contributions
ngth-0.488
orsi-0.455
riction-0.436
spection-0.428
ordinary-0.426
Token (
Token ID357
Feature activation+2.17e-01

Pos logit contributions
ngth+0.229
orsi+0.214
riction+0.207
spection+0.205
ordinary+0.203
Neg logit contributions
yond-0.206
swick-0.182
nance-0.176
hips-0.165
le-0.165
TokenCV
Token ID33538
Feature activation+4.95e+00

Pos logit contributions
ngth+0.226
orsi+0.208
riction+0.199
spection+0.197
ordinary+0.193
Neg logit contributions
yond-0.316
swick-0.285
nance-0.278
le-0.265
hips-0.264
TokenN
Token ID45
Feature activation+2.86e-01

Pos logit contributions
ngth+5.029
orsi+4.771
GS+4.533
spection+4.527
riction+4.492
Neg logit contributions
yond-6.720
swick-6.155
nance-5.968
hips-5.628
gency-5.611
Token 68
Token ID8257
Feature activation-6.85e-01

Pos logit contributions
ngth+0.319
orsi+0.295
riction+0.283
spection+0.280
ordinary+0.276
Neg logit contributions
yond-0.395
swick-0.355
nance-0.345
le-0.327
hips-0.326
Token-
Token ID12
Feature activation-2.52e-01

Pos logit contributions
yond+0.909
swick+0.815
nance+0.791
le+0.748
hips+0.747
Neg logit contributions
ngth-0.797
orsi-0.741
riction-0.712
spection-0.704
ordinary-0.696
Token77
Token ID3324
Feature activation-1.70e-01

Pos logit contributions
yond+0.371
swick+0.336
nance+0.327
le+0.313
hips+0.311
Neg logit contributions
ngth-0.259
orsi-0.238
riction-0.227
spection-0.225
ordinary-0.219
Token),
Token ID828
Feature activation-8.61e-01

Pos logit contributions
yond+0.228
swick+0.205
nance+0.199
le+0.187
hips+0.187
Neg logit contributions
ngth-0.194
orsi-0.181
riction-0.173
spection-0.172
ordinary-0.169
Token of
Token ID286
Feature activation+7.70e-01

Pos logit contributions
yond+1.071
swick+0.945
nance+0.913
le+0.858
hips+0.853
Neg logit contributions
ngth-1.183
orsi-1.112
riction-1.072
spection-1.065
ordinary-1.050
Token raw
Token ID8246
Feature activation+1.32e-01

Pos logit contributions
ngth+0.925
orsi+0.863
riction+0.831
spection+0.825
ordinary+0.814
Neg logit contributions
yond-0.990
swick-0.884
nance-0.856
hips-0.804
le-0.802
Token food
Token ID2057
Feature activation-7.05e-02

Pos logit contributions
ngth+0.161
orsi+0.151
riction+0.145
spection+0.144
ordinary+0.142
Neg logit contributions
yond-0.168
swick-0.150
nance-0.146
hips-0.136
le-0.136
Token prep
Token ID3143
Feature activation+7.68e-01

Pos logit contributions
yond+0.094
swick+0.085
nance+0.082
le+0.078
hips+0.077
Neg logit contributions
ngth-0.081
orsi-0.076
riction-0.072
spection-0.072
ordinary-0.071
Token sans
Token ID38078
Feature activation-1.63e-02

Pos logit contributions
ngth+0.881
orsi+0.819
riction+0.786
spection+0.781
ordinary+0.768
Neg logit contributions
yond-1.031
swick-0.925
nance-0.897
le-0.846
hips-0.846
Token Vita
Token ID24113
Feature activation+4.89e+00

Pos logit contributions
yond+0.021
swick+0.019
nance+0.018
le+0.017
hips+0.017
Neg logit contributions
ngth-0.020
orsi-0.018
riction-0.018
spection-0.018
ordinary-0.017
Token should
Token ID815
Feature activation+2.87e-01

Pos logit contributions
ngth+4.907
orsi+4.389
spection+4.292
riction+4.211
ordinary+4.190
Neg logit contributions
yond-6.953
swick-6.255
nance-6.069
hips-5.803
gency-5.737
Token take
Token ID1011
Feature activation+2.13e+00

Pos logit contributions
ngth+0.335
orsi+0.313
riction+0.299
spection+0.297
ordinary+0.291
Neg logit contributions
yond-0.382
swick-0.342
nance-0.333
le-0.315
hips-0.314
Token heart
Token ID2612
Feature activation-4.38e-01

Pos logit contributions
ngth+2.336
orsi+2.165
riction+2.071
spection+2.065
ordinary+2.035
Neg logit contributions
yond-2.962
swick-2.669
nance-2.586
hips-2.445
le-2.429
Token:
Token ID25
Feature activation-3.26e-01

Pos logit contributions
yond+0.589
swick+0.529
nance+0.514
hips+0.483
le+0.482
Neg logit contributions
ngth-0.502
orsi-0.467
riction-0.447
spection-0.446
ordinary-0.438
Token it
Token ID340
Feature activation+2.18e-01

Pos logit contributions
yond+0.405
swick+0.360
nance+0.348
le+0.329
hips+0.327
Neg logit contributions
ngth-0.406
orsi-0.381
riction-0.367
spection-0.364
ordinary-0.357
Token beating
Token ID11226
Feature activation-4.69e-01

Pos logit contributions
yond+0.009
swick+0.008
nance+0.008
le+0.008
hips+0.008
Neg logit contributions
ngth-0.010
orsi-0.009
riction-0.009
spection-0.009
ordinary-0.009
Token out
Token ID503
Feature activation-6.58e-01

Pos logit contributions
yond+0.497
swick+0.432
nance+0.415
le+0.383
hips+0.383
Neg logit contributions
ngth-0.671
orsi-0.633
riction-0.613
spection-0.609
ordinary-0.602
Token competitors
Token ID13861
Feature activation+5.07e-01

Pos logit contributions
yond+0.817
swick+0.726
nance+0.703
le+0.664
hips+0.662
Neg logit contributions
ngth-0.823
orsi-0.768
riction-0.739
spection-0.735
ordinary-0.724
Token like
Token ID588
Feature activation+7.84e-02

Pos logit contributions
ngth+0.581
orsi+0.541
riction+0.518
spection+0.515
ordinary+0.507
Neg logit contributions
yond-0.681
swick-0.611
nance-0.593
le-0.559
hips-0.557
Token the
Token ID262
Feature activation+2.77e-02

Pos logit contributions
ngth+0.102
orsi+0.096
riction+0.092
spection+0.092
ordinary+0.090
Neg logit contributions
yond-0.093
swick-0.082
nance-0.079
le-0.074
hips-0.074
Token PlayStation
Token ID14047
Feature activation+4.88e+00

Pos logit contributions
ngth+0.034
orsi+0.031
riction+0.030
spection+0.030
ordinary+0.030
Neg logit contributions
yond-0.035
swick-0.031
nance-0.030
le-0.029
hips-0.029
Token 4
Token ID604
Feature activation-5.90e-01

Pos logit contributions
ngth+4.956
orsi+4.694
spection+4.408
riction+4.403
GS+4.289
Neg logit contributions
yond-6.870
swick-6.257
nance-5.970
gency-5.681
hips-5.609
Token and
Token ID290
Feature activation-1.80e-01

Pos logit contributions
yond+0.721
swick+0.641
nance+0.621
le+0.587
hips+0.583
Neg logit contributions
ngth-0.748
orsi-0.701
riction-0.677
spection-0.672
ordinary-0.662
Token Wii
Token ID16591
Feature activation+1.71e+00

Pos logit contributions
yond+0.229
swick+0.204
nance+0.197
le+0.186
hips+0.186
Neg logit contributions
ngth-0.219
orsi-0.204
riction-0.197
spection-0.196
ordinary-0.192
Token U
Token ID471
Feature activation+1.10e+00

Pos logit contributions
ngth+2.087
orsi+1.955
riction+1.870
spection+1.866
ordinary+1.833
Neg logit contributions
yond-2.171
swick-1.931
nance-1.872
le-1.752
hips-1.749
Token.
Token ID13
Feature activation-2.20e-01

Pos logit contributions
ngth+1.244
orsi+1.158
riction+1.107
spection+1.101
ordinary+1.082
Neg logit contributions
yond-1.496
swick-1.343
nance-1.306
le-1.228
hips-1.227
Token"
Token ID1
Feature activation-1.67e+00

Pos logit contributions
yond+0.207
swick+0.183
nance+0.177
le+0.167
hips+0.166
Neg logit contributions
ngth-0.215
orsi-0.202
riction-0.195
spection-0.193
ordinary-0.189
Token will
Token ID481
Feature activation-6.23e-01

Pos logit contributions
yond+2.325
swick+2.090
nance+2.026
le+1.941
hips+1.924
Neg logit contributions
ngth-1.857
orsi-1.715
riction-1.647
spection-1.631
ordinary-1.589
Token be
Token ID307
Feature activation-1.09e+00

Pos logit contributions
yond+0.737
swick+0.651
nance+0.629
le+0.590
hips+0.588
Neg logit contributions
ngth-0.818
orsi-0.768
riction-0.739
spection-0.735
ordinary-0.724
Token appearing
Token ID12655
Feature activation-2.85e+00

Pos logit contributions
yond+1.297
swick+1.139
nance+1.099
le+1.039
hips+1.033
Neg logit contributions
ngth-1.441
orsi-1.351
riction-1.300
spection-1.291
ordinary-1.269
Token on
Token ID319
Feature activation-3.61e-01

Pos logit contributions
yond+3.281
swick+2.804
nance+2.704
hips+2.636
le+2.608
Neg logit contributions
ngth-3.851
orsi-3.650
riction-3.491
spection-3.447
ordinary-3.406
Token PlayStation
Token ID14047
Feature activation+4.87e+00

Pos logit contributions
yond+0.467
swick+0.418
nance+0.405
hips+0.381
le+0.381
Neg logit contributions
ngth-0.431
orsi-0.402
riction-0.386
spection-0.384
ordinary-0.378
Token 4
Token ID604
Feature activation-4.06e-01

Pos logit contributions
ngth+4.599
orsi+4.215
spection+4.030
riction+4.028
GS+3.982
Neg logit contributions
yond-7.076
swick-6.581
nance-6.336
gency-6.003
hips-5.940
Token and
Token ID290
Feature activation-2.73e-01

Pos logit contributions
yond+0.508
swick+0.446
nance+0.433
hips+0.411
le+0.410
Neg logit contributions
ngth-0.510
orsi-0.478
riction-0.457
spection-0.455
ordinary-0.449
Token Xbox
Token ID9445
Feature activation+1.34e+00

Pos logit contributions
yond+0.362
swick+0.324
nance+0.314
le+0.299
hips+0.298
Neg logit contributions
ngth-0.318
orsi-0.298
riction-0.286
spection-0.283
ordinary-0.277
Token One
Token ID1881
Feature activation+5.68e-01

Pos logit contributions
ngth+1.463
orsi+1.348
riction+1.293
spection+1.269
ordinary+1.258
Neg logit contributions
yond-1.837
swick-1.674
nance-1.639
gency-1.523
le-1.511
Token any
Token ID597
Feature activation-6.31e-01

Pos logit contributions
ngth+0.703
orsi+0.657
riction+0.632
spection+0.628
ordinary+0.619
Neg logit contributions
yond-0.713
swick-0.634
nance-0.614
le-0.577
hips-0.576
Token on
Token ID319
Feature activation-1.29e-01

Pos logit contributions
yond+2.366
swick+2.088
nance+2.025
le+1.908
hips+1.900
Neg logit contributions
ngth-2.509
orsi-2.346
riction-2.260
spection-2.246
ordinary-2.216
Token Twitter
Token ID3009
Feature activation+1.41e+00

Pos logit contributions
yond+0.157
swick+0.140
nance+0.134
le+0.125
hips+0.125
Neg logit contributions
ngth-0.163
orsi-0.154
riction-0.148
spection-0.148
ordinary-0.145
Token as
Token ID355
Feature activation+4.98e-02

Pos logit contributions
ngth+1.553
orsi+1.446
spection+1.388
riction+1.384
ordinary+1.355
Neg logit contributions
yond-1.925
swick-1.739
nance-1.696
hips-1.572
le-1.566
Token an
Token ID281
Feature activation+5.48e-01

Pos logit contributions
ngth+0.060
orsi+0.056
riction+0.053
spection+0.053
ordinary+0.052
Neg logit contributions
yond-0.064
swick-0.058
nance-0.056
hips-0.052
le-0.052
Token "
Token ID366
Feature activation-1.66e+00

Pos logit contributions
ngth+0.709
orsi+0.673
riction+0.650
spection+0.645
ordinary+0.643
Neg logit contributions
yond-0.647
swick-0.569
nance-0.549
hips-0.513
le-0.508
Tokenextra
Token ID26086
Feature activation+4.87e+00

Pos logit contributions
yond+2.152
swick+1.913
nance+1.865
le+1.776
hips+1.760
Neg logit contributions
ngth-1.995
orsi-1.851
riction-1.773
spection-1.756
ordinary-1.701
Token level
Token ID1241
Feature activation+3.09e-01

Pos logit contributions
ngth+2.398
ordinary+2.213
orsi+1.936
spection+1.914
riction+1.835
Neg logit contributions
yond-9.522
swick-8.983
nance-8.635
hips-8.528
le-8.144
Token of
Token ID286
Feature activation+7.81e-01

Pos logit contributions
ngth+0.418
orsi+0.397
riction+0.385
ordinary+0.385
spection+0.381
Neg logit contributions
yond-0.348
swick-0.310
nance-0.291
hips-0.269
le-0.267
Token safety
Token ID3747
Feature activation+1.52e+00

Pos logit contributions
ngth+0.843
orsi+0.778
riction+0.746
spection+0.744
ordinary+0.730
Neg logit contributions
yond-1.103
swick-0.997
nance-0.966
hips-0.913
le-0.912
Token."
Token ID526
Feature activation-1.12e+00

Pos logit contributions
ngth+1.866
orsi+1.752
spection+1.715
riction+1.706
ordinary+1.665
Neg logit contributions
yond-1.896
swick-1.700
nance-1.633
hips-1.526
le-1.511
Token It
Token ID632
Feature activation+9.58e-02

Pos logit contributions
yond+1.294
swick+1.151
nance+1.101
le+1.042
hips+1.034
Neg logit contributions
ngth-1.490
orsi-1.395
riction-1.346
spection-1.332
ordinary-1.312
Tokenray
Token ID2433
Feature activation-4.97e-01

Pos logit contributions
yond+0.297
swick+0.262
nance+0.253
hips+0.235
le+0.235
Neg logit contributions
ngth-0.340
orsi-0.320
riction-0.309
spection-0.308
ordinary-0.304
Token,
Token ID11
Feature activation-1.62e-01

Pos logit contributions
yond+0.632
swick+0.564
nance+0.547
le+0.515
hips+0.515
Neg logit contributions
ngth-0.607
orsi-0.566
riction-0.544
spection-0.539
ordinary-0.531
Token along
Token ID1863
Feature activation+7.10e-01

Pos logit contributions
yond+0.206
swick+0.183
nance+0.177
le+0.167
hips+0.166
Neg logit contributions
ngth-0.197
orsi-0.184
riction-0.176
spection-0.176
ordinary-0.173
Token with
Token ID351
Feature activation-4.26e-02

Pos logit contributions
ngth+1.023
orsi+0.966
riction+0.935
spection+0.930
ordinary+0.918
Neg logit contributions
yond-0.744
swick-0.646
nance-0.621
le-0.573
hips-0.573
Token bonus
Token ID7202
Feature activation+1.15e+00

Pos logit contributions
yond+0.056
swick+0.050
nance+0.048
hips+0.045
le+0.045
Neg logit contributions
ngth-0.051
orsi-0.047
riction-0.045
spection-0.045
ordinary-0.044
Token DLC
Token ID18068
Feature activation+4.81e+00

Pos logit contributions
ngth+1.451
orsi+1.355
spection+1.308
riction+1.303
ordinary+1.294
Neg logit contributions
yond-1.404
swick-1.251
nance-1.207
hips-1.127
le-1.124
Token and
Token ID290
Feature activation-2.95e-01

Pos logit contributions
ngth+5.411
spection+4.823
orsi+4.817
ordinary+4.712
riction+4.611
Neg logit contributions
yond-6.282
swick-5.786
nance-5.524
gency-5.102
le-5.027
Token a
Token ID257
Feature activation+8.51e-01

Pos logit contributions
yond+0.376
swick+0.335
nance+0.325
le+0.306
hips+0.306
Neg logit contributions
ngth-0.358
orsi-0.335
riction-0.322
spection-0.319
ordinary-0.314
Token mini
Token ID9927
Feature activation+1.39e+00

Pos logit contributions
ngth+1.031
orsi+0.962
riction+0.925
spection+0.920
ordinary+0.906
Neg logit contributions
yond-1.088
swick-0.971
nance-0.940
le-0.883
hips-0.883
Token license
Token ID5964
Feature activation-1.15e+00

Pos logit contributions
ngth+1.551
orsi+1.428
spection+1.377
riction+1.374
ordinary+1.365
Neg logit contributions
yond-1.888
swick-1.706
nance-1.655
hips-1.559
le-1.547
Token plate
Token ID7480
Feature activation+5.88e-01

Pos logit contributions
yond+1.445
swick+1.278
nance+1.244
le+1.185
hips+1.179
Neg logit contributions
ngth-1.413
orsi-1.329
riction-1.268
spection-1.252
ordinary-1.231
Token what
Token ID644
Feature activation+3.27e-01

Pos logit contributions
yond+0.418
swick+0.371
nance+0.359
le+0.337
hips+0.336
Neg logit contributions
ngth-0.419
orsi-0.393
riction-0.378
spection-0.375
ordinary-0.370
Token's
Token ID338
Feature activation-2.46e-01

Pos logit contributions
ngth+0.396
orsi+0.370
riction+0.355
spection+0.353
ordinary+0.349
Neg logit contributions
yond-0.417
swick-0.372
nance-0.361
hips-0.338
le-0.336
Token on
Token ID319
Feature activation-7.91e-02

Pos logit contributions
yond+0.286
swick+0.252
nance+0.244
le+0.227
hips+0.227
Neg logit contributions
ngth-0.326
orsi-0.306
riction-0.296
spection-0.294
ordinary-0.290
Token the
Token ID262
Feature activation-1.78e-01

