TOP ACTIVATIONS
MAX = 1.545

P WM fan setup with Pro pe ller Blade Technology and
( O mega Pharma - Quick step ) s . t
8 cm fan setup with Pro pe ller Blade Technology generate
ap = arg parse . Arg ument Parser () ap .
not there and my friends and family aren 't there .
( O mega Pharma - Quick step ) s . t
j ule p after mint j ule p at his desk
chosen based on stat istical data , prior complaints
removed and turn the V itus into a fixed gear bike
movie that sparked all this h oo - fer - ah
ert of the University of Gu el ph in Ontario ,
, including last week against San Diego when he scored just
as d Gu M ih o
such as hang gl iders . However , maybe
, or with your friends or roomm ates , for example
so on you need Pixel pipe . Shoot your photo
When Trump named his vice presidential pick , Gov . Mike
pave the way for re - establish ing a balance between
his prison , Worm t ong ue drops a sphere to
with Blake Wheeler and Mark Sche ife le has been strong

MIN ACTIVATIONS
MIN = -1.414

opponents physically and gets under their skin between plays . And
it is impossible to dis amb ig uate any single measurement
their mind . Get under their skin . I talk my
ag awa , ip ag pat ul oy lang n atin
comic . Ex ceptions to this include " The C MC
our senior civil servants , being fully bilingual ."
to be known as the Feder ated Islands of The Former
"). Male - to - female ( M TF ) transgender
S por adic gunfire rocked the new nation
v . normal * 1 ; } 1 2 3 void
t know how to behave in the 21 st
Ferdinand 's deep cross , Lor ik Can a sent another
senior civil servants , being fully bilingual ." In
make them useful . A 5 - mic ron pin hole
You can buy An Enemy of the State : The Life
1 db 439 70 de 5 e 4 cb 0 c
may legisl ate only within the subject areas enumer ated under
fact that roughly two out of every five Americans knows about
( m Grid Template ) ; density Grid . Init (
like N airo bi and M omb asa to make public

INTERVAL 0.805 - 1.545
CONTAINS 0.221%

prev _ state : Option < Board > , // The
we believe it 's vital that we pursue this common ground
types , ( B ) Type 1 probe test ( tri
# deb ates # Occup y The Deb ates pic .
of to secure his re - election , she can claim

INTERVAL 0.066 - 0.805
CONTAINS 39.412%

public property in Roh t ak city and parts of Roh
in time for the season opener , he replied :
2 Richard Sherman , Seahawks 1 AL READ Y COMP ET
its efforts in education , health and workforce matters .
pay a fixed return based on the profit generated by an

INTERVAL -0.674 - 0.066
CONTAINS 59.658%

next generation sequencing data . To our knowledge , we believe
'm trying very hard to craft a bill to strike a
Monday , but said it would try to mitigate the impact
the cigarette lighter inside the console storage area ( under the
that you really want in your collection . A great example

INTERVAL -1.414 - -0.674
CONTAINS 0.709%

Friends and foes alike hardly mention Land rie u
pause . A very long pause . During that time I
. x . x . 105 12 06 107 x .
of multi - store y residential and commercial buildings .
. He is one of the few , unfortunately forgotten today
Token P
Token ID350
Feature activation-1.32e-01

Pos logit contributions
+0.887
enegger+0.836
igham+0.793
 NIC+0.780
 Eag+0.763
Neg logit contributions
Ore-1.039
 Isis-0.980
 cherry-0.978
lining-0.957
ppo-0.955
TokenWM
Token ID22117
Feature activation-2.01e-01

Pos logit contributions
+1.009
enegger+0.959
igham+0.907
+0.866
 NIC+0.866
Neg logit contributions
Ore-1.496
 cherry-1.443
 Isis-1.430
lining-1.401
ppo-1.385
Token fan
Token ID4336
Feature activation+2.36e-02

Pos logit contributions
+1.947
enegger+1.843
igham+1.756
 NIC+1.749
 Eag+1.690
Neg logit contributions
Ore-1.875
 Isis-1.750
 cherry-1.746
ppo-1.718
lining-1.709
Token setup
Token ID9058
Feature activation-1.98e-01