Pos logit contributions
yond+0.105
swick+0.094
nance+0.091
hips+0.086
le+0.086
Neg logit contributions
ngth-0.091
orsi-0.085
riction-0.081
spection-0.081
ordinary-0.080
Token D
Token ID360
Feature activation+1.01e+00

Pos logit contributions
yond+0.213
swick+0.189
nance+0.182
le+0.171
hips+0.171
Neg logit contributions
ngth-0.230
orsi-0.215
riction-0.208
spection-0.206
ordinary-0.203
TokenVR
Token ID13024
Feature activation+4.81e+00

Pos logit contributions
ngth+0.925
orsi+0.853
riction+0.806
spection+0.792
ordinary+0.778
Neg logit contributions
yond-1.576
swick-1.445
nance-1.402
hips-1.331
le-1.328
Token.
Token ID13
Feature activation-9.36e-02

Pos logit contributions
ngth+4.865
orsi+4.606
spection+4.497
riction+4.345
ordinary+4.288
Neg logit contributions
yond-6.606
swick-6.016
nance-5.729
hips-5.419
gency-5.299
Token Streaming
Token ID43124
Feature activation-9.36e-01

Pos logit contributions
yond+0.104
swick+0.092
nance+0.088
le+0.083
hips+0.082
Neg logit contributions
ngth-0.130
orsi-0.122
riction-0.118
spection-0.116
ordinary-0.115
Token lets
Token ID8781
Feature activation+1.23e+00

Pos logit contributions
yond+1.138
swick+1.003
nance+0.972
le+0.924
hips+0.923
Neg logit contributions
ngth-1.206
orsi-1.123
riction-1.080
spection-1.072
ordinary-1.053
Token you
Token ID345
Feature activation-7.08e-01

Pos logit contributions
ngth+1.400
orsi+1.297
riction+1.247
spection+1.235
ordinary+1.222
Neg logit contributions
yond-1.663
swick-1.495
nance-1.448
hips-1.359
le-1.355
Token do
Token ID466
Feature activation-1.69e+00

Pos logit contributions
yond+0.899
swick+0.799
nance+0.777
hips+0.737
le+0.737
Neg logit contributions
ngth-0.868
orsi-0.813
riction-0.779
spection-0.774
ordinary-0.756
Token added
Token ID2087
Feature activation+2.44e+00

Pos logit contributions
yond+0.082
swick+0.073
nance+0.071
le+0.067
hips+0.067
Neg logit contributions
ngth-0.079
orsi-0.074
riction-0.071
spection-0.071
ordinary-0.070
Token borrowing
Token ID23669
Feature activation+1.95e-01

Pos logit contributions
ngth+2.878
orsi+2.756
ordinary+2.659
riction+2.656
spection+2.627
Neg logit contributions
yond-3.053
swick-2.744
nance-2.610
hips-2.467
le-2.422
Token,
Token ID11
Feature activation+1.96e-01

Pos logit contributions
ngth+0.230
orsi+0.214
riction+0.206
spection+0.204
ordinary+0.201
Neg logit contributions
yond-0.257
swick-0.230
nance-0.223
le-0.210
hips-0.210
Token those
Token ID883
Feature activation-4.83e-01

Pos logit contributions
ngth+0.231
orsi+0.218
riction+0.208
spection+0.207
ordinary+0.206
Neg logit contributions
yond-0.255
swick-0.230
nance-0.221
hips-0.207
le-0.206
Token "
Token ID366
Feature activation-1.59e+00

Pos logit contributions
yond+0.573
swick+0.508
nance+0.490
le+0.456
hips+0.455
Neg logit contributions
ngth-0.625
orsi-0.590
riction-0.567
spection-0.562
ordinary-0.558
Tokenextra
Token ID26086
Feature activation+4.79e+00

Pos logit contributions
yond+2.185
swick+1.961
nance+1.904
le+1.827
hips+1.810
Neg logit contributions
ngth-1.781
orsi-1.649
riction-1.578
spection-1.565
ordinary-1.519
Tokenordinary
Token ID35947
Feature activation+1.91e+00

Pos logit contributions
ngth+4.997
ordinary+4.767
orsi+4.724
spection+4.503
riction+4.495
Neg logit contributions
yond-6.560
swick-6.006
nance-5.784
hips-5.516
eous-5.300
Token measures
Token ID5260
Feature activation+1.34e+00

Pos logit contributions
ngth+2.354
orsi+2.259
ordinary+2.176
riction+2.161
spection+2.147
Neg logit contributions
yond-2.336
swick-2.085
nance-2.002
hips-1.853
le-1.843
Token"
Token ID1
Feature activation-2.01e+00

Pos logit contributions
ngth+1.649
orsi+1.558
riction+1.496
spection+1.482
ordinary+1.466
Neg logit contributions
yond-1.665
swick-1.481
nance-1.443
le-1.336
hips-1.328
Token will
Token ID481
Feature activation-5.25e-01

Pos logit contributions
yond+2.576
swick+2.304
nance+2.212
le+2.126
hips+2.124
Neg logit contributions
ngth-2.423
orsi-2.220
spection-2.153
riction-2.152
ordinary-2.095
Token be
Token ID307
Feature activation-1.01e+00

Pos logit contributions
yond+0.647
swick+0.574
nance+0.556
le+0.523
hips+0.522
Neg logit contributions
ngth-0.663
orsi-0.620
riction-0.596
spection-0.594
ordinary-0.584
Tokenun
Token ID403
Feature activation-3.19e-01

Pos logit contributions
ngth+0.347
orsi+0.322
riction+0.309
spection+0.306
ordinary+0.300
Neg logit contributions
yond-0.416
swick-0.373
nance-0.362
le-0.344
hips-0.343
Tokensuccessfully
Token ID37351
Feature activation+1.09e+00

Pos logit contributions
yond+0.563
swick+0.519
nance+0.508
le+0.488
hips+0.487
Neg logit contributions
ngth-0.232
orsi-0.206
riction-0.192
spection-0.189
ordinary-0.184
Token)
Token ID8
Feature activation-1.35e+00

Pos logit contributions
ngth+0.980
orsi+0.917
spection+0.857
riction+0.851
ordinary+0.831
Neg logit contributions
yond-1.683
swick-1.549
nance-1.514
hips-1.410
le-1.402
Token to
Token ID284
Feature activation-2.49e-01

Pos logit contributions
yond+1.824
swick+1.645
nance+1.595
hips+1.497
le+1.481
Neg logit contributions
ngth-1.539
orsi-1.443
riction-1.367
spection-1.365
ordinary-1.349
Token spray
Token ID11662
Feature activation-1.82e+00

Pos logit contributions
yond+0.299
swick+0.263
nance+0.256
le+0.240
hips+0.239
Neg logit contributions
ngth-0.322
orsi-0.301
riction-0.291
spection-0.289
ordinary-0.284
Token anth
Token ID26794
Feature activation-6.68e+00

Pos logit contributions
yond+2.415
swick+2.121
nance+2.105
le+2.014
hips+1.992
Neg logit contributions
ngth-2.106
orsi-1.958
riction-1.896
spection-1.871
ordinary-1.819
Tokenrax
Token ID32040
Feature activation+1.10e+00

Pos logit contributions
yond+7.820
nance+7.189
le+7.111
swick+6.870
hips+6.818
Neg logit contributions
ngth-7.662
EMBER-6.969
orsi-6.841
PDATE-6.837
UGE-6.728
Token spores
Token ID47306
Feature activation-1.88e+00

Pos logit contributions
ngth+1.386
orsi+1.301
riction+1.243
spection+1.243
ordinary+1.230
Neg logit contributions
yond-1.351
swick-1.211
nance-1.159
le-1.078
hips-1.077
Token over
Token ID625
Feature activation+2.33e-01

Pos logit contributions
yond+2.140
swick+1.841
nance+1.801
hips+1.713
le+1.711
Neg logit contributions
ngth-2.553
orsi-2.389
riction-2.316
spection-2.292
ordinary-2.252
Token Tokyo
Token ID11790
Feature activation-6.77e-01

Pos logit contributions
ngth+0.292
orsi+0.273
riction+0.263
spection+0.262
ordinary+0.258
Neg logit contributions
yond-0.287
swick-0.255
nance-0.246
le-0.231
hips-0.231
Token.
Token ID13
Feature activation-2.59e-03

Pos logit contributions
yond+0.894
swick+0.799
nance+0.778
le+0.734
hips+0.732
Neg logit contributions
ngth-0.793
orsi-0.736
riction-0.709
spection-0.702
ordinary-0.690
Token is
Token ID318
Feature activation+9.81e-01

Pos logit contributions
ngth+1.738
orsi+1.638
riction+1.565
spection+1.557
ordinary+1.537
Neg logit contributions
yond-1.924
swick-1.727
nance-1.680
le-1.566
hips-1.556
Token determined
Token ID5295
Feature activation+1.27e+00

Pos logit contributions
ngth+1.117
orsi+1.039
riction+0.996
spection+0.989
ordinary+0.974
Neg logit contributions
yond-1.324
swick-1.190
nance-1.154
le-1.088
hips-1.087
Token by
Token ID416
Feature activation-9.09e-02

Pos logit contributions
ngth+1.458
orsi+1.379
spection+1.324
riction+1.323
ordinary+1.292
Neg logit contributions
yond-1.654
swick-1.516
nance-1.447
hips-1.336
le-1.330
Token how
Token ID703
Feature activation+1.24e+00

Pos logit contributions
yond+0.123
swick+0.111
nance+0.108
le+0.102
hips+0.102
Neg logit contributions
ngth-0.103
orsi-0.096
riction-0.092
spection-0.091
ordinary-0.090
Token the
Token ID262
Feature activation+5.79e-03

Pos logit contributions
ngth+1.313
orsi+1.219
riction+1.168
spection+1.154
ordinary+1.142
Neg logit contributions
yond-1.761
swick-1.603
nance-1.548
hips-1.461
le-1.459
Token carc
Token ID36756
Feature activation-6.64e+00

Pos logit contributions
ngth+0.007
orsi+0.006
riction+0.006
spection+0.006
ordinary+0.006
Neg logit contributions
yond-0.008
swick-0.007
nance-0.007
le-0.006
hips-0.006
Tokenass
Token ID562
Feature activation-8.19e-01

Pos logit contributions
yond+7.959
nance+7.189
le+6.810
swick+6.766
hips+6.455
Neg logit contributions
ngth-7.859
orsi-7.198
EMBER-7.023
UGE-7.023
spection-6.834
Token is
Token ID318
Feature activation+6.43e-01

Pos logit contributions
yond+1.052
swick+0.938
nance+0.910
le+0.858
hips+0.856
Neg logit contributions
ngth-0.987
orsi-0.921
riction-0.885
spection-0.879
ordinary-0.866
Token scored
Token ID7781
Feature activation+1.17e+00

Pos logit contributions
ngth+0.725
orsi+0.672
riction+0.644
spection+0.639
ordinary+0.628
Neg logit contributions
yond-0.879
swick-0.789
nance-0.767
le-0.726
hips-0.724
Token for
Token ID329
Feature activation-7.25e-01

Pos logit contributions
ngth+1.367
orsi+1.277
riction+1.222
spection+1.218
ordinary+1.197
Neg logit contributions
yond-1.548
swick-1.394
nance-1.346
hips-1.263
le-1.260
Token things
Token ID1243
Feature activation-3.60e-01

Pos logit contributions
yond+0.930
swick+0.826
nance+0.805
le+0.761
hips+0.756
Neg logit contributions
ngth-0.879
orsi-0.818
riction-0.785
spection-0.776
ordinary-0.767
Token,
Token ID11
Feature activation-5.02e-02

Pos logit contributions
ngth+1.665
orsi+1.556
spection+1.487
riction+1.483
ordinary+1.463
Neg logit contributions
yond-1.857
swick-1.663
nance-1.622
gency-1.486
le-1.479
Token Liam
Token ID31684
Feature activation-5.54e-02

Pos logit contributions
yond+0.062
swick+0.055
nance+0.053
le+0.050
hips+0.050
Neg logit contributions
ngth-0.063
orsi-0.059
riction-0.057
spection-0.056
ordinary-0.056
Token,
Token ID11
Feature activation-6.54e-02

Pos logit contributions
yond+0.071
swick+0.063
nance+0.061
hips+0.057
le+0.056
Neg logit contributions
ngth-0.067
orsi-0.063
riction-0.061
spection-0.060
ordinary-0.059
Token Stella
Token ID45856
Feature activation+2.76e+00

Pos logit contributions
yond+0.088
swick+0.078
nance+0.076
le+0.072
hips+0.072
Neg logit contributions
ngth-0.076
orsi-0.070
riction-0.067
spection-0.067
ordinary-0.066
Token,
Token ID11
Feature activation-5.30e-02

Pos logit contributions
ngth+3.100
orsi+2.850
spection+2.743
riction+2.723
ordinary+2.716
Neg logit contributions
yond-3.655
swick-3.259
nance-3.218
gency-2.986
hips-2.956
Token Hatt
Token ID48509
Feature activation-6.58e+00

Pos logit contributions
yond+0.066
swick+0.058
nance+0.056
hips+0.053
le+0.053
Neg logit contributions
ngth-0.066
orsi-0.062
riction-0.060
spection-0.059
ordinary-0.058
Tokenie
Token ID494
Feature activation-6.14e-01

Pos logit contributions
yond+5.691
swick+4.945
nance+4.683
le+4.621
hips+4.322
Neg logit contributions
ngth-10.320
orsi-9.484
spection-9.381
riction-9.311
 Pwr-9.198
Token and
Token ID290
Feature activation+4.03e-01

Pos logit contributions
yond+0.812
swick+0.722
nance+0.705
hips+0.656
gency+0.650
Neg logit contributions
ngth-0.716
orsi-0.667
spection-0.638
riction-0.636
ordinary-0.625
Token Finn
Token ID15368
Feature activation+7.13e-01

Pos logit contributions
ngth+0.492
orsi+0.461
riction+0.443
spection+0.441
ordinary+0.435
Neg logit contributions
yond-0.506
swick-0.452
nance-0.438
hips-0.409
le-0.408
Token,
Token ID11
Feature activation+6.41e-02

Pos logit contributions
ngth+0.833
orsi+0.777
riction+0.748
spection+0.744
ordinary+0.732
Neg logit contributions
yond-0.939
swick-0.832
nance-0.812
hips-0.758
gency-0.748
Token and
Token ID290
Feature activation+5.38e-01

Pos logit contributions
ngth+0.077
orsi+0.071
riction+0.069
spection+0.068
ordinary+0.067
Neg logit contributions
yond-0.083
swick-0.074
nance-0.072
le-0.068
hips-0.068
Tokenlez
Token ID36858
Feature activation+1.18e+00

Pos logit contributions
yond+0.641
le+0.395
swick+0.358
nance+0.340
hips+0.268
Neg logit contributions
ngth-3.079
orsi-2.851
riction-2.806
spection-2.805
 Pwr-2.798
Tokenal
Token ID282
Feature activation+1.43e-01

Pos logit contributions
ngth+1.903
orsi+1.793
spection+1.739
riction+1.739
ordinary+1.701
Neg logit contributions
yond-1.065
swick-0.887
nance-0.859
le-0.810
hips-0.780
Token slide
Token ID10649
Feature activation+1.31e-01

Pos logit contributions
ngth+0.176
orsi+0.165
riction+0.158
spection+0.157
ordinary+0.155
Neg logit contributions
yond-0.179
swick-0.159
nance-0.154
le-0.144
hips-0.144
Token on
Token ID319
Feature activation-2.47e-01

Pos logit contributions
ngth+0.154
orsi+0.143
riction+0.137
spection+0.137
ordinary+0.135
Neg logit contributions
yond-0.171
swick-0.153
nance-0.149
hips-0.140
le-0.140
Token the
Token ID262
Feature activation-4.99e-01

Pos logit contributions
yond+0.318
swick+0.284
nance+0.276
le+0.260
hips+0.259
Neg logit contributions
ngth-0.296
orsi-0.276
riction-0.265
spection-0.263
ordinary-0.259
Token Cait
Token ID34118
Feature activation-6.25e+00

Pos logit contributions
yond+0.609
swick+0.540
nance+0.523
le+0.491
hips+0.489
Neg logit contributions
ngth-0.634
orsi-0.593
riction-0.571
spection-0.568
ordinary-0.559
Tokenlyn
Token ID6213
Feature activation-1.35e+00

Pos logit contributions
yond+4.041
swick+3.172
le+3.057
nance+2.988
hips+2.661
Neg logit contributions
ngth-11.311
orsi-10.660
spection-10.167
riction-10.114
ordinary-10.053
Token Jenner
Token ID39760
Feature activation+1.11e-01

Pos logit contributions
yond+1.433
swick+1.250
nance+1.201
le+1.117
hips+1.111
Neg logit contributions
ngth-1.921
orsi-1.810
riction-1.749
spection-1.739
ordinary-1.719
Token comparisons
Token ID17909
Feature activation-4.29e-01

Pos logit contributions
ngth+0.135
orsi+0.126
riction+0.121
spection+0.121
ordinary+0.119
Neg logit contributions
yond-0.141
swick-0.125
nance-0.121
hips-0.114
le-0.114
Token
Token ID960
Feature activation-2.14e-01

Pos logit contributions
yond+0.571
swick+0.511
nance+0.496
le+0.467
hips+0.467
Neg logit contributions
ngth-0.498
orsi-0.464
riction-0.445
spection-0.442
ordinary-0.435
Tokenand
Token ID392
Feature activation+1.04e+00

Pos logit contributions
yond+0.293
swick+0.263
nance+0.255
le+0.243
hips+0.242
Neg logit contributions
ngth-0.241
orsi-0.223
riction-0.214
spection-0.212
ordinary-0.208
TokenBut
Token ID1537
Feature activation+1.38e+00

Pos logit contributions
ngth+0.291
orsi+0.269
riction+0.258
spection+0.255
ordinary+0.250
Neg logit contributions
yond-0.318
swick-0.283
nance-0.275
le-0.263
hips-0.260
Token the
Token ID262
Feature activation-4.04e-02

Pos logit contributions
ngth+1.635
orsi+1.525
riction+1.463
spection+1.455
ordinary+1.432
Neg logit contributions
yond-1.806
swick-1.617
nance-1.566
le-1.474
hips-1.473
Token people
Token ID661
Feature activation-8.12e-01

Pos logit contributions
yond+0.051
swick+0.045
nance+0.044
le+0.041
hips+0.041
Neg logit contributions
ngth-0.050
orsi-0.047
riction-0.045
spection-0.045
ordinary-0.044
Token scoring
Token ID9689
Feature activation+8.12e-01

Pos logit contributions
yond+0.968
swick+0.857
nance+0.828
le+0.784
hips+0.782
Neg logit contributions
ngth-1.055
orsi-0.981
riction-0.952
spection-0.944
ordinary-0.931
Token the
Token ID262
Feature activation-2.97e-01

Pos logit contributions
ngth+0.938
orsi+0.871
riction+0.836
spection+0.830
ordinary+0.816
Neg logit contributions
yond-1.085
swick-0.972
nance-0.944
le-0.892
hips-0.890
Token carc
Token ID36756
Feature activation-6.22e+00

Pos logit contributions
yond+0.384
swick+0.342
nance+0.332
le+0.315
hips+0.313
Neg logit contributions
ngth-0.357
orsi-0.332
riction-0.319
spection-0.316
ordinary-0.311
Tokenasses
Token ID13978
Feature activation+2.80e-02

Pos logit contributions
yond+7.366
nance+6.570
le+6.489
swick+6.343
hips+6.179
Neg logit contributions
ngth-7.580
PDATE-7.196
UGE-6.862
EMBER-6.744
orsi-6.740
Token are
Token ID389
Feature activation+7.17e-02

Pos logit contributions
ngth+0.035
orsi+0.032
riction+0.031
spection+0.031
ordinary+0.030
Neg logit contributions
yond-0.035
swick-0.031
nance-0.030
hips-0.029
le-0.029
Token employees
Token ID4409
Feature activation-9.03e-01

Pos logit contributions
ngth+0.082
orsi+0.076
riction+0.073
spection+0.072
ordinary+0.071
Neg logit contributions
yond-0.097
swick-0.087
nance-0.085
le-0.081
hips-0.080
Token of
Token ID286
Feature activation+7.16e-01

Pos logit contributions
yond+1.011
swick+0.886
nance+0.854
le+0.795
hips+0.795
Neg logit contributions
ngth-1.237
orsi-1.164
riction-1.124
spection-1.118
ordinary-1.103
Token the
Token ID262
Feature activation-2.50e-01

Pos logit contributions
ngth+0.840
orsi+0.784
riction+0.753
spection+0.752
ordinary+0.739
Neg logit contributions
yond-0.939
swick-0.841
nance-0.812
hips-0.766
le-0.761
Token they
Token ID484
Feature activation-1.34e+00

Pos logit contributions
ngth+1.357
orsi+1.270
riction+1.222
spection+1.214
ordinary+1.193
Neg logit contributions
yond-1.362
swick-1.231
nance-1.188
le-1.090
hips-1.084
Token need
Token ID761
Feature activation+3.31e-02

Pos logit contributions
yond+1.293
swick+1.112
nance+1.071
le+1.004
hips+1.000
Neg logit contributions
ngth-2.009
orsi-1.885
riction-1.841
spection-1.840
ordinary-1.826
Token to
Token ID284
Feature activation-5.93e-02

Pos logit contributions
ngth+0.039
orsi+0.036
riction+0.035
spection+0.035
ordinary+0.034
Neg logit contributions
yond-0.044
swick-0.039
nance-0.038
hips-0.036
le-0.035
Token enter
Token ID3802
Feature activation+5.10e-01

Pos logit contributions
yond+0.074
swick+0.066
nance+0.064
le+0.060
hips+0.060
Neg logit contributions
ngth-0.074
orsi-0.069
riction-0.066
spection-0.066
ordinary-0.065
Token the
Token ID262
Feature activation-2.77e-01

Pos logit contributions
ngth+0.574
orsi+0.533
riction+0.514
spection+0.508
ordinary+0.503
Neg logit contributions
yond-0.691
swick-0.621
nance-0.603
le-0.566
hips-0.564
Token predomin
Token ID15960
Feature activation-5.98e+00

Pos logit contributions
yond+0.354
swick+0.315
nance+0.305
le+0.290
hips+0.289
Neg logit contributions
ngth-0.338
orsi-0.315
riction-0.301
spection-0.299
ordinary-0.294
Tokenately
Token ID1286
Feature activation+2.12e-01

Pos logit contributions
yond+7.065
swick+6.233
nance+6.072
le+5.715
hips+5.663
Neg logit contributions
ngth-7.738
orsi-7.252
spection-6.962
riction-6.940
ordinary-6.843
Token male
Token ID4257
Feature activation-2.24e+00

Pos logit contributions
ngth+0.274
orsi+0.257
riction+0.247
spection+0.246
ordinary+0.242
Neg logit contributions
yond-0.255
swick-0.226
nance-0.218
le-0.204
hips-0.204
Token-
Token ID12
Feature activation-5.13e-01

Pos logit contributions
yond+2.802
swick+2.444
nance+2.383
le+2.283
hips+2.262
Neg logit contributions
ngth-2.800
orsi-2.615
spection-2.494
riction-2.487
ordinary-2.434
Tokendominated
Token ID34475
Feature activation-3.25e-01

Pos logit contributions
yond+0.716
swick+0.643
nance+0.626
le+0.599
hips+0.595
Neg logit contributions
ngth-0.564
orsi-0.521
riction-0.499
spection-0.496
ordinary-0.484
Token programming
Token ID8300
Feature activation+3.34e-01

Pos logit contributions
yond+0.408
swick+0.362
nance+0.351
le+0.332
hips+0.331
Neg logit contributions
ngth-0.404
orsi-0.377
riction-0.362
spection-0.360
ordinary-0.354
Token know
Token ID760
Feature activation+1.14e+00

Pos logit contributions
yond+0.067
swick+0.060
nance+0.058
le+0.054
hips+0.054
Neg logit contributions
ngth-0.070
orsi-0.065
riction-0.063
spection-0.062
ordinary-0.062
Token:
Token ID25
Feature activation-1.40e-01

Pos logit contributions
ngth+1.204
orsi+1.115
riction+1.065
spection+1.059
ordinary+1.040
Neg logit contributions
yond-1.624
swick-1.470
nance-1.428
le-1.348
hips-1.348
Token In
Token ID554
Feature activation+3.77e-01

Pos logit contributions
yond+0.173
swick+0.154
nance+0.149
le+0.140
hips+0.140
Neg logit contributions
ngth-0.175
orsi-0.164
riction-0.158
spection-0.157
ordinary-0.154
Token the
Token ID262
Feature activation-4.66e-02

Pos logit contributions
ngth+0.458
orsi+0.427
riction+0.411
spection+0.407
ordinary+0.401
Neg logit contributions
yond-0.482
swick-0.430
nance-0.416
le-0.392
hips-0.391
Token Atlanta
Token ID9371
Feature activation-1.60e+00

Pos logit contributions
yond+0.057
swick+0.050
nance+0.049
le+0.046
hips+0.046
Neg logit contributions
ngth-0.059
orsi-0.055
riction-0.053
spection-0.053
ordinary-0.052
Token Journal
Token ID4913
Feature activation-5.95e+00

Pos logit contributions
yond+1.935
swick+1.713
nance+1.660
hips+1.547
le+1.542
Neg logit contributions
ngth-2.059
orsi-1.931
riction-1.864
spection-1.853
ordinary-1.830
Token-
Token ID12
Feature activation-1.43e-01

Pos logit contributions
yond+6.814
swick+6.204
nance+5.788
le+5.729
hips+5.514
Neg logit contributions
ngth-7.906
orsi-7.187
spection-6.806
riction-6.723
ordinary-6.644
TokenConst
Token ID34184
Feature activation+2.35e+00

Pos logit contributions
yond+0.225
swick+0.206
nance+0.201
hips+0.192
le+0.189
Neg logit contributions
ngth-0.126
orsi-0.117
riction-0.111
spection-0.110
ordinary-0.109
Tokenitution
Token ID2738
Feature activation-6.09e-01

Pos logit contributions
ngth+2.783
riction+2.707
orsi+2.600
spection+2.555
ordinary+2.527
Neg logit contributions
yond-2.938
swick-2.602
nance-2.488
hips-2.393
gency-2.312
Token's
Token ID338
Feature activation-6.72e-01

Pos logit contributions
yond+0.847
swick+0.757
nance+0.745
hips+0.697
le+0.688
Neg logit contributions
ngth-0.670
orsi-0.622
riction-0.601
spection-0.596
ordinary-0.582
Token published
Token ID3199
Feature activation+2.53e-01

Pos logit contributions
yond+0.828
swick+0.736
nance+0.711
le+0.672
hips+0.668
Neg logit contributions
ngth-0.846
orsi-0.790
riction-0.759
spection-0.753
ordinary-0.744
Token hormone
Token ID17770
Feature activation-2.16e+00

Pos logit contributions
ngth+0.616
orsi+0.572
riction+0.549
spection+0.547
ordinary+0.537
Neg logit contributions
yond-0.694
swick-0.621
nance-0.604
le-0.572
hips-0.568
Token secret
Token ID3200
Feature activation-5.07e-01

Pos logit contributions
yond+2.635
swick+2.331
nance+2.270
le+2.144
hips+2.128
Neg logit contributions
ngth-2.744
orsi-2.567
riction-2.460
spection-2.453
ordinary-2.415
Tokened
Token ID276
Feature activation-1.61e+00

Pos logit contributions
yond+0.410
swick+0.337
nance+0.326
le+0.292
hips+0.288
Neg logit contributions
ngth-0.856
orsi-0.812
riction-0.787
spection-0.785
ordinary-0.777
Token by
Token ID416
Feature activation-3.57e-01

Pos logit contributions
yond+1.947
swick+1.724
nance+1.666
le+1.559
hips+1.558
Neg logit contributions
ngth-2.072
orsi-1.942
riction-1.872
spection-1.860
ordinary-1.834
Token the
Token ID262
Feature activation-1.14e-01

Pos logit contributions
yond+0.474
swick+0.423
nance+0.412
le+0.389
hips+0.388
Neg logit contributions
ngth-0.417
orsi-0.387
riction-0.372
spection-0.370
ordinary-0.363
Token hypothal
Token ID48641
Feature activation-5.92e+00

Pos logit contributions
yond+0.137
swick+0.121
nance+0.117
hips+0.109
le+0.109
Neg logit contributions
ngth-0.146
orsi-0.137
riction-0.132
spection-0.131
ordinary-0.129
Tokenamus
Token ID25509
Feature activation-1.92e+00

Pos logit contributions
yond+2.488
swick+1.574
nance+1.505
le+1.295
hips+1.163
Neg logit contributions
ngth-12.084
orsi-11.467
spection-11.248
riction-11.232
ordinary-11.090
Token in
Token ID287
Feature activation-1.34e-01

Pos logit contributions
yond+2.363
swick+2.089
nance+2.033
le+1.926
hips+1.912
Neg logit contributions
ngth-2.395
orsi-2.235
riction-2.156
spection-2.141
ordinary-2.115
Token response
Token ID2882
Feature activation-5.71e-01

Pos logit contributions
yond+0.165
swick+0.147
nance+0.142
le+0.133
hips+0.133
Neg logit contributions
ngth-0.168
orsi-0.157
riction-0.151
spection-0.150
ordinary-0.148
Token to
Token ID284
Feature activation+1.11e-01

Pos logit contributions
yond+0.657
swick+0.555
le+0.548
nance+0.547
hips+0.531
Neg logit contributions
ngth-0.794
orsi-0.732
spection-0.694
riction-0.692
ordinary-0.672
Token stress
Token ID5503
Feature activation+1.82e+00

Pos logit contributions
ngth+0.121
orsi+0.112
riction+0.107
spection+0.106
ordinary+0.104
Neg logit contributions
yond-0.156
swick-0.141
nance-0.137
le-0.130
hips-0.130
Token
Token ID198
Feature activation+1.39e-02

Pos logit contributions
ngth+0.169
orsi+0.153
riction+0.146
spection+0.143
ftime+0.139
Neg logit contributions
yond-0.122
swick-0.105
le-0.102
nance-0.101
hips-0.097
TokenThe
Token ID464
Feature activation+4.17e-01

Pos logit contributions
ngth+0.017
orsi+0.015
riction+0.015
spection+0.015
ordinary+0.014
Neg logit contributions
yond-0.018
swick-0.016
nance-0.016
le-0.015
hips-0.015
Token United
Token ID1578
Feature activation-8.58e-01

Pos logit contributions
ngth+0.521
orsi+0.488
riction+0.470
spection+0.467
ordinary+0.461
Neg logit contributions
yond-0.517
swick-0.459
nance-0.444
hips-0.416
le-0.415
Token States
Token ID1829
Feature activation-3.86e-01

Pos logit contributions
yond+0.783
swick+0.659
nance+0.602
le+0.542
hips+0.535
Neg logit contributions
ngth-1.362
orsi-1.291
riction-1.272
spection-1.260
ordinary-1.246
Token is
Token ID318
Feature activation+4.05e-01

Pos logit contributions
yond+0.495
swick+0.442
nance+0.428
le+0.402
hips+0.402
Neg logit contributions
ngth-0.466
orsi-0.435
riction-0.418
spection-0.415
ordinary-0.409
Token spir
Token ID9158
Feature activation-5.91e+00

Pos logit contributions
ngth+0.471
orsi+0.439
riction+0.421
spection+0.418
ordinary+0.411
Neg logit contributions
yond-0.536
swick-0.480
nance-0.466
le-0.439
hips-0.439
Tokenalling
Token ID9221
Feature activation+4.17e-02

Pos logit contributions
yond+4.088
swick+3.217
nance+2.977
le+2.786
hips+2.661
Neg logit contributions
ngth-10.512
orsi-9.970
spection-9.737
riction-9.728
ordinary-9.596
Token down
Token ID866
Feature activation+7.33e-01

Pos logit contributions
ngth+0.057
orsi+0.054
riction+0.052
spection+0.052
ordinary+0.051
Neg logit contributions
yond-0.047
swick-0.041
nance-0.040
le-0.037
hips-0.037
Token into
Token ID656
Feature activation-7.10e-01

Pos logit contributions
ngth+0.845
orsi+0.784
riction+0.753
spection+0.753
ordinary+0.738
Neg logit contributions
yond-0.976
swick-0.881
nance-0.846
hips-0.798
le-0.794
Token a
Token ID257
Feature activation+5.67e-01

Pos logit contributions
yond+0.928
swick+0.829
nance+0.805
le+0.758
hips+0.757
Neg logit contributions
ngth-0.839
orsi-0.782
riction-0.751
spection-0.746
ordinary-0.734
Token basic
Token ID4096
Feature activation+2.37e-01

Pos logit contributions
ngth+0.676
orsi+0.630
riction+0.604
spection+0.600
ordinary+0.591
Neg logit contributions
yond-0.738
swick-0.659
nance-0.640
le-0.603
hips-0.602
Token 8
Token ID807
Feature activation-2.16e+00

Pos logit contributions
yond+0.591
swick+0.523
nance+0.506
le+0.473
hips+0.473
Neg logit contributions
ngth-0.629
orsi-0.590
riction-0.568
spection-0.565
ordinary-0.557
Token Great
Token ID3878
Feature activation-5.95e-01

Pos logit contributions
yond+2.633
swick+2.336
nance+2.249
le+2.156
hips+2.131
Neg logit contributions
ngth-2.720
orsi-2.560
riction-2.468
spection-2.446
ordinary-2.395
Token New
Token ID968
Feature activation-4.50e-01

Pos logit contributions
yond+0.776
swick+0.693
nance+0.671
le+0.637
hips+0.635
Neg logit contributions
ngth-0.706
orsi-0.658
riction-0.633
spection-0.628
ordinary-0.616
Token Female
Token ID15396
Feature activation-1.05e+00

Pos logit contributions
yond+0.583
swick+0.521
nance+0.505
le+0.476
hips+0.475
Neg logit contributions
ngth-0.538
orsi-0.501
riction-0.482
spection-0.478
ordinary-0.471
Token Positive
Token ID33733
Feature activation-1.53e-01

Pos logit contributions
yond+1.376
swick+1.231
nance+1.185
le+1.150
hips+1.146
Neg logit contributions
ngth-1.235
orsi-1.145
riction-1.102
spection-1.087
ordinary-1.052
Token Ong
Token ID48041
Feature activation-5.88e+00

Pos logit contributions
yond+0.196
swick+0.175
nance+0.169
le+0.161
hips+0.161
Neg logit contributions
ngth-0.186
orsi-0.173
riction-0.166
spection-0.165
ordinary-0.162
Tokeno
Token ID78
Feature activation-1.82e-01

Pos logit contributions
yond+2.628
swick+1.846
nance+1.661
le+1.422
hips+1.335
Neg logit contributions
ngth-11.806
orsi-11.228
riction-11.054
spection-10.946
ordinary-10.888
Tokenings
Token ID654
Feature activation-2.90e+00

Pos logit contributions
yond+0.235
swick+0.210
nance+0.204
hips+0.190
le+0.190
Neg logit contributions
ngth-0.218
orsi-0.204
riction-0.195
spection-0.195
ordinary-0.192
Token.
Token ID13
Feature activation-9.34e-02

Pos logit contributions
yond+3.601
swick+3.181
nance+3.071
hips+3.001
le+2.977
Neg logit contributions
ngth-3.523
orsi-3.314
riction-3.200
spection-3.151
ordinary-3.137
Token
Token ID198
Feature activation+8.14e-02

Pos logit contributions
yond+0.115
swick+0.102
nance+0.099
hips+0.092
le+0.092
Neg logit contributions
ngth-0.117
orsi-0.110
riction-0.106
spection-0.105
ordinary-0.104
Token
Token ID198
Feature activation+2.23e-02

Pos logit contributions
ngth+0.122
orsi+0.111
riction+0.105
spection+0.103
ftime+0.101
Neg logit contributions
yond-0.089
swick-0.076
le-0.074
nance-0.073
hips-0.071
Token.
Token ID13
Feature activation-3.41e-02

Pos logit contributions
ngth+0.630
orsi+0.586
riction+0.562
spection+0.559
ordinary+0.550
Neg logit contributions
yond-0.732
swick-0.656
nance-0.637
le-0.601
hips-0.600
Token
Token ID198
Feature activation+9.51e-02

Pos logit contributions
yond+0.040
swick+0.035
nance+0.034
le+0.032
hips+0.032
Neg logit contributions
ngth-0.045
orsi-0.042
riction-0.041
spection-0.041
ordinary-0.040
Token
Token ID198
Feature activation+2.77e-02