Pos logit contributions
Ore+0.205
 cherry+0.195
 Isis+0.194
lining+0.187
ppo+0.186
Neg logit contributions
-0.244
enegger-0.235
igham-0.224
-0.219
 NIC-0.217
Token with
Token ID351
Feature activation-1.39e-01

Pos logit contributions
+1.878
enegger+1.774
igham+1.699
 NIC+1.690
 Eag+1.637
Neg logit contributions
Ore-1.880
 Isis-1.756
 cherry-1.751
ppo-1.713
lining-1.700
Token Pro
Token ID1041
Feature activation+1.54e+00

Pos logit contributions
+1.334
enegger+1.258
igham+1.205
 NIC+1.185
 Eag+1.165
Neg logit contributions
Ore-1.316
 Isis-1.234
 cherry-1.226
ppo-1.197
lining-1.197
Tokenpe
Token ID431
Feature activation+6.00e-01

Pos logit contributions
Ore+6.955
pec+6.426
ppo+6.289
lining+5.915
 Isis+5.898
Neg logit contributions
-18.650
enegger-18.571
ModLoader-17.807
-17.750
-17.534
Tokenller
Token ID6051
Feature activation+5.61e-01

Pos logit contributions
Ore+4.915
 cherry+4.662
ppo+4.533
 Isis+4.449
lining+4.410
Neg logit contributions
-6.301
enegger-6.268
-5.867
igham-5.842
 Eag-5.804
TokenBlade
Token ID47520
Feature activation-5.14e-01

Pos logit contributions
Ore+4.713
 Isis+4.398
lining+4.324
 cherry+4.299
Bee+4.161
Neg logit contributions
-5.694
enegger-5.578
igham-5.283
-5.208
 NIC-5.143
Token Technology
Token ID8987
Feature activation+4.39e-02

Pos logit contributions
+4.716
enegger+4.452
 NIC+4.279
igham+4.228
+4.112
Neg logit contributions
Ore-4.840
 cherry-4.556
 Isis-4.521
ppo-4.478
lining-4.380
Token and
Token ID290
Feature activation-2.13e-01

Pos logit contributions
Ore+0.400
 cherry+0.380
 Isis+0.379
lining+0.366
ppo+0.363
Neg logit contributions
-0.437
enegger-0.420
igham-0.400
-0.389
 NIC-0.386
Token (
Token ID357
Feature activation+4.43e-01

Pos logit contributions
+2.139
enegger+2.088
igham+1.984
 NIC+1.925
+1.908
Neg logit contributions
Ore-1.988
 cherry-1.879
 Isis-1.871
lining-1.818
ppo-1.781
TokenO
Token ID46
Feature activation+3.19e-01

Pos logit contributions
Ore+4.038
 Isis+3.642
 cherry+3.620
Bee+3.499
lining+3.492
Neg logit contributions
enegger-4.418
-4.376
igham-4.178
-3.981
 Eag-3.942
Tokenmega
Token ID13731
Feature activation-3.79e-01

Pos logit contributions
Ore+3.341
 Isis+3.220
ppo+3.176
 cherry+3.166
lining+3.072
Neg logit contributions
-2.665
enegger-2.622
igham-2.417
-2.380
 NIC-2.336
Token Pharma
Token ID41845
Feature activation+2.78e-01

Pos logit contributions
+3.305
enegger+3.177
igham+2.980
 NIC+2.948
 Eag+2.838
Neg logit contributions
Ore-3.804
 cherry-3.590
 Isis-3.565
lining-3.524
ppo-3.487
Token -
Token ID532
Feature activation+2.53e-01

Pos logit contributions
Ore+2.415
 Isis+2.333
 cherry+2.311
lining+2.198
ppo+2.161
Neg logit contributions
-2.853
enegger-2.789
igham-2.676
-2.629
 NIC-2.528
Token Quick
Token ID12029
Feature activation+1.48e+00

Pos logit contributions
Ore+2.151
 Isis+2.070
 cherry+2.059
ppo+1.956
lining+1.945
Neg logit contributions
-2.625
enegger-2.587
igham-2.458
-2.417
 Eag-2.313
Tokenstep
Token ID9662
Feature activation-1.43e-01

Pos logit contributions
Ore+5.460
 cherry+5.129
lining+5.008
ppo+4.797
step+4.790
Neg logit contributions
enegger-19.818
-19.723
ModLoader-19.648
-18.919
 teasp-18.873
Token)
Token ID8
Feature activation+2.92e-01

Pos logit contributions
+1.464
enegger+1.379
igham+1.303
 NIC+1.288
 Eag+1.267
Neg logit contributions
Ore-1.251
 cherry-1.191
 Isis-1.189
lining-1.153
ppo-1.141
Token s
Token ID264
Feature activation+6.39e-02

Pos logit contributions
Ore+2.209
 cherry+2.117
 Isis+2.095
ppo+1.987
lining+1.984
Neg logit contributions
-3.303
enegger-3.205
igham-3.082
-2.998
 NIC-2.961
Token.
Token ID13
Feature activation+1.41e-01

Pos logit contributions
Ore+0.578
 cherry+0.549
 Isis+0.548
lining+0.529
ppo+0.525
Neg logit contributions
-0.640
enegger-0.616
igham-0.586
-0.571
 NIC-0.566
Tokent
Token ID83
Feature activation+1.32e-01

Pos logit contributions
Ore+1.380
 cherry+1.312
 Isis+1.308
lining+1.274
ppo+1.262
Neg logit contributions
-1.310
enegger-1.272
igham-1.206
-1.176
 NIC-1.158
Token 8
Token ID807
Feature activation+2.22e-02

Pos logit contributions
+0.795
enegger+0.752
igham+0.723
 NIC+0.710
+0.695
Neg logit contributions
Ore-0.772
 cherry-0.725
 Isis-0.724
ppo-0.705
lining-0.701
Tokencm
Token ID11215
Feature activation-7.62e-02

Pos logit contributions
Ore+0.197
 cherry+0.187
 Isis+0.187
lining+0.180
ppo+0.179
Neg logit contributions
-0.226
enegger-0.217
igham-0.208
-0.202
 NIC-0.201
Token fan
Token ID4336
Feature activation+1.58e-01

Pos logit contributions
+0.723
enegger+0.685
igham+0.655
 NIC+0.642
 Eag+0.630
Neg logit contributions
Ore-0.731
 Isis-0.688
 cherry-0.686
lining-0.671
ppo-0.669
Token setup
Token ID9058
Feature activation-2.29e-01

Pos logit contributions
Ore+1.410
 cherry+1.349
 Isis+1.344
lining+1.297
ppo+1.282
Neg logit contributions
-1.597
enegger-1.548
igham-1.468
-1.441
 NIC-1.401
Token with
Token ID351
Feature activation+3.68e-01

Pos logit contributions
+2.259
enegger+2.127
igham+2.049
 NIC+2.039
 Eag+1.982
Neg logit contributions
Ore-2.102
 Isis-1.954
 cherry-1.930
lining-1.899
ppo-1.898
Token Pro
Token ID1041
Feature activation+1.45e+00

Pos logit contributions
Ore+3.289
 cherry+3.210
 Isis+3.168
lining+3.046
ppo+2.983
Neg logit contributions
-3.627
enegger-3.549
igham-3.340
-3.313
 NIC-3.141
Tokenpe
Token ID431
Feature activation+3.43e-01

Pos logit contributions
Ore+7.066
 Isis+6.794
 cherry+6.658
ppo+6.643
pec+6.477
Neg logit contributions
enegger-16.302
-15.960
igham-15.349
 Ghana-15.083
-14.699
Tokenller
Token ID6051
Feature activation+7.18e-01

Pos logit contributions
Ore+2.988
 cherry+2.849
 Isis+2.759
ppo+2.750
lining+2.721
Neg logit contributions
-3.492
enegger-3.468
igham-3.221
-3.192
 Eag-3.147
TokenBlade
Token ID47520
Feature activation+8.00e-03

Pos logit contributions
Ore+5.666
 Isis+5.337
 cherry+5.261
lining+5.251
Bee+5.036
Neg logit contributions
-7.357
enegger-7.235
igham-6.834
-6.774
 NIC-6.597
Token Technology
Token ID8987
Feature activation+1.60e-01

Pos logit contributions
Ore+0.073
 cherry+0.069
 Isis+0.069
lining+0.067
ppo+0.066
Neg logit contributions
-0.080
enegger-0.076
igham-0.073
 NIC-0.071
-0.071
Token generate
Token ID7716
Feature activation-2.53e-01