Pos logit contributions
ngth+0.143
orsi+0.130
riction+0.123
spection+0.121
ftime+0.118
Neg logit contributions
yond-0.104
swick-0.089
le-0.086
nance-0.086
hips-0.083
TokenMy
Token ID3666
Feature activation-1.26e-01

Pos logit contributions
ngth+0.032
orsi+0.029
riction+0.028
spection+0.027
ordinary+0.027
Neg logit contributions
yond-0.038
swick-0.034
nance-0.033
le-0.032
hips-0.031
Token colleague
Token ID16008
Feature activation+6.20e-01

Pos logit contributions
yond+0.156
swick+0.138
nance+0.134
le+0.127
hips+0.126
Neg logit contributions
ngth-0.158
orsi-0.148
riction-0.142
spection-0.141
ordinary-0.139
Token Amer
Token ID33391
Feature activation-5.87e+00

Pos logit contributions
ngth+0.749
orsi+0.700
riction+0.674
spection+0.672
ordinary+0.660
Neg logit contributions
yond-0.789
swick-0.705
nance-0.680
le-0.636
hips-0.635
Token A
Token ID317
Feature activation+9.32e-01

Pos logit contributions
yond+7.240
swick+6.461
nance+6.248
le+6.150
hips+5.892
Neg logit contributions
ngth-7.037
orsi-6.515
riction-6.298
spection-6.247
ordinary-6.173
Tokenther
Token ID490
Feature activation+8.68e-01

Pos logit contributions
ngth+1.138
orsi+1.067
riction+1.024
spection+1.017
ordinary+1.000
Neg logit contributions
yond-1.175
swick-1.050
nance-1.017
hips-0.950
le-0.945
Token was
Token ID373
Feature activation+6.89e-01

Pos logit contributions
ngth+1.201
orsi+1.134
riction+1.097
spection+1.093
ordinary+1.077
Neg logit contributions
yond-0.948
swick-0.833
nance-0.799
hips-0.743
le-0.728
Token responsible
Token ID4497
Feature activation-6.60e-01

Pos logit contributions
ngth+0.848
orsi+0.792
riction+0.763
spection+0.758
ordinary+0.747
Neg logit contributions
yond-0.866
swick-0.771
nance-0.746
le-0.700
hips-0.699
Token for
Token ID329
Feature activation-5.82e-01

Pos logit contributions
yond+0.910
swick+0.823
nance+0.796
le+0.741
hips+0.736
Neg logit contributions
ngth-0.733
orsi-0.664
spection-0.648
riction-0.647
ordinary-0.633
Token
Token ID198
Feature activation+2.65e-01

Pos logit contributions
ngth+0.315
orsi+0.295
riction+0.285
spection+0.285
ordinary+0.280
Neg logit contributions
yond-0.302
swick-0.267
nance-0.259
hips-0.241
le-0.240
Token
Token ID198
Feature activation+2.18e-01

Pos logit contributions
ngth+0.392
orsi+0.359
riction+0.340
spection+0.334
 Pwr+0.324
Neg logit contributions
yond-0.292
swick-0.252
le-0.242
nance-0.242
hips-0.232
TokenLike
Token ID7594
Feature activation+6.06e-02

Pos logit contributions
ngth+0.262
orsi+0.244
riction+0.234
spection+0.231
ordinary+0.227
Neg logit contributions
yond-0.285
swick-0.253
nance-0.245
le-0.234
hips-0.232
Token elephants
Token ID25368
Feature activation+4.38e-01

Pos logit contributions
ngth+0.078
orsi+0.073
riction+0.070
spection+0.070
ordinary+0.069
Neg logit contributions
yond-0.073
swick-0.065
nance-0.063
le-0.059
hips-0.058
Token,
Token ID11
Feature activation+3.01e-01

Pos logit contributions
ngth+0.500
orsi+0.466
riction+0.445
spection+0.444
ordinary+0.437
Neg logit contributions
yond-0.589
swick-0.529
nance-0.515
le-0.481
hips-0.480
Token mamm
Token ID13418
Feature activation-5.87e+00

Pos logit contributions
ngth+0.366
orsi+0.341
riction+0.328
spection+0.325
ordinary+0.320
Neg logit contributions
yond-0.384
swick-0.341
nance-0.331
le-0.313
hips-0.312
Tokenoths
Token ID27118
Feature activation+2.16e-01

Pos logit contributions
yond+4.823
swick+3.895
nance+3.873
le+3.603
hips+3.507
Neg logit contributions
ngth-9.473
orsi-8.844
spection-8.670
riction-8.576
EMBER-8.569
Token had
Token ID550
Feature activation+1.32e+00

Pos logit contributions
ngth+0.265
orsi+0.247
riction+0.237
spection+0.236
ordinary+0.232
Neg logit contributions
yond-0.273
swick-0.243
nance-0.235
le-0.222
hips-0.222
Token two
Token ID734
Feature activation+5.84e-01

Pos logit contributions
ngth+1.462
orsi+1.359
riction+1.305
spection+1.291
ordinary+1.276
Neg logit contributions
yond-1.814
swick-1.636
nance-1.588
hips-1.491
le-1.490
Token flesh
Token ID11222
Feature activation-1.66e+00

Pos logit contributions
ngth+0.708
orsi+0.659
riction+0.633
spection+0.630
ordinary+0.618
Neg logit contributions
yond-0.748
swick-0.667
nance-0.647
le-0.611
hips-0.610
Tokeny
Token ID88
Feature activation-1.35e-01

Pos logit contributions
yond+1.754
swick+1.523
nance+1.460
le+1.401
hips+1.390
Neg logit contributions
ngth-2.390
orsi-2.216
riction-2.149
spection-2.147
ordinary-2.115
Tokenaghetti
Token ID35812
Feature activation-3.46e+00

Pos logit contributions
yond+0.671
swick+0.599
nance+0.580
hips+0.544
le+0.544
Neg logit contributions
ngth-0.625
orsi-0.586
riction-0.563
spection-0.558
ordinary-0.551
Token Dinner
Token ID34584
Feature activation+8.28e-02

Pos logit contributions
yond+4.198
swick+3.791
nance+3.658
le+3.515
hips+3.430
Neg logit contributions
ngth-4.376
orsi-4.029
riction-3.862
spection-3.819
ordinary-3.739
Token at
Token ID379
Feature activation-7.35e-01

Pos logit contributions
ngth+0.105
orsi+0.099
riction+0.096
spection+0.095
ordinary+0.094
Neg logit contributions
yond-0.100
swick-0.089
nance-0.086
hips-0.080
le-0.080
Token Clear
Token ID11459
Feature activation-1.58e-03

Pos logit contributions
yond+0.942
swick+0.839
nance+0.814
hips+0.764
le+0.763
Neg logit contributions
ngth-0.887
orsi-0.830
riction-0.798
spection-0.794
ordinary-0.781
Token Creek
Token ID13509
Feature activation-1.51e+00

Pos logit contributions
yond+0.002
swick+0.002
nance+0.002
hips+0.002
le+0.002
Neg logit contributions
ngth-0.002
orsi-0.002
riction-0.002
spection-0.002
ordinary-0.002
Token Aman
Token ID42614
Feature activation-5.85e+00

Pos logit contributions
yond+1.896
swick+1.695
nance+1.641
le+1.555
hips+1.544
Neg logit contributions
ngth-1.879
orsi-1.743
riction-1.683
spection-1.662
ordinary-1.635
Tokena
Token ID64
Feature activation+9.51e-01

Pos logit contributions
yond+6.196
swick+5.634
nance+5.447
le+5.232
hips+5.088
Neg logit contributions
ngth-8.155
orsi-7.440
riction-7.227
ordinary-7.090
spection-7.018
Token High
Token ID3334
Feature activation+7.71e-01

Pos logit contributions
ngth+1.129
orsi+1.067
spection+1.022
riction+1.022
ordinary+1.009
Neg logit contributions
yond-1.217
swick-1.082
nance-1.049
hips-0.979
le-0.969
Token School
Token ID3961
Feature activation-9.73e-02

Pos logit contributions
ngth+1.008
orsi+0.956
riction+0.922
spection+0.916
ordinary+0.905
Neg logit contributions
yond-0.899
swick-0.791
nance-0.763
hips-0.704
le-0.702
Token on
Token ID319
Feature activation-2.38e-01

Pos logit contributions
yond+0.116
swick+0.103
nance+0.100
le+0.093
hips+0.093
Neg logit contributions
ngth-0.126
orsi-0.118
riction-0.114
spection-0.113
ordinary-0.112
Token April
Token ID3035
Feature activation-4.27e-01

Pos logit contributions
yond+0.241
swick+0.208
nance+0.199
le+0.189
hips+0.184
Neg logit contributions
ngth-0.358
orsi-0.335
riction-0.324
spection-0.319
ordinary-0.316
Token law
Token ID1099
Feature activation-9.80e-01

Pos logit contributions
ngth+0.058
orsi+0.054
riction+0.052
spection+0.052
ordinary+0.052
Neg logit contributions
yond-0.052
swick-0.046
nance-0.045
hips-0.042
le-0.041
Token,
Token ID11
Feature activation+1.93e-01

Pos logit contributions
yond+1.288
swick+1.152
nance+1.117
le+1.054
hips+1.052
Neg logit contributions
ngth-1.154
orsi-1.074
riction-1.031
spection-1.024
ordinary-1.009
Token he
Token ID339
Feature activation+4.67e-01

Pos logit contributions
ngth+0.236
orsi+0.221
riction+0.212
spection+0.211
ordinary+0.208
Neg logit contributions
yond-0.245
swick-0.219
nance-0.212
hips-0.198
le-0.198
Token has
Token ID468
Feature activation+1.53e+00

Pos logit contributions
ngth+0.557
orsi+0.522
riction+0.500
spection+0.497
ordinary+0.490
Neg logit contributions
yond-0.604
swick-0.539
nance-0.523
hips-0.489
le-0.488
Token st
Token ID336
Feature activation+6.97e-01

Pos logit contributions
ngth+1.733
orsi+1.626
riction+1.562
spection+1.550
ordinary+1.527
Neg logit contributions
yond-2.037
swick-1.829
nance-1.774
hips-1.658
le-1.656
Tokenonew
Token ID44181
Feature activation-5.82e+00

Pos logit contributions
ngth+1.025
orsi+0.973
riction+0.944
spection+0.933
ordinary+0.925
Neg logit contributions
yond-0.702
swick-0.608
nance-0.584
hips-0.533
le-0.527
Tokenalled
Token ID4262
Feature activation+6.80e-01

Pos logit contributions
yond+4.118
le+3.316
nance+3.239
hips+3.072
swick+2.929
Neg logit contributions
ngth-10.367
 Pwr-9.492
orsi-9.352
PDATE-9.307
spection-9.260
Token public
Token ID1171
Feature activation+1.14e+00

Pos logit contributions
ngth+0.843
orsi+0.792
riction+0.759
spection+0.757
ordinary+0.747
Neg logit contributions
yond-0.847
swick-0.757
nance-0.729
hips-0.683
le-0.680
Token interest
Token ID1393
Feature activation-7.51e-01

Pos logit contributions
ngth+1.480
orsi+1.386
riction+1.340
spection+1.336
ordinary+1.312
Neg logit contributions
yond-1.368
swick-1.217
nance-1.170
hips-1.090
le-1.082
Token groups
Token ID2628
Feature activation-3.53e-01

Pos logit contributions
yond+0.872
swick+0.766
nance+0.742
le+0.697
hips+0.693
Neg logit contributions
ngth-0.998
orsi-0.937
riction-0.903
spection-0.897
ordinary-0.884
Token,
Token ID11
Feature activation-1.34e-01

Pos logit contributions
yond+0.434
swick+0.384
nance+0.372
le+0.351
hips+0.351
Neg logit contributions
ngth-0.446
orsi-0.416
riction-0.401
spection-0.398
ordinary-0.393
Tokense
Token ID325
Feature activation-1.07e-01

Pos logit contributions
ngth+0.376
orsi+0.350
riction+0.335
spection+0.333
ordinary+0.327
Neg logit contributions
yond-0.453
swick-0.407
nance-0.395
hips-0.372
le-0.372
Tokenus
Token ID385
Feature activation+2.60e-01

Pos logit contributions
yond+0.115
swick+0.100
nance+0.096
le+0.091
hips+0.089
Neg logit contributions
ngth-0.153
orsi-0.144
riction-0.139
spection-0.138
ordinary-0.136
Token tied
Token ID8165
Feature activation-1.91e+00

Pos logit contributions
ngth+0.318
orsi+0.297
riction+0.286
spection+0.284
ordinary+0.280
Neg logit contributions
yond-0.329
swick-0.293
nance-0.284
le-0.267
hips-0.266
Token to
Token ID284
Feature activation-4.20e-01

Pos logit contributions
yond+2.444
swick+2.172
nance+2.114
le+2.019
hips+2.004
Neg logit contributions
ngth-2.304
orsi-2.137
riction-2.056
spection-2.032
ordinary-1.989
Token the
Token ID262
Feature activation-5.91e-01

Pos logit contributions
yond+0.547
swick+0.489
nance+0.475
le+0.446
hips+0.446
Neg logit contributions
ngth-0.497
orsi-0.464
riction-0.445
spection-0.443
ordinary-0.436
Token mast
Token ID17288
Feature activation-5.69e+00

Pos logit contributions
yond+0.737
swick+0.655
nance+0.633
le+0.597
hips+0.594
Neg logit contributions
ngth-0.738
orsi-0.689
riction-0.663
spection-0.659
ordinary-0.648
Token,
Token ID11
Feature activation-4.54e-01

Pos logit contributions
yond+6.367
swick+5.544
nance+5.377
le+5.359
hips+5.078
Neg logit contributions
ngth-7.373
orsi-6.858
spection-6.622
ordinary-6.537
 Pwr-6.491
Token sailing
Token ID28499
Feature activation+7.05e-02

Pos logit contributions
yond+0.572
swick+0.509
nance+0.493
le+0.464
hips+0.463
Neg logit contributions
ngth-0.559
orsi-0.522
riction-0.503
spection-0.499
ordinary-0.492
Token away
Token ID1497
Feature activation+2.98e-01

Pos logit contributions
ngth+0.088
orsi+0.082
riction+0.079
spection+0.079
ordinary+0.078
Neg logit contributions
yond-0.087
swick-0.078
nance-0.075
le-0.070
hips-0.070
Token from
Token ID422
Feature activation-9.81e-01

Pos logit contributions
ngth+0.393
orsi+0.370
riction+0.356
spection+0.355
ordinary+0.351
Neg logit contributions
yond-0.346
swick-0.308
nance-0.297
le-0.275
hips-0.274
Token the
Token ID262
Feature activation-5.22e-01

Pos logit contributions
yond+1.288
swick+1.151
nance+1.115
le+1.059
hips+1.053
Neg logit contributions
ngth-1.157
orsi-1.075
riction-1.034
spection-1.025
ordinary-1.007
Token hide
Token ID7808
Feature activation+2.35e-01

Pos logit contributions
yond+0.161
swick+0.143
nance+0.138
le+0.129
hips+0.129
Neg logit contributions
ngth-0.171
orsi-0.161
riction-0.155
spection-0.154
ordinary-0.152
Token details
Token ID3307
Feature activation+3.88e-01

Pos logit contributions
ngth+0.274
orsi+0.256
riction+0.246
spection+0.245
ordinary+0.241
Neg logit contributions
yond-0.310
swick-0.278
nance-0.269
hips-0.252
le-0.252
Token of
Token ID286
Feature activation+5.34e-01

Pos logit contributions
ngth+0.464
orsi+0.434
riction+0.418
spection+0.416
ordinary+0.410
Neg logit contributions
yond-0.499
swick-0.449
nance-0.434
le-0.405
hips-0.404
Token the
Token ID262
Feature activation-3.68e-01

Pos logit contributions
ngth+0.592
orsi+0.557
riction+0.532
spection+0.531
ordinary+0.523
Neg logit contributions
yond-0.728
swick-0.658
nance-0.635
hips-0.599
le-0.596
Token massive
Token ID4858
Feature activation-7.80e-01

Pos logit contributions
yond+0.440
swick+0.389
nance+0.376
le+0.352
hips+0.351
Neg logit contributions
ngth-0.476
orsi-0.447
riction-0.431
spection-0.428
ordinary-0.422
Token backlog
Token ID38780
Feature activation-5.65e+00

Pos logit contributions
yond+0.914
swick+0.805
nance+0.780
le+0.732
hips+0.729
Neg logit contributions
ngth-1.029
orsi-0.964
riction-0.930
spection-0.924
ordinary-0.911
Token they
Token ID484
Feature activation-1.68e+00

Pos logit contributions
yond+6.018
swick+5.140
nance+4.954
le+4.857
hips+4.762
Neg logit contributions
ngth-7.784
orsi-7.308
riction-7.095
spection-6.979
 Pwr-6.922
Token were
Token ID547
Feature activation-1.49e-01

Pos logit contributions
yond+2.034
swick+1.807
nance+1.746
le+1.660
hips+1.659
Neg logit contributions
ngth-2.164
orsi-1.999
riction-1.940
spection-1.917
ordinary-1.894
Token am
Token ID716
Feature activation-5.52e-01

Pos logit contributions
yond+0.179
swick+0.158
nance+0.152
le+0.143
hips+0.143
Neg logit contributions
ngth-0.195
orsi-0.182
riction-0.176
spection-0.174
ordinary-0.172
Tokenassing
Token ID19696
Feature activation-2.04e-01

Pos logit contributions
yond+0.851
swick+0.774
nance+0.755
le+0.721
hips+0.717
Neg logit contributions
ngth-0.526
orsi-0.480
riction-0.456
spection-0.452
ordinary-0.443
Token as
Token ID355
Feature activation-1.57e-01

Pos logit contributions
yond+0.269
swick+0.242
nance+0.234
le+0.220
hips+0.220
Neg logit contributions
ngth-0.238
orsi-0.222
riction-0.212
spection-0.211
ordinary-0.208
Tokenv
Token ID85
Feature activation+3.39e+00

Pos logit contributions
ngth+0.273
orsi+0.253
riction+0.242
spection+0.240
ordinary+0.236
Neg logit contributions
yond-0.340
swick-0.307
nance-0.298
hips-0.281
le-0.281
Tokenme
Token ID1326
Feature activation+9.59e-01