Pos logit contributions
Ore+1.393
 cherry+1.328
 Isis+1.322
lining+1.273
ppo+1.262
Neg logit contributions
-1.651
enegger-1.595
igham-1.519
-1.484
 NIC-1.460
Token ap
Token ID2471
Feature activation+1.80e-01

Pos logit contributions
Ore+1.862
 cherry+1.751
 Isis+1.659
lining+1.512
ppo+1.509
Neg logit contributions
-5.694
enegger-5.515
igham-5.339
-5.244
 NIC-5.124
Token =
Token ID796
Feature activation+6.22e-01

Pos logit contributions
Ore+2.098
 cherry+2.004
 Isis+1.997
lining+1.948
ppo+1.936
Neg logit contributions
-1.344
enegger-1.291
igham-1.212
-1.163
 Eag-1.134
Token arg
Token ID1822
Feature activation+5.60e-01

Pos logit contributions
 cherry+2.953
Ore+2.935
 Isis+2.649
lining+2.465
ppo+2.422
Neg logit contributions
-8.794
enegger-8.607
-8.392
igham-8.295
 Eag-7.808
Tokenparse
Token ID29572
Feature activation+2.18e-01

Pos logit contributions
Ore+2.611
 cherry+2.430
lining+2.336
 Isis+2.315
ppo+2.236
Neg logit contributions
-7.838
enegger-7.747
-7.407
igham-7.397
 NIC-7.338
Token.
Token ID13
Feature activation+9.25e-01

Pos logit contributions
Ore+1.871
 cherry+1.768
 Isis+1.763
lining+1.694
ppo+1.670
Neg logit contributions
-2.273
enegger-2.223
igham-2.133
-2.077
 NIC-2.020
TokenArg
Token ID28100
Feature activation+1.41e+00

Pos logit contributions
Ore+2.623
Bee+1.243
ppo+1.186
 Isis+1.180
ifier+1.125
Neg logit contributions
enegger-15.132
igham-14.708
-14.595
-14.127
-14.010
Tokenument
Token ID1713
Feature activation+9.42e-01

Pos logit contributions
Ore+4.435
ifier+4.046
 cherry+3.052
lining+2.831
Bee+2.611
Neg logit contributions
enegger-20.211
-20.110
-19.514
-19.502
 exting-19.132
TokenParser
Token ID46677
Feature activation+6.45e-01

Pos logit contributions
Ore+3.918
ifier+2.768
 cherry+2.750
 Isis+2.741
Bee+2.490
Neg logit contributions
enegger-13.803
-13.642
igham-13.625
-13.050
 Eag-12.910
Token()
Token ID3419
Feature activation+6.13e-01

Pos logit contributions
Ore+3.378
 cherry+3.060
 Isis+3.024
lining+2.796
ppo+2.780
Neg logit contributions
-8.638
igham-8.598
enegger-8.528
-8.126
 Eag-8.027
Token ap
Token ID2471
Feature activation-1.13e-02

Pos logit contributions
Ore+2.636
 cherry+2.580
 Isis+2.323
 pid+2.099
lining+2.062
Neg logit contributions
-9.012
enegger-8.831
-8.515
igham-8.424
 NIC-8.024
Token.
Token ID13
Feature activation-3.49e-01

Pos logit contributions
+0.111
enegger+0.106
igham+0.101
+0.098
 NIC+0.098
Neg logit contributions
Ore-0.103
 cherry-0.099
 Isis-0.098
lining-0.095
ppo-0.095
Token not
Token ID407
Feature activation-2.02e-01

Pos logit contributions
Ore+0.454
 Isis+0.430
 cherry+0.429
lining+0.416
ppo+0.413
Neg logit contributions
-0.472
enegger-0.453
igham-0.431
-0.418
 NIC-0.417
Token there
Token ID612
Feature activation+7.42e-02

Pos logit contributions
+1.951
enegger+1.870
igham+1.780
 NIC+1.755
 Eag+1.725
Neg logit contributions
Ore-1.869
 Isis-1.742
 cherry-1.721
ppo-1.694
lining-1.689
Token and
Token ID290
Feature activation-1.13e-01

Pos logit contributions
Ore+0.697
 cherry+0.667
 Isis+0.664
lining+0.643
ppo+0.637
Neg logit contributions
-0.715
enegger-0.686
igham-0.653
-0.636
 NIC-0.628
Token my
Token ID616
Feature activation-4.61e-02

Pos logit contributions
+1.117
enegger+1.077
igham+1.028
 NIC+1.004
 Eag+0.993
Neg logit contributions
Ore-1.020
 Isis-0.951
 cherry-0.950
lining-0.927
ppo-0.921
Token friends
Token ID2460
Feature activation+2.00e-01

Pos logit contributions
+0.470
enegger+0.454
igham+0.432
 NIC+0.422
+0.419
Neg logit contributions
Ore-0.405
 Isis-0.380
 cherry-0.379
lining-0.368
ppo-0.366
Token and
Token ID290
Feature activation+1.40e+00

Pos logit contributions
Ore+1.748
 cherry+1.694
 Isis+1.679
lining+1.615
ppo+1.607
Neg logit contributions
-2.058
enegger-1.975
igham-1.887
-1.851
 NIC-1.810
Token family
Token ID1641
Feature activation-2.61e-01

Pos logit contributions
 Isis+7.835
 cherry+7.638
Ore+7.403
lining+6.632
 Pike+6.513
Neg logit contributions
-16.197
enegger-15.715
igham-15.179
-15.135
 Eag-13.666
Token aren
Token ID3588
Feature activation+2.18e-01

Pos logit contributions
+2.418
enegger+2.330
igham+2.198
 NIC+2.165
 Eag+2.119
Neg logit contributions
Ore-2.524
 Isis-2.341
 cherry-2.306
lining-2.279
ppo-2.257
Token't
Token ID470
Feature activation-2.29e-01

Pos logit contributions
Ore+1.579
 cherry+1.462
 Isis+1.458
lining+1.393
ppo+1.381
Neg logit contributions
-2.552
enegger-2.530
igham-2.427
-2.361
 Eag-2.330
Token there
Token ID612
Feature activation+1.04e-01

Pos logit contributions
+2.045
enegger+1.966
igham+1.853
 NIC+1.833
 Eag+1.782
Neg logit contributions
Ore-2.268
 Isis-2.132
 cherry-2.114
lining-2.064
ppo-2.055
Token.
Token ID13
Feature activation-2.87e-02

Pos logit contributions
Ore+0.886
 cherry+0.846
 Isis+0.841
lining+0.812
ppo+0.804
Neg logit contributions
-1.091
enegger-1.050
igham-1.005
-0.981
 NIC-0.968
Token (
Token ID357
Feature activation+3.49e-01

Pos logit contributions
+1.486
enegger+1.435
igham+1.368
 NIC+1.325
+1.313
Neg logit contributions
Ore-1.346
 cherry-1.274
 Isis-1.268
lining-1.232
ppo-1.222
TokenO
Token ID46
Feature activation+3.75e-01

Pos logit contributions
Ore+3.094
 Isis+2.836
 cherry+2.824
lining+2.711
ppo+2.708
Neg logit contributions
-3.555
enegger-3.552
igham-3.383
-3.243
 Eag-3.189
Tokenmega
Token ID13731
Feature activation-2.65e-01

Pos logit contributions
Ore+4.232
 Isis+4.117
ppo+4.073
 cherry+4.030
lining+3.917
Neg logit contributions
-2.789
enegger-2.743
igham-2.490
-2.487
 NIC-2.392
Token Pharma
Token ID41845
Feature activation+4.08e-01

Pos logit contributions
+2.441
enegger+2.338
igham+2.220
 NIC+2.167
 Eag+2.106
Neg logit contributions
Ore-2.572
 cherry-2.438
 Isis-2.411
lining-2.375
ppo-2.352
Token -
Token ID532
Feature activation+3.23e-01

Pos logit contributions
Ore+3.315
 Isis+3.261
 cherry+3.209
lining+3.053
ppo+2.935
Neg logit contributions
-4.320
enegger-4.199
igham-4.075
-4.017
 NIC-3.827
Token Quick
Token ID12029
Feature activation+1.39e+00

Pos logit contributions
Ore+2.680
 Isis+2.594
 cherry+2.570
ppo+2.434
lining+2.429
Neg logit contributions
-3.420
enegger-3.366
igham-3.165
-3.133
 Eag-3.012
Tokenstep
Token ID9662
Feature activation-6.56e-02