Pos logit contributions
ngth+3.958
orsi+3.716
spection+3.568
riction+3.561
ordinary+3.503
Neg logit contributions
yond-4.301
swick-3.876
nance-3.797
hips-3.540
gency-3.417
Token storage
Token ID6143
Feature activation+1.61e+00

Pos logit contributions
ngth+1.095
orsi+1.016
riction+0.979
spection+0.974
ordinary+0.958
Neg logit contributions
yond-1.285
swick-1.161
nance-1.122
hips-1.059
le-1.049
Token driver
Token ID4639
Feature activation+1.16e+00

Pos logit contributions
ngth+1.878
orsi+1.751
riction+1.684
spection+1.678
ordinary+1.652
Neg logit contributions
yond-2.122
swick-1.908
nance-1.844
hips-1.732
le-1.729
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
ngth+1.309
orsi+1.217
riction+1.170
spection+1.169
ordinary+1.145
Neg logit contributions
yond-1.561
swick-1.408
nance-1.365
le-1.281
hips-1.278
Token Amer
Token ID33391
Feature activation-5.63e+00

Pos logit contributions
yond+0.167
swick+0.147
nance+0.142
le+0.134
hips+0.134
Neg logit contributions
ngth-0.183
orsi-0.172
riction-0.166
spection-0.164
ordinary-0.162
Token has
Token ID468
Feature activation+6.42e-01

Pos logit contributions
yond+6.441
swick+5.637
nance+5.470
le+5.391
hips+5.271
Neg logit contributions
ngth-7.309
orsi-6.655
riction-6.500
spection-6.333
ordinary-6.267
Token tested
Token ID6789
Feature activation+1.77e-01

Pos logit contributions
ngth+0.754
orsi+0.701
riction+0.673
spection+0.668
ordinary+0.658
Neg logit contributions
yond-0.848
swick-0.758
nance-0.736
le-0.694
hips-0.693
Token and
Token ID290
Feature activation-5.97e-01

Pos logit contributions
ngth+0.211
orsi+0.196
riction+0.189
spection+0.187
ordinary+0.184
Neg logit contributions
yond-0.231
swick-0.206
nance-0.201
le-0.190
hips-0.189
Token deployed
Token ID12380
Feature activation+5.63e-01

Pos logit contributions
yond+0.765
swick+0.675
nance+0.661
le+0.627
hips+0.626
Neg logit contributions
ngth-0.736
orsi-0.681
riction-0.655
spection-0.647
ordinary-0.637
Token this
Token ID428
Feature activation-5.40e-01

Pos logit contributions
ngth+0.666
orsi+0.620
riction+0.595
spection+0.590
ordinary+0.581
Neg logit contributions
yond-0.738
swick-0.659
nance-0.641
le-0.606
hips-0.604
Token an
Token ID281
Feature activation+2.78e-01

Pos logit contributions
yond+1.307
swick+1.141
nance+1.112
le+1.068
hips+1.060
Neg logit contributions
ngth-1.376
orsi-1.276
riction-1.218
spection-1.211
ordinary-1.196
Token alternative
Token ID5559
Feature activation+1.71e+00

Pos logit contributions
ngth+0.382
orsi+0.360
riction+0.347
spection+0.345
ordinary+0.341
Neg logit contributions
yond-0.310
swick-0.271
nance-0.261
le-0.244
hips-0.243
Token to
Token ID284
Feature activation+9.80e-02

Pos logit contributions
ngth+2.124
orsi+1.978
riction+1.904
spection+1.866
ordinary+1.839
Neg logit contributions
yond-2.152
swick-1.908
nance-1.855
le-1.767
hips-1.733
Token The
Token ID383
Feature activation+5.75e-01

Pos logit contributions
ngth+0.114
orsi+0.108
riction+0.106
spection+0.104
ordinary+0.104
Neg logit contributions
yond-0.127
swick-0.114
nance-0.111
hips-0.104
le-0.101
Token Ad
Token ID1215
Feature activation-1.30e+00

Pos logit contributions
ngth+0.736
orsi+0.699
riction+0.678
spection+0.672
ordinary+0.671
Neg logit contributions
yond-0.676
swick-0.600
nance-0.580
hips-0.544
le-0.531
Tokenvertis
Token ID3346
Feature activation-5.61e+00

Pos logit contributions
yond+0.786
le+0.567
nance+0.541
swick+0.533
inator+0.470
Neg logit contributions
ngth-2.551
orsi-2.370
spection-2.264
riction-2.249
UGE-2.247
Tokener
Token ID263
Feature activation-6.82e-01

Pos logit contributions
yond+3.200
le+2.614
nance+2.367
et+1.988
inator+1.978
Neg logit contributions
ngth-11.058
orsi-10.130
UGE-9.683
 Pwr-9.529
perty-9.524
Token,
Token ID11
Feature activation+4.30e-02

Pos logit contributions
yond+0.864
swick+0.772
nance+0.743
le+0.723
hips+0.707
Neg logit contributions
ngth-0.857
orsi-0.794
riction-0.742
ordinary-0.732
spection-0.727
Token a
Token ID257
Feature activation+7.97e-01

Pos logit contributions
ngth+0.049
orsi+0.046
riction+0.044
spection+0.044
ordinary+0.043
Neg logit contributions
yond-0.058
swick-0.052
nance-0.050
hips-0.047
le-0.047
Token different
Token ID1180
Feature activation+8.29e-01

Pos logit contributions
ngth+1.118
orsi+1.027
riction+0.974
ordinary+0.970
spection+0.964
Neg logit contributions
yond-0.892
swick-0.784
nance-0.781
le-0.741
hips-0.700
Token voice
Token ID3809
Feature activation-5.87e-01

Pos logit contributions
ngth+1.102
orsi+1.038
riction+0.985
spection+0.975
ordinary+0.969
Neg logit contributions
yond-0.972
swick-0.869
nance-0.834
le-0.798
hips-0.777
Token
Token ID447
Feature activation+8.26e-02

Pos logit contributions
ngth+0.057
orsi+0.054
riction+0.052
spection+0.051
ordinary+0.051
Neg logit contributions
yond-0.057
swick-0.050
nance-0.049
le-0.046
hips-0.045
Token
Token ID251
Feature activation-1.91e-01

Pos logit contributions
ngth+0.105
orsi+0.098
riction+0.095
spection+0.095
ordinary+0.093
Neg logit contributions
yond-0.101
swick-0.090
nance-0.087
hips-0.080
le-0.080
Token said
Token ID531
Feature activation+6.81e-01

Pos logit contributions
yond+0.243
swick+0.216
nance+0.209
le+0.197
hips+0.197
Neg logit contributions
ngth-0.233
orsi-0.217
riction-0.209
spection-0.207
ordinary-0.204
Token Sen
Token ID2311
Feature activation-6.57e-02

Pos logit contributions
ngth+0.860
orsi+0.808
riction+0.776
spection+0.773
ordinary+0.763
Neg logit contributions
yond-0.829
swick-0.738
nance-0.712
hips-0.663
le-0.660
Token.
Token ID13
Feature activation-3.88e-01

Pos logit contributions
yond+0.095
swick+0.086
nance+0.084
hips+0.078
le+0.078
Neg logit contributions
ngth-0.068
orsi-0.063
riction-0.061
spection-0.060
ordinary-0.058
Token Kay
Token ID17356
Feature activation-5.56e+00

Pos logit contributions
yond+0.465
swick+0.411
nance+0.397
le+0.373
hips+0.372
Neg logit contributions
ngth-0.502
orsi-0.470
riction-0.453
spection-0.450
ordinary-0.444
Token Bailey
Token ID20330
Feature activation-1.51e+00

Pos logit contributions
yond+6.089
swick+5.279
le+5.273
nance+5.261
hips+4.947
Neg logit contributions
ngth-7.274
orsi-6.942
riction-6.679
spection-6.623
ordinary-6.450
Token Hutch
Token ID30492
Feature activation-2.25e+00

Pos logit contributions
yond+1.297
swick+1.057
nance+0.997
le+0.945
hips+0.922
Neg logit contributions
ngth-2.477
orsi-2.364
riction-2.287
spection-2.259
ordinary-2.231
Tokenison
Token ID1653
Feature activation-9.42e-01

Pos logit contributions
yond+2.555
swick+2.279
nance+2.152
le+2.110
hips+2.063
Neg logit contributions
ngth-2.991
orsi-2.769
riction-2.676
spection-2.626
UGE-2.623
Token (
Token ID357
Feature activation+5.27e-01

Pos logit contributions
yond+1.258
swick+1.127
nance+1.097
hips+1.027
le+1.027
Neg logit contributions
ngth-1.088
orsi-1.014
riction-0.973
spection-0.967
ordinary-0.951
TokenR
Token ID49
Feature activation+2.36e+00

Pos logit contributions
ngth+0.571
orsi+0.531
riction+0.509
spection+0.505
ordinary+0.498
Neg logit contributions
yond-0.737
swick-0.666
nance-0.648
hips-0.609
le-0.608
Token)
Token ID8
Feature activation-1.15e+00

Pos logit contributions
ngth+0.724
orsi+0.671
riction+0.643
spection+0.638
ordinary+0.627
Neg logit contributions
yond-0.907
swick-0.821
nance-0.795
le-0.746
hips-0.746
Token such
Token ID884
Feature activation+6.17e-02

Pos logit contributions
yond+1.479
swick+1.311
nance+1.276
le+1.208
hips+1.204
Neg logit contributions
ngth-1.397
orsi-1.303
riction-1.251
spection-1.242
ordinary-1.221
Token as
Token ID355
Feature activation-6.05e-01

Pos logit contributions
ngth+0.092
orsi+0.085
riction+0.081
spection+0.081
ordinary+0.079
Neg logit contributions
yond-0.066
swick-0.056
nance-0.055
le-0.053
hips-0.052
Token methane
Token ID25006
Feature activation-2.09e-01

Pos logit contributions
yond+0.808
swick+0.714
nance+0.705
le+0.671
hips+0.663
Neg logit contributions
ngth-0.706
orsi-0.654
riction-0.623
spection-0.623
ordinary-0.606
Token and
Token ID290
Feature activation-2.35e-01

Pos logit contributions
yond+0.270
swick+0.242
nance+0.234
hips+0.220
le+0.220
Neg logit contributions
ngth-0.249
orsi-0.232
riction-0.223
spection-0.222
ordinary-0.218
Token aeros
Token ID41376
Feature activation-5.54e+00

Pos logit contributions
yond+0.324
swick+0.287
nance+0.281
le+0.268
hips+0.266
Neg logit contributions
ngth-0.266
orsi-0.246
spection-0.234
riction-0.234
ordinary-0.229
Tokenols
Token ID10220
Feature activation-4.18e-01

Pos logit contributions
yond+6.136
nance+5.257
hips+5.240
swick+5.239
le+5.238
Neg logit contributions
ngth-7.267
orsi-6.628
 Pwr-6.611
spection-6.558
EMBER-6.457
Token,
Token ID11
Feature activation+1.73e-01

Pos logit contributions
yond+0.556
swick+0.499
nance+0.484
le+0.456
hips+0.455
Neg logit contributions
ngth-0.484
orsi-0.451
riction-0.432
spection-0.429
ordinary-0.423
Token as
Token ID355
Feature activation+1.30e-01

Pos logit contributions
ngth+0.207
orsi+0.193
riction+0.186
spection+0.184
ordinary+0.182
Neg logit contributions
yond-0.223
swick-0.200
nance-0.193
le-0.182
hips-0.182
Token well
Token ID880
Feature activation+1.29e+00

Pos logit contributions
ngth+0.150
orsi+0.140
riction+0.134
spection+0.133
ordinary+0.131
Neg logit contributions
yond-0.175
swick-0.157
nance-0.152
le-0.143
hips-0.143
Token as
Token ID355
Feature activation+4.73e-02

Pos logit contributions
ngth+1.828
orsi+1.702
riction+1.635
spection+1.623
ordinary+1.588
Neg logit contributions
yond-1.449
swick-1.241
nance-1.214
le-1.143
hips-1.127
Token public
Token ID1171
Feature activation+1.23e+00

Pos logit contributions
yond+0.066
swick+0.059
nance+0.058
le+0.055
hips+0.055
Neg logit contributions
ngth-0.055
orsi-0.051
riction-0.048
spection-0.048
ordinary-0.047
Token b
Token ID275
Feature activation-4.18e-01

Pos logit contributions
ngth+1.442
orsi+1.359
riction+1.316
spection+1.294
ordinary+1.280
Neg logit contributions
yond-1.607
swick-1.433
nance-1.384
le-1.287
hips-1.276
Tokenrom
Token ID398
Feature activation+1.80e-01

Pos logit contributions
yond+0.457
swick+0.399
nance+0.385
le+0.358
hips+0.358
Neg logit contributions
ngth-0.584
orsi-0.549
riction-0.530
spection-0.528
ordinary-0.521
Tokenance
Token ID590
Feature activation-1.70e+00

Pos logit contributions
ngth+0.217
orsi+0.204
riction+0.200
spection+0.197
ordinary+0.194
Neg logit contributions
yond-0.226
swick-0.202
nance-0.194
hips-0.180
le-0.179
Token,
Token ID11
Feature activation-6.73e-02

Pos logit contributions
yond+2.129
swick+1.883
nance+1.835
hips+1.740
le+1.736
Neg logit contributions
ngth-2.106
orsi-1.953
riction-1.884
spection-1.875
ordinary-1.849
Token Putin
Token ID8144
Feature activation+3.01e+00

Pos logit contributions
yond+0.086
swick+0.076
nance+0.074
le+0.070
hips+0.070
Neg logit contributions
ngth-0.082
orsi-0.076
riction-0.073
spection-0.073
ordinary-0.072
Token would
Token ID561
Feature activation-8.80e-01

Pos logit contributions
ngth+3.423
orsi+3.257
riction+3.084
spection+3.056
ordinary+3.024
Neg logit contributions
yond-3.961
swick-3.530
nance-3.428
hips-3.195
gency-3.164
Token much
Token ID881
Feature activation+5.12e-02

Pos logit contributions
yond+1.142
swick+1.015
nance+0.992
le+0.941
hips+0.937
Neg logit contributions
ngth-1.057
orsi-0.982
riction-0.940
spection-0.936
ordinary-0.918
Token prefer
Token ID4702
Feature activation+7.17e-01

Pos logit contributions
ngth+0.055
orsi+0.051
riction+0.049
spection+0.048
ordinary+0.047
Neg logit contributions
yond-0.073
swick-0.065
nance-0.064
le-0.061
hips-0.060
Token a
Token ID257
Feature activation+4.51e-01

Pos logit contributions
ngth+0.862
orsi+0.805
riction+0.774
spection+0.768
ordinary+0.757
Neg logit contributions
yond-0.922
swick-0.824
nance-0.798
le-0.749
hips-0.749
Token Trump
Token ID1301
Feature activation-1.11e+00

Pos logit contributions
ngth+0.544
orsi+0.503
riction+0.483
spection+0.481
ordinary+0.472
Neg logit contributions
yond-0.584
swick-0.522
nance-0.506
le-0.481
hips-0.476
Token not
Token ID407
Feature activation-6.03e-01

Pos logit contributions
ngth+0.319
orsi+0.300
riction+0.290
spection+0.288
ordinary+0.284
Neg logit contributions
yond-0.274
swick-0.241
nance-0.233
le-0.217
hips-0.216
Token just
Token ID655
Feature activation+3.69e-01

Pos logit contributions
yond+0.870
swick+0.779
nance+0.762
le+0.729
hips+0.728
Neg logit contributions
ngth-0.634
orsi-0.583
riction-0.555
spection-0.552
ordinary-0.541
Token at
Token ID379
Feature activation-1.35e-01

Pos logit contributions
ngth+0.471
orsi+0.442
riction+0.426
spection+0.423
ordinary+0.418
Neg logit contributions
yond-0.446
swick-0.397
nance-0.383
le-0.357
hips-0.356
Token or
Token ID393
Feature activation-3.84e-01

Pos logit contributions
yond+0.180
swick+0.161
nance+0.156
le+0.147
hips+0.147
Neg logit contributions
ngth-0.157
orsi-0.146
riction-0.140
spection-0.139
ordinary-0.137
Token near
Token ID1474
Feature activation+1.15e+00

Pos logit contributions
yond+0.494
swick+0.438
nance+0.424
le+0.402
hips+0.401
Neg logit contributions
ngth-0.465
orsi-0.433
riction-0.416
spection-0.415
ordinary-0.407
Token v
Token ID410
Feature activation+3.60e+00

Pos logit contributions
ngth+1.294
orsi+1.209
riction+1.159
spection+1.146
ordinary+1.131
Neg logit contributions
yond-1.550
swick-1.404
nance-1.357
hips-1.273
le-1.265
Tokenort
Token ID419
Feature activation-1.46e-01

Pos logit contributions
ngth+2.049
orsi+1.945
riction+1.802
spection+1.696
ordinary+1.642
Neg logit contributions
yond-6.674
swick-6.229
nance-6.025
hips-5.789
gency-5.780
Tokenons
Token ID684
Feature activation+3.52e-01

Pos logit contributions
yond+0.188
swick+0.168
nance+0.162
hips+0.152
le+0.152
Neg logit contributions
ngth-0.174
orsi-0.163
riction-0.158
spection-0.155
ordinary-0.153
Token.
Token ID13
Feature activation+2.23e-01

Pos logit contributions
ngth+0.389
orsi+0.361
riction+0.346
spection+0.343
ordinary+0.337
Neg logit contributions
yond-0.485
swick-0.438
nance-0.425
le-0.401
hips-0.399
Token So
Token ID1406
Feature activation+2.62e-01

Pos logit contributions
ngth+0.304
orsi+0.285
riction+0.275
spection+0.273
ordinary+0.269
Neg logit contributions
yond-0.251
swick-0.221
nance-0.213
le-0.200
hips-0.199
Token,
Token ID11
Feature activation+3.17e-01

Pos logit contributions
ngth+0.309
orsi+0.286
riction+0.274
spection+0.272
ordinary+0.268
Neg logit contributions
yond-0.346
swick-0.307
nance-0.300
le-0.284
hips-0.283
Token type
Token ID2099
Feature activation+6.92e-02

Pos logit contributions
ngth+0.012
orsi+0.011
riction+0.011
spection+0.011
ordinary+0.010
Neg logit contributions
yond-0.015
swick-0.013
nance-0.013
hips-0.012
le-0.012
Token uses
Token ID3544
Feature activation+1.02e+00