Pos logit contributions
Ore+5.110
 cherry+4.739
lining+4.535
 Isis+4.264
step+4.193
Neg logit contributions
enegger-18.948
ModLoader-18.549
-18.110
 NIC-17.849
-17.840
Token)
Token ID8
Feature activation+3.58e-01

Pos logit contributions
+0.688
enegger+0.655
igham+0.622
 NIC+0.610
+0.605
Neg logit contributions
Ore-0.561
 cherry-0.533
 Isis-0.532
lining-0.514
ppo-0.509
Token s
Token ID264
Feature activation+6.08e-02

Pos logit contributions
Ore+2.638
 cherry+2.544
 Isis+2.510
ppo+2.384
lining+2.365
Neg logit contributions
-4.085
enegger-3.979
igham-3.831
-3.722
 NIC-3.671
Token.
Token ID13
Feature activation+1.79e-01

Pos logit contributions
Ore+0.550
 cherry+0.523
 Isis+0.522
lining+0.504
ppo+0.500
Neg logit contributions
-0.609
enegger-0.586
igham-0.558
-0.543
 NIC-0.539
Tokent
Token ID83
Feature activation+1.27e-01

Pos logit contributions
Ore+1.725
 cherry+1.638
 Isis+1.632
lining+1.594
ppo+1.577
Neg logit contributions
-1.672
enegger-1.629
igham-1.545
-1.512
 NIC-1.485
Token j
Token ID474
Feature activation+6.55e-01

Pos logit contributions
Ore+3.296
 cherry+3.183
 Isis+3.076
lining+2.958
ppo+2.910
Neg logit contributions
-4.156
enegger-4.036
igham-3.789
-3.716
 NIC-3.680
Tokenule
Token ID2261
Feature activation+2.72e-01

Pos logit contributions
Ore+4.873
 cherry+4.686
 Isis+4.507
ppo+4.498
ifier+4.455
Neg logit contributions
-7.293
enegger-7.034
-6.796
 Eag-6.578
igham-6.504
Tokenp
Token ID79
Feature activation+1.54e-01

Pos logit contributions
Ore+1.731
 cherry+1.613
 Isis+1.593
ppo+1.526
lining+1.506
Neg logit contributions
-3.473
enegger-3.397
igham-3.232
-3.155
 NIC-3.134
Token after
Token ID706
Feature activation-4.30e-01

Pos logit contributions
Ore+1.368
 cherry+1.311
 Isis+1.296
lining+1.244
ppo+1.235
Neg logit contributions
-1.574
enegger-1.511
igham-1.439
-1.403
 NIC-1.378
Token mint
Token ID21043
Feature activation+5.61e-01

Pos logit contributions
+4.060
enegger+3.858
igham+3.766
 NIC+3.714
 Eag+3.634
Neg logit contributions
Ore-3.881
ppo-3.586
 Isis-3.581
lining-3.560
 cherry-3.478
Token j
Token ID474
Feature activation+1.39e+00

Pos logit contributions
 cherry+4.273
Ore+4.245
 Isis+4.051
lining+3.820
ppo+3.770
Neg logit contributions
-6.269
enegger-6.086
igham-5.732
-5.682
 Eag-5.599
Tokenule
Token ID2261
Feature activation+3.45e-01

Pos logit contributions
Ore+4.686
 cherry+4.257
ppo+3.925
pec+3.851
ifier+3.844
Neg logit contributions
enegger-19.617
-19.189
-19.164
 Eag-18.877
-18.787
Tokenp
Token ID79
Feature activation-2.47e-01

Pos logit contributions
Ore+2.355
 cherry+2.240
 Isis+2.188
ppo+2.184
lining+2.096
Neg logit contributions
-4.202
enegger-4.101
igham-3.895
-3.864
 NIC-3.813
Token at
Token ID379
Feature activation-2.44e-01

Pos logit contributions
+2.330
enegger+2.226
igham+2.113
 NIC+2.061
+2.058
Neg logit contributions
Ore-2.355
 Isis-2.221
 cherry-2.194
ppo-2.159
lining-2.148
Token his
Token ID465
Feature activation-1.83e-01

Pos logit contributions
+2.431
enegger+2.325
igham+2.215
 NIC+2.180
+2.155
Neg logit contributions
Ore-2.193
 Isis-2.041
 cherry-2.027
lining-1.991
ppo-1.984
Token desk
Token ID6915
Feature activation-2.28e-01

Pos logit contributions
+1.827
enegger+1.750
igham+1.651
 NIC+1.632
+1.609
Neg logit contributions
Ore-1.647
 Isis-1.545
 cherry-1.521
lining-1.505
ppo-1.503
Token chosen
Token ID7147
Feature activation+1.84e-02

Pos logit contributions
+1.370
enegger+1.310
igham+1.259
 NIC+1.235
+1.209
Neg logit contributions
Ore-1.279
 Isis-1.203
 cherry-1.190
ppo-1.175
lining-1.168
Token based
Token ID1912
Feature activation-1.58e-02

Pos logit contributions
Ore+0.181
 cherry+0.172
 Isis+0.172
lining+0.167
ppo+0.166
Neg logit contributions
-0.170
enegger-0.163
igham-0.154
-0.150
 NIC-0.149
Token on
Token ID319
Feature activation-1.27e-01

Pos logit contributions
+0.153
enegger+0.147
igham+0.140
+0.136
 NIC+0.135
Neg logit contributions
Ore-0.148
 cherry-0.141
 Isis-0.141
lining-0.136
ppo-0.135
Token
Token ID564
Feature activation-2.06e-01

Pos logit contributions
+1.245
enegger+1.190
igham+1.141
 NIC+1.121
+1.113
Neg logit contributions
Ore-1.155
 Isis-1.085
 cherry-1.077
ppo-1.060
lining-1.050
Token
Token ID250
Feature activation-1.46e-02

Pos logit contributions
+2.192
enegger+2.067
igham+1.977
+1.939
 NIC+1.910
Neg logit contributions
Ore-1.740
 Isis-1.652
 cherry-1.639
lining-1.585
ppo-1.585
Tokenstat
Token ID14269
Feature activation+1.33e+00

Pos logit contributions
+0.151
enegger+0.145
igham+0.139
+0.135
 NIC+0.134
Neg logit contributions
Ore-0.126
 cherry-0.120
 Isis-0.120
lining-0.115
ppo-0.115
Tokenistical
Token ID19929
Feature activation+4.79e-01

Pos logit contributions
 cherry+7.682
Ore+7.564
lining+7.288
 Isis+7.232
ifier+6.976
Neg logit contributions
enegger-15.412
-14.237
igham-13.679
-13.585
 Eag-13.289
Token data
Token ID1366
Feature activation+3.92e-01

Pos logit contributions
 cherry+3.986
Ore+3.971
 Isis+3.836
lining+3.688
ppo+3.610
Neg logit contributions
-4.968
enegger-4.869
igham-4.638
-4.487
 NIC-4.302
Token,
Token ID11
Feature activation+4.23e-01

Pos logit contributions
Ore+3.266
 cherry+3.177
 Isis+3.107
lining+2.996
ppo+2.911
Neg logit contributions
-4.082
enegger-3.995
igham-3.820
-3.685
 NIC-3.584
Token prior
Token ID3161
Feature activation+1.73e-01

Pos logit contributions
Ore+3.682
 cherry+3.587
 Isis+3.516
lining+3.396
ppo+3.274
Neg logit contributions
-4.277
enegger-4.202
igham-3.936
-3.806
 NIC-3.712
Token complaints
Token ID9687
Feature activation+2.58e-01

Pos logit contributions
Ore+1.446
 cherry+1.374
 Isis+1.367
lining+1.316
ppo+1.293
Neg logit contributions
-1.849
enegger-1.791
igham-1.704
-1.650
 NIC-1.636
Token removed
Token ID4615
Feature activation-2.36e-01

Pos logit contributions
Ore+3.580
 cherry+3.523
 Isis+3.440
lining+3.326
ppo+3.237
Neg logit contributions
-4.545
enegger-4.402
igham-4.253
-4.126
 NIC-3.989
Token and
Token ID290
Feature activation+4.25e-02

Pos logit contributions
+2.138
enegger+2.030
igham+1.931
 NIC+1.892
 Eag+1.866
Neg logit contributions
Ore-2.313
 Isis-2.181
 cherry-2.163
ppo-2.132
lining-2.112
Token turn
Token ID1210
Feature activation+4.11e-01