Pos logit contributions
ngth+0.084
orsi+0.079
riction+0.076
spection+0.075
ordinary+0.074
Neg logit contributions
yond-0.088
swick-0.079
nance-0.076
le-0.072
hips-0.071
Token a
Token ID257
Feature activation+6.22e-01

Pos logit contributions
ngth+1.125
orsi+1.043
riction+1.000
spection+0.995
ordinary+0.977
Neg logit contributions
yond-1.414
swick-1.272
nance-1.235
hips-1.166
le-1.165
Token new
Token ID649
Feature activation+2.67e-01

Pos logit contributions
ngth+0.741
orsi+0.689
riction+0.660
spection+0.654
ordinary+0.645
Neg logit contributions
yond-0.812
swick-0.726
nance-0.705
le-0.668
hips-0.663
Token hyper
Token ID8718
Feature activation+1.40e+00

Pos logit contributions
ngth+0.316
orsi+0.294
riction+0.282
spection+0.279
ordinary+0.275
Neg logit contributions
yond-0.351
swick-0.314
nance-0.305
le-0.289
hips-0.287
Tokenvisor
Token ID13131
Feature activation+2.86e+00

Pos logit contributions
ngth+0.586
orsi+0.471
riction+0.421
spection+0.420
ordinary+0.398
Neg logit contributions
yond-2.890
swick-2.705
nance-2.652
hips-2.558
le-2.535
Token called
Token ID1444
Feature activation-5.32e-01

Pos logit contributions
ngth+3.435
orsi+3.227
spection+3.143
riction+3.123
ordinary+3.091
Neg logit contributions
yond-3.576
swick-3.197
nance-3.071
hips-2.878
le-2.855
Token Nit
Token ID24282
Feature activation-9.93e-01

Pos logit contributions
yond+0.685
swick+0.612
nance+0.593
le+0.559
hips+0.558
Neg logit contributions
ngth-0.640
orsi-0.596
riction-0.573
spection-0.569
ordinary-0.560
Tokenro
Token ID305
Feature activation+4.02e-01

Pos logit contributions
yond+1.339
swick+1.188
nance+1.183
le+1.144
hips+1.098
Neg logit contributions
ngth-1.160
orsi-1.025
riction-0.982
spection-0.981
ordinary-0.964
Token.
Token ID13
Feature activation-1.33e-01

Pos logit contributions
ngth+0.467
orsi+0.434
riction+0.416
spection+0.413
ordinary+0.407
Neg logit contributions
yond-0.536
swick-0.480
nance-0.466
le-0.440
hips-0.439
Token Nit
Token ID24282
Feature activation-6.14e-01

Pos logit contributions
yond+0.155
swick+0.137
nance+0.132
le+0.124
hips+0.123
Neg logit contributions
ngth-0.177
orsi-0.166
riction-0.160
spection-0.159
ordinary-0.156
Token Apex
Token ID49440
Feature activation-1.11e-01

Pos logit contributions
ngth+1.028
orsi+0.958
riction+0.923
spection+0.907
ordinary+0.890
Neg logit contributions
yond-1.644
swick-1.501
nance-1.458
le-1.389
hips-1.384
Token has
Token ID468
Feature activation+9.94e-01

Pos logit contributions
yond+0.141
swick+0.126
nance+0.122
le+0.116
hips+0.116
Neg logit contributions
ngth-0.136
orsi-0.126
riction-0.121
spection-0.121
ordinary-0.119
Token been
Token ID587
Feature activation-5.04e-01

Pos logit contributions
ngth+1.103
orsi+1.022
riction+0.978
spection+0.971
ordinary+0.955
Neg logit contributions
yond-1.374
swick-1.236
nance-1.201
le-1.137
hips-1.135
Token built
Token ID3170
Feature activation-8.50e-02

Pos logit contributions
yond+0.648
swick+0.580
nance+0.561
le+0.533
hips+0.529
Neg logit contributions
ngth-0.613
orsi-0.570
riction-0.544
spection-0.543
ordinary-0.532
Token with
Token ID351
Feature activation-4.96e-01

Pos logit contributions
yond+0.101
swick+0.090
nance+0.087
hips+0.081
le+0.081
Neg logit contributions
ngth-0.110
orsi-0.103
riction-0.100
spection-0.099
ordinary-0.098
Token VR
Token ID6453
Feature activation+4.37e+00

Pos logit contributions
yond+0.660
swick+0.588
nance+0.572
le+0.548
hips+0.541
Neg logit contributions
ngth-0.578
orsi-0.537
riction-0.510
spection-0.507
ordinary-0.499
Token in
Token ID287
Feature activation-1.97e-01

Pos logit contributions
ngth+5.018
orsi+4.624
riction+4.522
spection+4.492
ordinary+4.349
Neg logit contributions
yond-5.691
swick-5.183
nance-4.940
hips-4.638
le-4.634
Token mind
Token ID2000
Feature activation+1.27e+00

Pos logit contributions
yond+0.289
swick+0.258
nance+0.254
le+0.242
hips+0.242
Neg logit contributions
ngth-0.204
orsi-0.189
riction-0.179
spection-0.177
ordinary-0.174
Token,
Token ID11
Feature activation+4.23e-02

Pos logit contributions
ngth+1.544
orsi+1.446
riction+1.391
spection+1.389
ordinary+1.360
Neg logit contributions
yond-1.620
swick-1.451
nance-1.397
hips-1.304
le-1.301
Token for
Token ID329
Feature activation-5.59e-01

Pos logit contributions
ngth+0.057
orsi+0.053
riction+0.052
spection+0.051
ordinary+0.051
Neg logit contributions
yond-0.049
swick-0.043
nance-0.041
le-0.038
hips-0.038
Token example
Token ID1672
Feature activation+3.38e-02

Pos logit contributions
yond+0.752
swick+0.671
nance+0.652
le+0.621
hips+0.618
Neg logit contributions
ngth-0.644
orsi-0.597
riction-0.571
spection-0.566
ordinary-0.557
Token de
Token ID390
Feature activation+2.72e+00

Pos logit contributions
ngth+0.846
orsi+0.793
riction+0.763
spection+0.763
ordinary+0.753
Neg logit contributions
yond-0.834
swick-0.737
nance-0.716
hips-0.669
le-0.659
Token N
Token ID399
Feature activation+3.65e-01

Pos logit contributions
ngth+3.299
orsi+3.075
riction+2.952
spection+2.949
ordinary+2.862
Neg logit contributions
yond-3.406
swick-3.043
nance-2.969
hips-2.780
gency-2.725
Tokenog
Token ID519
Feature activation-1.08e+00

Pos logit contributions
ngth+0.411
orsi+0.384
riction+0.367
spection+0.363
ordinary+0.359
Neg logit contributions
yond-0.495
swick-0.446
nance-0.432
hips-0.407
le-0.407
Tokenales
Token ID2040
Feature activation-2.86e-01

Pos logit contributions
yond+1.363
swick+1.214
nance+1.175
le+1.106
hips+1.103
Neg logit contributions
ngth-1.340
orsi-1.249
riction-1.203
spection-1.195
ordinary-1.178
Token Lep
Token ID42957
Feature activation+1.27e+00

Pos logit contributions
yond+0.359
swick+0.319
nance+0.309
hips+0.289
le+0.287
Neg logit contributions
ngth-0.353
orsi-0.331
riction-0.317
spection-0.316
ordinary-0.311
Tokenre
Token ID260
Feature activation+2.94e+00

Pos logit contributions
ngth+1.706
orsi+1.626
riction+1.564
spection+1.547
ordinary+1.536
Neg logit contributions
yond-1.436
swick-1.268
nance-1.212
hips-1.139
le-1.114
Token-
Token ID12
Feature activation-5.15e-01

Pos logit contributions
ngth+3.378
orsi+3.137
riction+2.982
spection+2.977
ordinary+2.936
Neg logit contributions
yond-3.899
swick-3.489
nance-3.370
hips-3.212
le-3.115
Tokenv
Token ID85
Feature activation+3.16e+00

Pos logit contributions
yond+0.718
swick+0.645
nance+0.629
le+0.599
hips+0.594
Neg logit contributions
ngth-0.567
orsi-0.523
riction-0.503
spection-0.498
ordinary-0.487
Tokenost
Token ID455
Feature activation-6.22e-01

Pos logit contributions
ngth+4.044
orsi+3.936
riction+3.760
spection+3.689
ordinary+3.656
Neg logit contributions
yond-3.617
swick-3.241
nance-3.067
hips-2.830
gency-2.816
Token and
Token ID290
Feature activation-2.26e-01

Pos logit contributions
yond+0.818
swick+0.732
nance+0.709
hips+0.668
le+0.667
Neg logit contributions
ngth-0.730
orsi-0.682
riction-0.655
spection-0.649
ordinary-0.640
Token Edwin
Token ID37016
Feature activation-9.11e-01

Pos logit contributions
yond+0.283
swick+0.252
nance+0.243
hips+0.228
le+0.227
Neg logit contributions
ngth-0.280
orsi-0.262
riction-0.252
spection-0.251
ordinary-0.247
Token )
Token ID1267
Feature activation-5.41e-01

Pos logit contributions
ngth+2.479
orsi+2.309
spection+2.258
riction+2.239
ordinary+2.189
Neg logit contributions
yond-2.267
swick-1.955
nance-1.917
hips-1.768
gency-1.727
Token {
Token ID1391
Feature activation+7.53e-01

Pos logit contributions
yond+0.721
swick+0.642
nance+0.620
hips+0.583
le+0.568
Neg logit contributions
ngth-0.626
orsi-0.597
spection-0.578
riction-0.574
ordinary-0.553
Token let
Token ID1309
Feature activation+1.62e+00

Pos logit contributions
ngth+0.985
orsi+0.928
riction+0.895
spection+0.890
ordinary+0.879
Neg logit contributions
yond-0.888
swick-0.783
nance-0.756
le-0.704
hips-0.704
Token prev
Token ID8654
Feature activation+1.76e+00

Pos logit contributions
ngth+1.862
orsi+1.743
riction+1.677
spection+1.663
ordinary+1.638
Neg logit contributions
yond-2.148
swick-1.936
nance-1.869
hips-1.746
le-1.744
Token_
Token ID62
Feature activation+9.18e-01

Pos logit contributions
ngth+1.588
orsi+1.431
riction+1.394
spection+1.387
ordinary+1.335
Neg logit contributions
yond-2.796
swick-2.522
nance-2.452
hips-2.309
gency-2.285
Tokenstate
Token ID5219
Feature activation+4.17e-01

Pos logit contributions
ngth+1.226
orsi+1.133
riction+1.111
spection+1.107
ordinary+1.092
Neg logit contributions
yond-1.064
swick-0.940
nance-0.896
hips-0.829
eous-0.808
Token =
Token ID796
Feature activation+5.26e-01

Pos logit contributions
ngth+0.480
orsi+0.444
riction+0.429
spection+0.427
ordinary+0.418
Neg logit contributions
yond-0.563
swick-0.502
nance-0.489
hips-0.456
le-0.452
Token self
Token ID2116
Feature activation+1.70e+00

Pos logit contributions
ngth+0.598
orsi+0.556
riction+0.533
spection+0.530
ordinary+0.521
Neg logit contributions
yond-0.711
swick-0.638
nance-0.619
le-0.584
hips-0.584
Token.
Token ID764
Feature activation+1.04e+00

Pos logit contributions
ngth+1.695
orsi+1.579
spection+1.555
riction+1.523
ordinary+1.475
Neg logit contributions
yond-2.465
swick-2.237
nance-2.183
hips-2.055
gency-2.036
Tokencopy
Token ID30073
Feature activation+1.48e+00

Pos logit contributions
ngth+1.189
orsi+1.104
riction+1.062
spection+1.057
ordinary+1.042
Neg logit contributions
yond-1.406
swick-1.267
nance-1.227
hips-1.155
le-1.148
Token_
Token ID62
Feature activation+6.65e-01

Pos logit contributions
ngth+1.613
orsi+1.493
spection+1.455
riction+1.450
ordinary+1.413
Neg logit contributions
yond-2.045
swick-1.860
nance-1.792
hips-1.683
le-1.668
Token you
Token ID345
Feature activation-4.84e-01

Pos logit contributions
ngth+0.999
orsi+0.929
riction+0.889
spection+0.885
ordinary+0.870
Neg logit contributions
yond-1.238
swick-1.118
nance-1.085
hips-1.023
le-1.020
Token can
Token ID460
Feature activation+1.08e+00

Pos logit contributions
yond+0.612
swick+0.542
nance+0.526
le+0.501
hips+0.501
Neg logit contributions
ngth-0.594
orsi-0.556
riction-0.535
spection-0.532
ordinary-0.522
Token continue
Token ID2555
Feature activation-7.66e-01

Pos logit contributions
ngth+1.334
orsi+1.247
riction+1.199
spection+1.192
ordinary+1.174
Neg logit contributions
yond-1.358
swick-1.209
nance-1.170
le-1.099
hips-1.097
Token following
Token ID1708
Feature activation+2.85e-01

Pos logit contributions
yond+0.969
swick+0.859
nance+0.834
le+0.791
hips+0.787
Neg logit contributions
ngth-0.937
orsi-0.874
riction-0.842
spection-0.834
ordinary-0.822
Token me
Token ID502
Feature activation+1.10e+00

Pos logit contributions
ngth+0.344
orsi+0.321
riction+0.309
spection+0.307
ordinary+0.302
Neg logit contributions
yond-0.365
swick-0.326
nance-0.316
le-0.297
hips-0.297
Token on
Token ID319
Feature activation-1.52e-02

Pos logit contributions
ngth+1.369
orsi+1.278
riction+1.230
spection+1.227
ordinary+1.205
Neg logit contributions
yond-1.350
swick-1.213
nance-1.173
hips-1.087
le-1.085
Token this
Token ID428
Feature activation-3.61e-01

Pos logit contributions
yond+0.019
swick+0.017
nance+0.016
le+0.015
hips+0.015
Neg logit contributions
ngth-0.019
orsi-0.018
riction-0.017
spection-0.017
ordinary-0.017
Token j
Token ID474
Feature activation+5.70e-01

Pos logit contributions
yond+0.475
swick+0.421
nance+0.411
le+0.391
hips+0.388
Neg logit contributions
ngth-0.428
orsi-0.397
riction-0.379
spection-0.377
ordinary-0.372
Tokenourn
Token ID1798
Feature activation+4.32e-01

Pos logit contributions
ngth+0.673
orsi+0.628
riction+0.603
spection+0.599
ordinary+0.589
Neg logit contributions
yond-0.747
swick-0.668
nance-0.647
hips-0.609
le-0.609
Tokeny
Token ID88
Feature activation+3.60e-01

Pos logit contributions
ngth+0.670
orsi+0.640
riction+0.622
spection+0.617
ordinary+0.614
Neg logit contributions
yond-0.398
swick-0.340
nance-0.325
hips-0.293
le-0.285
Token,
Token ID11
Feature activation-2.04e-01

Pos logit contributions
ngth+0.434
orsi+0.405
riction+0.389
spection+0.387
ordinary+0.380
Neg logit contributions
yond-0.461
swick-0.412
nance-0.399
hips-0.375
le-0.375
Token must
Token ID1276
Feature activation+1.70e+00

Pos logit contributions
yond+0.460
le+0.401
swick+0.401
nance+0.391
hips+0.390
Neg logit contributions
ngth-0.383
orsi-0.352
riction-0.331
 Pwr-0.328
spection-0.326
Token not
Token ID407
Feature activation-1.15e+00

Pos logit contributions
ngth+1.981
orsi+1.825
riction+1.725
spection+1.712
ordinary+1.670
Neg logit contributions
yond-2.321
swick-2.038
nance-2.022
le-1.952
hips-1.917
Token modify
Token ID13096
Feature activation+2.35e+00

Pos logit contributions
yond+1.249
nance+1.014
swick+0.988
le+0.976
hips+0.958
Neg logit contributions
ngth-1.706
orsi-1.587
riction-1.494
spection-1.489
UGE-1.466
Token the
Token ID262
Feature activation-5.11e-01

Pos logit contributions
ngth+2.821
orsi+2.613
riction+2.487
spection+2.467
ordinary+2.420
Neg logit contributions
yond-3.095
swick-2.755
nance-2.675
le-2.553
hips-2.534
Token state
Token ID1181
Feature activation-1.22e+00

Pos logit contributions
yond+0.392
swick+0.302
nance+0.300
le+0.284
hips+0.274
Neg logit contributions
ngth-0.911
orsi-0.854
riction-0.814
spection-0.813
ordinary-0.803
Token of
Token ID286
Feature activation+3.14e-01

Pos logit contributions
yond+1.052
swick+0.818
le+0.808
nance+0.790
hips+0.772
Neg logit contributions
ngth-2.112
orsi-1.968
riction-1.869
spection-1.842
renches-1.813
Token the
Token ID262
Feature activation-6.09e-01

Pos logit contributions
ngth+0.418
orsi+0.382
riction+0.360
spection+0.356
renches+0.345
Neg logit contributions
yond-0.388
swick-0.338
nance-0.327
le-0.322
hips-0.313
Token original
Token ID2656
Feature activation-1.22e+00

Pos logit contributions
yond+0.547
swick+0.444
nance+0.438
le+0.410
hips+0.403
Neg logit contributions
ngth-1.009
orsi-0.943
spection-0.901
riction-0.900
 Pwr-0.872
Token copy
Token ID4866
Feature activation+2.52e-01

Pos logit contributions
yond+1.355
swick+1.153
nance+1.143
le+1.115
hips+1.077
Neg logit contributions
ngth-1.738
orsi-1.600
riction-1.512
spection-1.511
renches-1.483
Token.
Token ID13
Feature activation-2.31e-01

Pos logit contributions
ngth+0.337
orsi+0.307
riction+0.286
spection+0.281
ftime+0.275
Neg logit contributions
yond-0.314
swick-0.273
le-0.265
nance-0.264
hips-0.259
Token Board
Token ID5926
Feature activation-1.03e-01

Pos logit contributions
yond+0.272
swick+0.240
nance+0.232
le+0.219
hips+0.219
Neg logit contributions
ngth-0.302
orsi-0.283
riction-0.273
spection-0.271
ordinary-0.266
Token out
Token ID503
Feature activation-5.24e-01

Pos logit contributions
ngth+1.232
orsi+1.143
riction+1.093
spection+1.086
ordinary+1.066
Neg logit contributions
yond-1.488
swick-1.334
nance-1.295
le-1.230
hips-1.223
Token of
Token ID286
Feature activation+1.04e+00

Pos logit contributions
yond+0.544
swick+0.473
nance+0.456
hips+0.419
le+0.417
Neg logit contributions
ngth-0.759
orsi-0.716
riction-0.692
spection-0.689
ordinary-0.680
Token hand
Token ID1021
Feature activation+1.12e+00

Pos logit contributions
ngth+0.994
orsi+0.913
riction+0.865
spection+0.859
ordinary+0.846
Neg logit contributions
yond-1.592
swick-1.452
nance-1.413
hips-1.342
le-1.339
Token and
Token ID290
Feature activation+1.55e-01

Pos logit contributions
ngth+1.282
orsi+1.191
riction+1.142
spection+1.134
ordinary+1.115
Neg logit contributions
yond-1.510
swick-1.354
nance-1.314
le-1.242
hips-1.240
Token the
Token ID262
Feature activation+3.36e-01

Pos logit contributions
ngth+0.183
orsi+0.170
riction+0.163
spection+0.162
ordinary+0.159
Neg logit contributions
yond-0.203
swick-0.182
nance-0.176
le-0.167
hips-0.166
Token shit
Token ID7510
Feature activation+2.16e+00

Pos logit contributions
ngth+0.390
orsi+0.363
riction+0.348
spection+0.345
ordinary+0.339
Neg logit contributions
yond-0.448
swick-0.401
nance-0.389
le-0.369
hips-0.366
Token hits
Token ID7127
Feature activation+1.04e+00

Pos logit contributions
ngth+2.640
orsi+2.462
riction+2.373
spection+2.371
ordinary+2.341
Neg logit contributions
yond-2.684
swick-2.396
nance-2.323
hips-2.159
le-2.131
Token the
Token ID262
Feature activation+5.76e-02

Pos logit contributions
ngth+1.122
orsi+1.043
riction+1.002
spection+0.993
ordinary+0.980
Neg logit contributions
yond-1.452
swick-1.311
nance-1.279
hips-1.197
le-1.185
Token fan
Token ID4336
Feature activation-4.96e-01

Pos logit contributions
ngth+0.059
orsi+0.054
riction+0.051
spection+0.051
ordinary+0.050
Neg logit contributions
yond-0.085
swick-0.077
nance-0.075
le-0.071
hips-0.071
Token.
Token ID13
Feature activation+3.15e-02

Pos logit contributions
yond+0.664
swick+0.593
nance+0.575
le+0.549
hips+0.548
Neg logit contributions
ngth-0.574
orsi-0.532
riction-0.511
spection-0.504
ordinary-0.498
Token Luckily
Token ID24262
Feature activation+2.22e+00

Pos logit contributions
ngth+0.043
orsi+0.041
riction+0.039
spection+0.039
ordinary+0.038
Neg logit contributions
yond-0.035
swick-0.031
nance-0.030
le-0.028
hips-0.028
Token USA
Token ID4916
Feature activation-1.08e-01

Pos logit contributions
yond+1.135
swick+1.011
nance+0.982
le+0.925
hips+0.922
Neg logit contributions
ngth-1.111
orsi-1.041
riction-1.000
spection-0.992
ordinary-0.978
Token State
Token ID1812
Feature activation+2.43e-01

Pos logit contributions
yond+0.141
swick+0.126
nance+0.123
le+0.116
hips+0.116
Neg logit contributions
ngth-0.127
orsi-0.118
riction-0.113
spection-0.113
ordinary-0.111
Token Ac
Token ID4013
Feature activation-5.83e-01

Pos logit contributions
ngth+0.293
orsi+0.272
riction+0.263
spection+0.262
ordinary+0.257
Neg logit contributions
yond-0.312
swick-0.279
nance-0.269
le-0.252
hips-0.251
Tokenro
Token ID305
Feature activation+3.21e-01

Pos logit contributions
yond+0.849
swick+0.769
nance+0.748
le+0.711
hips+0.709
Neg logit contributions
ngth-0.602
orsi-0.554
riction-0.528
spection-0.525
ordinary-0.515
Token
Token ID198
Feature activation-1.63e-01

Pos logit contributions
ngth+0.384
orsi+0.357
riction+0.343
spection+0.342
ordinary+0.336
Neg logit contributions
yond-0.417
swick-0.373
nance-0.361
hips-0.340
le-0.339
Token
Token ID198
Feature activation-2.83e-01

Pos logit contributions
yond+0.176
swick+0.151
le+0.146
nance+0.146
hips+0.141
Neg logit contributions
ngth-0.246
orsi-0.223
riction-0.211
spection-0.208
renches-0.203
TokenAc
Token ID12832
Feature activation-1.07e+00

Pos logit contributions
yond+0.405
swick+0.365
nance+0.356
le+0.337
hips+0.337
Neg logit contributions
ngth-0.301
orsi-0.278
riction-0.266
spection-0.264
ordinary-0.259
Tokenro
Token ID305
Feature activation+1.17e-01

Pos logit contributions
yond+1.575
swick+1.426
nance+1.388
le+1.318
hips+1.316
Neg logit contributions
ngth-1.100
orsi-1.013
riction-0.966
spection-0.959
ordinary-0.941
Token
Token ID198
Feature activation-2.06e-01

Pos logit contributions
ngth+0.141
orsi+0.131
riction+0.126
spection+0.126
ordinary+0.124
Neg logit contributions
yond-0.151
swick-0.135
nance-0.131
le-0.123
hips-0.123
Token
Token ID198
Feature activation-3.19e-01

Pos logit contributions
yond+0.222
swick+0.191
le+0.185
nance+0.184
hips+0.178
Neg logit contributions
ngth-0.311
orsi-0.282
riction-0.268
spection-0.263
renches-0.256
TokenAc
Token ID12832
Feature activation-9.56e-01

Pos logit contributions
yond+0.447
swick+0.402
nance+0.391
le+0.372
hips+0.371
Neg logit contributions
ngth-0.348
orsi-0.322
riction-0.308
spection-0.306
ordinary-0.300
Token mechanism
Token ID9030
Feature activation-1.07e+00

Pos logit contributions
ngth+0.433
orsi+0.407
riction+0.393
spection+0.390
ordinary+0.384
Neg logit contributions
yond-0.428
swick-0.380
nance-0.366
hips-0.343
le-0.342
Token had
Token ID550
Feature activation+1.13e+00

Pos logit contributions
yond+1.372
swick+1.218
nance+1.184
le+1.129
hips+1.128
Neg logit contributions
ngth-1.296
orsi-1.193
riction-1.147
spection-1.139
ordinary-1.125
Token broken
Token ID5445
Feature activation-1.81e+00

Pos logit contributions
ngth+1.192
orsi+1.102
riction+1.053
spection+1.045
ordinary+1.026
Neg logit contributions
yond-1.625
swick-1.469
nance-1.428
le-1.353
hips-1.351
Token under
Token ID739
Feature activation+5.00e-01

Pos logit contributions
yond+2.182
swick+1.891
nance+1.858
le+1.793
hips+1.757
Neg logit contributions
ngth-2.366
orsi-2.188
riction-2.086
spection-2.074
ordinary-2.038
Token the
Token ID262
Feature activation-3.47e-01

Pos logit contributions
ngth+0.554
orsi+0.514
riction+0.493
spection+0.489
ordinary+0.482
Neg logit contributions
yond-0.689
swick-0.621
nance-0.602
hips-0.569
le-0.569
Token air
Token ID1633
Feature activation-1.82e+00

Pos logit contributions
yond+0.480
swick+0.432
nance+0.420
le+0.398
hips+0.396
Neg logit contributions
ngth-0.385
orsi-0.357
riction-0.341
spection-0.339
ordinary-0.333
Tokenloads
Token ID46030
Feature activation+1.27e+00

Pos logit contributions
yond+2.379
swick+2.120
nance+2.056
le+1.953
hips+1.941
Neg logit contributions
ngth-2.149
orsi-2.000
riction-1.915
spection-1.909
ordinary-1.879
Token allowing
Token ID5086
Feature activation-6.68e-01

Pos logit contributions
ngth+1.465
orsi+1.371
riction+1.318
spection+1.306
ordinary+1.286
Neg logit contributions
yond-1.687
swick-1.526
nance-1.475
le-1.378
hips-1.374
Token the
Token ID262
Feature activation-5.00e-01

Pos logit contributions
yond+0.882
swick+0.787
nance+0.767
le+0.725
hips+0.722
Neg logit contributions
ngth-0.784
orsi-0.728
riction-0.694
spection-0.694
ordinary-0.680
Token wing
Token ID8539
Feature activation-3.64e-01

Pos logit contributions
yond+0.710
swick+0.639
nance+0.622
le+0.592
hips+0.590
Neg logit contributions
ngth-0.539
orsi-0.496
riction-0.474
spection-0.472
ordinary-0.462
Tokentips
Token ID41315
Feature activation-1.09e+00

Pos logit contributions
yond+0.436
swick+0.386
nance+0.373
hips+0.348
le+0.348
Neg logit contributions
ngth-0.471
orsi-0.442
riction-0.426
spection-0.424
ordinary-0.418
Token 59
Token ID7863
Feature activation+9.91e-01

Pos logit contributions
ngth+0.143
orsi+0.133
riction+0.128
spection+0.127
ordinary+0.125
Neg logit contributions
yond-0.148
swick-0.131
nance-0.127
le-0.120
hips-0.120
Token-
Token ID12
Feature activation+1.94e-01

Pos logit contributions
ngth+1.259
orsi+1.136
riction+1.098
spection+1.077
ordinary+1.041
Neg logit contributions
yond-1.274
swick-1.127
nance-1.099
le-1.059
hips-1.038
Token42
Token ID3682
Feature activation+1.08e-01

Pos logit contributions
ngth+0.260
orsi+0.238
riction+0.228
spection+0.223
 Pwr+0.217
Neg logit contributions
yond-0.238
swick-0.209
nance-0.202
le-0.199
hips-0.193
Token.
Token ID13
Feature activation+1.78e-01

Pos logit contributions
ngth+0.122
orsi+0.114
riction+0.109
spection+0.108
ordinary+0.106
Neg logit contributions
yond-0.147
swick-0.132
nance-0.128
le-0.121
hips-0.121
Token But
Token ID887
Feature activation+1.41e+00

Pos logit contributions
ngth+0.227
orsi+0.213
riction+0.205
spection+0.204
ordinary+0.201
Neg logit contributions
yond-0.216
swick-0.192
nance-0.185
le-0.174
hips-0.173
Token Mason
Token ID14737
Feature activation-7.43e-01

Pos logit contributions
ngth+1.687
orsi+1.576
riction+1.511
spection+1.505
ordinary+1.481
Neg logit contributions
yond-1.818
swick-1.623
nance-1.574
hips-1.479
le-1.477
Token earned
Token ID7366
Feature activation+3.47e-02

Pos logit contributions
yond+0.989
swick+0.888
nance+0.860
le+0.825
hips+0.816
Neg logit contributions
ngth-0.859
orsi-0.791
riction-0.766
spection-0.757
ordinary-0.745
Token the
Token ID262
Feature activation+5.45e-02

Pos logit contributions
ngth+0.041
orsi+0.038
riction+0.036
spection+0.036
ordinary+0.035
Neg logit contributions
yond-0.046
swick-0.041
nance-0.040
le-0.038
hips-0.038
Token game
Token ID983
Feature activation+8.88e-01

Pos logit contributions
ngth+0.065
orsi+0.061
riction+0.058
spection+0.058
ordinary+0.057
Neg logit contributions
yond-0.071
swick-0.063
nance-0.061
le-0.058
hips-0.057
Token
Token ID447
Feature activation+1.17e-01

Pos logit contributions
ngth+0.961
orsi+0.904
riction+0.860
spection+0.857
ordinary+0.851
Neg logit contributions
yond-1.233
swick-1.109
nance-1.079
hips-1.020
le-0.999
Token
Token ID247
Feature activation+5.85e-01

Pos logit contributions
ngth+0.155
orsi+0.146
riction+0.139
spection+0.139
ordinary+0.136
Neg logit contributions
yond-0.137
swick-0.120
nance-0.116
le-0.111
hips-0.111
Token Italian
Token ID8200
Feature activation-1.30e-01

Pos logit contributions
ngth+0.626
orsi+0.586
riction+0.564
spection+0.562
ordinary+0.554
Neg logit contributions
yond-0.632
swick-0.563
nance-0.544
hips-0.510
le-0.508
Token firm
Token ID4081
Feature activation-2.03e-01

Pos logit contributions
yond+0.166
swick+0.148
nance+0.144
le+0.135
hips+0.135
Neg logit contributions
ngth-0.158
orsi-0.148
riction-0.142
spection-0.141
ordinary-0.139
Token En
Token ID2039
Feature activation-7.12e-01

Pos logit contributions
yond+0.253
swick+0.225
nance+0.218
le+0.204
hips+0.204
Neg logit contributions
ngth-0.253
orsi-0.236
riction-0.227
spection-0.226
ordinary-0.223
Tokeni
Token ID72
Feature activation-1.74e-02

Pos logit contributions
yond+0.901
swick+0.803
nance+0.778
le+0.735
hips+0.730
Neg logit contributions
ngth-0.871
orsi-0.815
riction-0.782
spection-0.777
ordinary-0.765
Token received
Token ID2722
Feature activation-1.06e+00

Pos logit contributions
yond+0.022
swick+0.020
nance+0.019
le+0.018
hips+0.018
Neg logit contributions
ngth-0.021
orsi-0.020
riction-0.019
spection-0.019
ordinary-0.018
Token the
Token ID262
Feature activation-3.98e-01

Pos logit contributions
yond+1.488
swick+1.329
nance+1.314
le+1.258
hips+1.245
Neg logit contributions
ngth-1.158
orsi-1.068
riction-1.018
spection-1.003
ordinary-0.985
Token largest
Token ID4387
Feature activation-5.95e-01

Pos logit contributions
yond+0.478
swick+0.423
nance+0.411
le+0.387
hips+0.385
Neg logit contributions
ngth-0.514
orsi-0.481
riction-0.462
spection-0.458
ordinary-0.452
Token fine
Token ID3734
Feature activation+1.45e+00

Pos logit contributions
yond+0.720
swick+0.635
nance+0.618
le+0.582
hips+0.579
Neg logit contributions
ngth-0.764
orsi-0.715
riction-0.687
spection-0.683
ordinary-0.672
Token -
Token ID532
Feature activation+8.57e-01

Pos logit contributions
ngth+1.809
orsi+1.692
riction+1.633
spection+1.622
ordinary+1.603
Neg logit contributions
yond-1.788
swick-1.622
nance-1.545
hips-1.428
le-1.424
Token more
Token ID517
Feature activation+6.44e-01

Pos logit contributions
ngth+0.892
orsi+0.822
riction+0.785
spection+0.779
ordinary+0.764
Neg logit contributions
yond-1.244
swick-1.124
nance-1.095
le-1.041
hips-1.039
Token than
Token ID621
Feature activation+3.01e-01

Pos logit contributions
ngth+0.783
orsi+0.731
riction+0.703
spection+0.698
ordinary+0.688
Neg logit contributions
yond-0.820
swick-0.732
nance-0.708
le-0.666
hips-0.665
Token,
Token ID11
Feature activation-1.47e-01

Pos logit contributions
yond+1.237
swick+1.089
nance+1.049
le+1.003
hips+1.002
Neg logit contributions
ngth-1.248
orsi-1.167
riction-1.124
spection-1.111
ordinary-1.098
Token probably
Token ID2192
Feature activation-6.46e-02

Pos logit contributions
yond+0.185
swick+0.164
nance+0.159
le+0.150
hips+0.149
Neg logit contributions
ngth-0.181
orsi-0.169
riction-0.163
spection-0.162
ordinary-0.159
Token in
Token ID287
Feature activation-1.22e-01

Pos logit contributions
yond+0.078
swick+0.069
nance+0.067
le+0.063
hips+0.063
Neg logit contributions
ngth-0.083
orsi-0.078
riction-0.075
spection-0.074
ordinary-0.073
Token China
Token ID2807
Feature activation+1.41e-01

Pos logit contributions
yond+0.151
swick+0.134
nance+0.129
le+0.122
hips+0.122
Neg logit contributions
ngth-0.153
orsi-0.143
riction-0.138
spection-0.137
ordinary-0.135
Token.
Token ID13
Feature activation-9.97e-02

Pos logit contributions
ngth+0.167
orsi+0.156
riction+0.150
spection+0.149
ordinary+0.147
Neg logit contributions
yond-0.183
swick-0.164
nance-0.159
le-0.150
hips-0.149
Token This
Token ID770
Feature activation-4.35e-01

Pos logit contributions
yond+0.121
swick+0.107
nance+0.103
le+0.097
hips+0.097
Neg logit contributions
ngth-0.128
orsi-0.120
riction-0.115
spection-0.115
ordinary-0.113
Token would
Token ID561
Feature activation-1.22e+00

Pos logit contributions
yond+0.561
swick+0.500
nance+0.485
le+0.459
hips+0.457
Neg logit contributions
ngth-0.524
orsi-0.488
riction-0.469
spection-0.466
ordinary-0.458
Token mean
Token ID1612
Feature activation-1.30e+00

Pos logit contributions
yond+1.527
swick+1.359
nance+1.317
le+1.249
hips+1.246
Neg logit contributions
ngth-1.508
orsi-1.411
riction-1.352
spection-1.350
ordinary-1.322
Token co
Token ID763
Feature activation+6.67e-01

Pos logit contributions
yond+1.642
swick+1.449
nance+1.410
le+1.337
hips+1.332
Neg logit contributions
ngth-1.603
orsi-1.502
riction-1.442
spection-1.433
ordinary-1.408
Token-
Token ID12
Feature activation-7.68e-01

Pos logit contributions
ngth+0.668
orsi+0.614
riction+0.589
spection+0.584
ordinary+0.579
Neg logit contributions
yond-0.971
swick-0.889
nance-0.876
gency-0.807
eous-0.803
Tokenoperation
Token ID27184
Feature activation-4.73e-01

Pos logit contributions
yond+1.005
swick+0.899
nance+0.871
le+0.821
hips+0.820
Neg logit contributions
ngth-0.907
orsi-0.845
riction-0.811
spection-0.806
ordinary-0.793
Token by
Token ID416
Feature activation-2.40e-01

Pos logit contributions
yond+0.866
swick+0.771
nance+0.746
le+0.703
hips+0.702
Neg logit contributions
ngth-0.841
orsi-0.785
riction-0.755
spection-0.750
ordinary-0.739
Token the
Token ID262
Feature activation-1.19e-01

Pos logit contributions
yond+0.320
swick+0.287
nance+0.278
hips+0.262
le+0.261
Neg logit contributions
ngth-0.278
orsi-0.259
riction-0.249
spection-0.248
ordinary-0.243
Token wide
Token ID3094
Feature activation-1.64e-01

Pos logit contributions
yond+0.147
swick+0.130
nance+0.126
hips+0.118
le+0.118
Neg logit contributions
ngth-0.149
orsi-0.140
riction-0.134
spection-0.134
ordinary-0.132
Token-
Token ID12
Feature activation-4.25e-01

Pos logit contributions
yond+0.225
swick+0.203
nance+0.197
hips+0.186
le+0.185
Neg logit contributions
ngth-0.184
orsi-0.171
riction-0.164
spection-0.163
ordinary-0.160
Tokenranging
Token ID32319
Feature activation-7.23e-02

Pos logit contributions
yond+0.738
swick+0.679
nance+0.664
le+0.636
hips+0.635
Neg logit contributions
ngth-0.320
orsi-0.286
riction-0.267
spection-0.264
ordinary-0.257
Token crackdown
Token ID22671
Feature activation-1.03e+00

Pos logit contributions
yond+0.088
swick+0.078
nance+0.076
le+0.071
hips+0.071
Neg logit contributions
ngth-0.092
orsi-0.086
riction-0.083
spection-0.082
ordinary-0.081
Token were
Token ID547
Feature activation+2.05e-01

Pos logit contributions
yond+1.363
swick+1.221
nance+1.184
le+1.119
hips+1.117
Neg logit contributions
ngth-1.196
orsi-1.112
riction-1.067
spection-1.059
ordinary-1.044
Token 200
Token ID939
Feature activation-1.28e+00

Pos logit contributions
ngth+0.247
orsi+0.230
riction+0.221
spection+0.220
ordinary+0.216
Neg logit contributions
yond-0.263
swick-0.235
nance-0.228
le-0.214
hips-0.214
Token,
Token ID11
Feature activation-4.59e-03

Pos logit contributions
yond+1.613
swick+1.432
nance+1.393
le+1.318
hips+1.315
Neg logit contributions
ngth-1.565
orsi-1.466
riction-1.409
spection-1.394
ordinary-1.367
Token000
Token ID830
Feature activation+5.72e-01

Pos logit contributions
yond+0.006
swick+0.005
nance+0.005
le+0.005
hips+0.005
Neg logit contributions
ngth-0.005
orsi-0.005
riction-0.005
spection-0.005
ordinary-0.004
Token who
Token ID508
Feature activation+2.78e-01

Pos logit contributions
ngth+0.721
orsi+0.677
riction+0.649
spection+0.647
ordinary+0.641
Neg logit contributions
yond-0.700
swick-0.625
nance-0.601
le-0.561
hips-0.561
Token about
Token ID546
Feature activation+5.40e-01

Pos logit contributions
yond+0.010
swick+0.009
nance+0.009
le+0.009
hips+0.009
Neg logit contributions
ngth-0.008
orsi-0.007
riction-0.007
spection-0.007
ordinary-0.007
Token W
Token ID370
Feature activation-2.96e-01

Pos logit contributions
ngth+0.610
orsi+0.567
riction+0.543
spection+0.540
ordinary+0.531
Neg logit contributions
yond-0.734
swick-0.660
nance-0.641
le-0.604
hips-0.604
Tokenile
Token ID576
Feature activation-2.30e-01

Pos logit contributions
yond+0.384
swick+0.343
nance+0.333
le+0.313
hips+0.313
Neg logit contributions
ngth-0.353
orsi-0.329
riction-0.316
spection-0.314
ordinary-0.309
Token E
Token ID412
Feature activation+1.32e+00

Pos logit contributions
yond+0.245
swick+0.215
nance+0.206
hips+0.191
le+0.189
Neg logit contributions
ngth-0.328
orsi-0.310
riction-0.299
spection-0.297
ordinary-0.293
Token.
Token ID13
Feature activation-2.48e-01

Pos logit contributions
ngth+1.377
orsi+1.268
riction+1.212
spection+1.202
ordinary+1.171
Neg logit contributions
yond-1.882
swick-1.712
nance-1.668
hips-1.576
le-1.544
Token Coy
Token ID26887
Feature activation-3.74e+00

Pos logit contributions
yond+0.357
swick+0.327
nance+0.315
hips+0.299
le+0.293
Neg logit contributions
ngth-0.257
orsi-0.239
riction-0.229
spection-0.229
ordinary-0.223
Tokenote
Token ID1258
Feature activation+7.83e-01

Pos logit contributions
yond+3.515
swick+3.017
le+2.876
nance+2.780
hips+2.629
Neg logit contributions
ngth-5.907
orsi-5.424
riction-5.291
spection-5.168
ordinary-5.144
Token and
Token ID290
Feature activation-2.55e-01

Pos logit contributions
ngth+0.879
orsi+0.817
riction+0.782
spection+0.781
ordinary+0.767
Neg logit contributions
yond-1.066
swick-0.958
nance-0.934
hips-0.875
le-0.871
Token about
Token ID546
Feature activation+4.32e-01

Pos logit contributions
yond+0.345
swick+0.309
nance+0.300
le+0.285
hips+0.284
Neg logit contributions
ngth-0.290
orsi-0.269
riction-0.258
spection-0.255
ordinary-0.251
Token people
Token ID661
Feature activation-2.78e-01

Pos logit contributions
ngth+0.518
orsi+0.484
riction+0.466
spection+0.463
ordinary+0.456
Neg logit contributions
yond-0.556
swick-0.498
nance-0.482
hips-0.452
le-0.452
Token who
Token ID508
Feature activation+2.77e-01

Pos logit contributions
yond+0.349
swick+0.310
nance+0.300
le+0.283
hips+0.282
Neg logit contributions
ngth-0.344
orsi-0.321
riction-0.309
spection-0.307
ordinary-0.303
Token so
Token ID523
Feature activation-1.54e-01

Pos logit contributions
ngth+0.665
orsi+0.622
riction+0.598
spection+0.595
ordinary+0.585
Neg logit contributions
yond-0.748
swick-0.672
nance-0.651
le-0.610
hips-0.607
Token rapidly
Token ID8902
Feature activation-1.11e+00

Pos logit contributions
yond+0.207
swick+0.185
nance+0.180
le+0.170
hips+0.170
Neg logit contributions
ngth-0.178
orsi-0.165
riction-0.158
spection-0.157
ordinary-0.154
Token?
Token ID30
Feature activation+2.01e-01

Pos logit contributions
yond+1.461
swick+1.303
nance+1.265
le+1.201
hips+1.200
Neg logit contributions
ngth-1.312
orsi-1.217
riction-1.171
spection-1.159
ordinary-1.142
Token Though
Token ID7486
Feature activation-1.65e-01

Pos logit contributions
ngth+0.266
orsi+0.248
riction+0.241
spection+0.236
ordinary+0.233
Neg logit contributions
yond-0.237
swick-0.210
nance-0.201
le-0.192
hips-0.190
Token the
Token ID262
Feature activation+2.90e-01

Pos logit contributions
yond+0.214
swick+0.190
nance+0.185
le+0.174
hips+0.174
Neg logit contributions
ngth-0.197
orsi-0.183
riction-0.176
spection-0.175
ordinary-0.172
Token boom
Token ID14166
Feature activation-4.45e+00

Pos logit contributions
ngth+0.367
orsi+0.346
riction+0.332
spection+0.332
ordinary+0.328
Neg logit contributions
yond-0.352
swick-0.312
nance-0.302
hips-0.282
le-0.280
Token in
Token ID287
Feature activation+7.59e-02

Pos logit contributions
yond+5.218
swick+4.641
nance+4.435
le+4.305
hips+4.234
Neg logit contributions
ngth-5.652
orsi-5.223
riction-5.100
spection-5.000
 Pwr-4.975
Token global
Token ID3298
Feature activation-4.49e-01

Pos logit contributions
ngth+0.093
orsi+0.087
riction+0.084
spection+0.083
ordinary+0.082
Neg logit contributions
yond-0.096
swick-0.085
nance-0.083
le-0.077
hips-0.077
Token commodity
Token ID19464
Feature activation+6.62e-01

Pos logit contributions
yond+0.548
swick+0.484
nance+0.469
le+0.443
hips+0.441
Neg logit contributions
ngth-0.573
orsi-0.534
riction-0.515
spection-0.511
ordinary-0.502
Token prices
Token ID4536
Feature activation-5.94e-01

Pos logit contributions
ngth+0.974
orsi+0.928
riction+0.899
spection+0.892
ordinary+0.883
Neg logit contributions
yond-0.669
swick-0.581
nance-0.553
hips-0.506
le-0.505
Token played
Token ID2826
Feature activation+1.86e+00

Pos logit contributions
yond+0.745
swick+0.659
nance+0.640
hips+0.613
le+0.609
Neg logit contributions
ngth-0.741
orsi-0.682
riction-0.659
spection-0.654
ordinary-0.643
Token L
Token ID406
Feature activation+4.19e-01

Pos logit contributions
ngth+0.190
orsi+0.178
riction+0.170
spection+0.169
ordinary+0.167
Neg logit contributions
yond-0.189
swick-0.169
nance-0.163
hips-0.152
le-0.151
Tokenä
Token ID11033
Feature activation+7.96e-01

Pos logit contributions
ngth+0.528
orsi+0.497
riction+0.476
spection+0.471
ordinary+0.466
Neg logit contributions
yond-0.511
swick-0.459
nance-0.441
hips-0.412
le-0.407
Tokennt
Token ID429
Feature activation+7.37e-01

Pos logit contributions
ngth+0.971
orsi+0.907
riction+0.870
spection+0.866
ordinary+0.853
Neg logit contributions
yond-1.011
swick-0.900
nance-0.872
hips-0.819
le-0.815
Tokeninen
Token ID42326
Feature activation+1.01e-01

Pos logit contributions
ngth+0.949
orsi+0.893
riction+0.856
spection+0.850
ordinary+0.840
Neg logit contributions
yond-0.882
swick-0.783
nance-0.753
hips-0.705
le-0.696
Token,
Token ID11
Feature activation-2.34e-01

Pos logit contributions
ngth+0.114
orsi+0.106
spection+0.101
riction+0.100
ordinary+0.099
Neg logit contributions
yond-0.138
swick-0.124
nance-0.120
hips-0.114
le-0.112
Token Sus
Token ID8932
Feature activation-4.80e+00

Pos logit contributions
yond+0.288
swick+0.257
nance+0.247
hips+0.231
le+0.230
Neg logit contributions
ngth-0.295
orsi-0.277
riction-0.265
spection-0.265
ordinary-0.261
Tokenanna
Token ID7697
Feature activation-9.97e-01

Pos logit contributions
yond+5.990
swick+5.305
nance+5.210
le+5.092
hips+4.971
Neg logit contributions
ngth-5.728
orsi-5.322
riction-5.160
spection-5.159
EMBER-4.981
Token Ha
Token ID9398
Feature activation+8.02e-01

Pos logit contributions
yond+1.239
swick+1.101
nance+1.066
le+1.003
hips+0.999
Neg logit contributions
ngth-1.244
orsi-1.164
riction-1.121
spection-1.114
ordinary-1.097
Tokenav
Token ID615
Feature activation+9.85e-01

Pos logit contributions
ngth+0.927
orsi+0.866
riction+0.828
spection+0.821
ordinary+0.811
Neg logit contributions
yond-1.065
swick-0.961
nance-0.929
hips-0.874
le-0.866
Tokenist
Token ID396
Feature activation-6.05e-03

Pos logit contributions
ngth+1.238
orsi+1.164
riction+1.117
spection+1.108
ordinary+1.095
Neg logit contributions
yond-1.211
swick-1.078
nance-1.042
hips-0.975
le-0.969
Tokeno
Token ID78
Feature activation-1.35e-01

Pos logit contributions
yond+0.007
swick+0.006
nance+0.006
hips+0.006
le+0.005
Neg logit contributions
ngth-0.008
orsi-0.008
riction-0.007
spection-0.007
ordinary-0.007
Token.
Token ID13
Feature activation+1.27e-01

Pos logit contributions
yond+1.587
swick+1.396
nance+1.353
le+1.283
hips+1.282
Neg logit contributions
ngth-1.661
orsi-1.542
riction-1.491
spection-1.473
ordinary-1.452
Token
Token ID198
Feature activation+1.69e-01

Pos logit contributions
ngth+0.163
orsi+0.153
riction+0.147
spection+0.146
ordinary+0.144
Neg logit contributions
yond-0.153
swick-0.136
nance-0.131
le-0.123
hips-0.123
Token
Token ID198
Feature activation+2.03e-02

Pos logit contributions
ngth+0.205
orsi+0.192
riction+0.185
spection+0.184
ordinary+0.182
Neg logit contributions
yond-0.214
swick-0.190
nance-0.185
hips-0.172
le-0.172
TokenRen
Token ID26764
Feature activation-4.87e-01

Pos logit contributions
ngth+0.023
orsi+0.021
riction+0.020
spection+0.020
ordinary+0.020
Neg logit contributions
yond-0.028
swick-0.025
nance-0.024
le-0.023
hips-0.023
Tokenowned
Token ID11990
Feature activation-8.78e-01

Pos logit contributions
yond+0.603
swick+0.536
nance+0.519
le+0.490
hips+0.488
Neg logit contributions
ngth-0.611
orsi-0.571
riction-0.548
spection-0.545
ordinary-0.537
Token dou
Token ID2255
Feature activation-3.63e+00

Pos logit contributions
yond+1.106
swick+0.984
nance+0.954
le+0.906
hips+0.899
Neg logit contributions
ngth-1.081
orsi-1.010
riction-0.971
spection-0.962
ordinary-0.942
Tokenjin
Token ID18594
Feature activation-6.46e-01

Pos logit contributions
yond+3.260
swick+2.764
nance+2.692
le+2.548
hips+2.414
Neg logit contributions
ngth-5.660
orsi-5.459
riction-5.271
spection-5.197
ordinary-5.135
Token video
Token ID2008
Feature activation-7.76e-02

Pos logit contributions
yond+0.814
swick+0.727
nance+0.702
le+0.665
hips+0.660
Neg logit contributions
ngth-0.798
orsi-0.746
riction-0.714
spection-0.708
ordinary-0.696
Token game
Token ID983
Feature activation+1.76e+00

Pos logit contributions
yond+0.104
swick+0.093
nance+0.090
le+0.085
hips+0.085
Neg logit contributions
ngth-0.090
orsi-0.084
riction-0.080
spection-0.080
ordinary-0.078
Token maker
Token ID16009
Feature activation-1.34e+00

Pos logit contributions
ngth+2.192
orsi+2.058
riction+1.986
spection+1.975
ordinary+1.949
Neg logit contributions
yond-2.161
swick-1.922
nance-1.854
hips-1.737
le-1.721
Token Jun
Token ID7653
Feature activation+9.38e-01

Pos logit contributions
yond+1.640
swick+1.459
nance+1.411
le+1.339
hips+1.334
Neg logit contributions
ngth-1.694
orsi-1.592
riction-1.523
spection-1.511
ordinary-1.487
Token a
Token ID257
Feature activation+6.81e-01

Pos logit contributions
ngth+0.090
orsi+0.084
riction+0.081
spection+0.080
ordinary+0.079
Neg logit contributions
yond-0.104
swick-0.094
nance-0.091
hips-0.085
le-0.085
Token pot
Token ID1787
Feature activation-2.06e+00

Pos logit contributions
ngth+0.833
orsi+0.778
riction+0.748
spection+0.743
ordinary+0.731
Neg logit contributions
yond-0.864
swick-0.770
nance-0.746
le-0.703
hips-0.701
Token-
Token ID12
Feature activation-3.86e-01

Pos logit contributions
yond+2.604
swick+2.319
nance+2.246
le+2.110
hips+2.108
Neg logit contributions
ngth-2.526
orsi-2.360
riction-2.269
spection-2.255
ordinary-2.221
Tokenadd
Token ID2860
Feature activation+1.62e+00

Pos logit contributions
yond+0.452
swick+0.399
nance+0.384
hips+0.356
le+0.350
Neg logit contributions
ngth-0.507
orsi-0.477
spection-0.460
riction-0.460
ordinary-0.456
Tokenled
Token ID992
Feature activation+6.91e-01

Pos logit contributions
ngth+2.246
orsi+2.122
riction+2.083
spection+2.049
ordinary+2.026
Neg logit contributions
yond-1.753
swick-1.545
nance-1.472
hips-1.376
gency-1.323
Token Ober
Token ID33753
Feature activation-4.27e+00

Pos logit contributions
ngth+0.843
orsi+0.788
riction+0.759
spection+0.755
ordinary+0.745
Neg logit contributions
yond-0.876
swick-0.781
nance-0.755
hips-0.708
le-0.706
Tokenlin
Token ID2815
Feature activation-2.49e+00

Pos logit contributions
yond+3.671
swick+3.054
nance+2.918
le+2.854
hips+2.631
Neg logit contributions
ngth-6.892
orsi-6.615
riction-6.325
spection-6.306
ordinary-6.274
Token College
Token ID5535
Feature activation+3.17e-01

Pos logit contributions
yond+3.140
swick+2.831
nance+2.760
le+2.613
hips+2.586
Neg logit contributions
ngth-3.027
orsi-2.811
riction-2.694
spection-2.667
ordinary-2.630
Token freshman
Token ID18621
Feature activation+8.22e-01

Pos logit contributions
ngth+0.374
orsi+0.349
riction+0.335
spection+0.333
ordinary+0.327
Neg logit contributions
yond-0.417
swick-0.373
nance-0.361
le-0.340
hips-0.340
Token's
Token ID338
Feature activation-6.79e-01

Pos logit contributions
ngth+0.996
orsi+0.934
riction+0.897
spection+0.893
ordinary+0.880
Neg logit contributions
yond-1.046
swick-0.933
nance-0.902
hips-0.844
le-0.843
Token
Token ID851
Feature activation-1.81e+00

Pos logit contributions
yond+0.849
swick+0.754
nance+0.732
le+0.690
hips+0.690
Neg logit contributions
ngth-0.843
orsi-0.787
riction-0.757
spection-0.751
ordinary-0.740