Pos logit contributions
Ore+0.384
 Isis+0.364
 cherry+0.364
lining+0.352
ppo+0.349
Neg logit contributions
-0.425
enegger-0.409
igham-0.389
-0.379
 NIC-0.377
Token the
Token ID262
Feature activation+8.11e-01

Pos logit contributions
Ore+3.357
 cherry+3.244
 Isis+3.182
lining+3.077
ppo+3.008
Neg logit contributions
-4.391
enegger-4.297
igham-4.103
-3.969
 NIC-3.915
Token V
Token ID569
Feature activation+6.15e-01

Pos logit contributions
 cherry+5.692
Ore+5.463
 Isis+5.338
 Pike+5.006
lining+5.001
Neg logit contributions
-9.255
enegger-9.148
igham-8.893
-8.793
 NIC-8.016
Tokenitus
Token ID17506
Feature activation+1.33e+00

Pos logit contributions
Ore+4.250
 cherry+3.837
 Isis+3.754
ppo+3.638
lining+3.529
Neg logit contributions
-7.261
enegger-7.244
-6.937
 NIC-6.897
 Eag-6.845
Token into
Token ID656
Feature activation+2.69e-01

Pos logit contributions
 cherry+9.735
 Isis+8.990
Ore+8.897
 Pike+8.767
ifier+8.315
Neg logit contributions
-13.464
enegger-12.840
-12.819
igham-12.532
ierrez-11.432
Token a
Token ID257
Feature activation+3.10e-01

Pos logit contributions
Ore+2.165
 cherry+2.079
 Isis+2.055
lining+1.968
ppo+1.935
Neg logit contributions
-2.963
enegger-2.860
igham-2.751
-2.678
 NIC-2.624
Token fixed
Token ID5969
Feature activation+3.14e-02

Pos logit contributions
Ore+2.726
 cherry+2.666
 Isis+2.615
lining+2.502
ppo+2.469
Neg logit contributions
-3.166
enegger-3.055
igham-2.939
-2.856
 NIC-2.750
Token gear
Token ID7733
Feature activation+5.12e-01

Pos logit contributions
Ore+0.276
 cherry+0.262
 Isis+0.262
lining+0.253
ppo+0.250
Neg logit contributions
-0.322
enegger-0.310
igham-0.295
-0.288
 NIC-0.285
Token bike
Token ID7161
Feature activation-7.13e-04

Pos logit contributions
Ore+3.573
 cherry+3.483
 Isis+3.388
lining+3.221
 Pike+3.150
Neg logit contributions
-6.002
enegger-5.841
igham-5.691
-5.576
 Eag-5.340
Token movie
Token ID3807
Feature activation-1.84e-01

Pos logit contributions
Ore+0.152
 cherry+0.143
 Isis+0.143
lining+0.138
ppo+0.137
Neg logit contributions
-0.188
enegger-0.181
igham-0.173
-0.168
 NIC-0.168
Token that
Token ID326
Feature activation+2.91e-01

Pos logit contributions
+1.825
enegger+1.746
igham+1.651
+1.613
 NIC+1.608
Neg logit contributions
Ore-1.695
 cherry-1.592
 Isis-1.589
lining-1.545
ppo-1.537
Token sparked
Token ID16752
Feature activation-4.30e-02

Pos logit contributions
Ore+2.489
 cherry+2.392
 Isis+2.376
lining+2.257
ppo+2.251
Neg logit contributions
-2.990
enegger-2.945
igham-2.791
-2.726
 NIC-2.662
Token all
Token ID477
Feature activation+3.49e-01

Pos logit contributions
+0.437
enegger+0.418
igham+0.402
+0.390
 NIC+0.390
Neg logit contributions
Ore-0.380
 cherry-0.359
 Isis-0.358
lining-0.348
ppo-0.347
Token this
Token ID428
Feature activation+9.35e-03

Pos logit contributions
Ore+2.874
 cherry+2.762
 Isis+2.748
lining+2.599
ppo+2.548
Neg logit contributions
-3.721
enegger-3.651
igham-3.440
-3.335
 Eag-3.306
Token h
Token ID289
Feature activation+1.33e+00

Pos logit contributions
Ore+0.080
 cherry+0.075
 Isis+0.075
lining+0.073
ppo+0.072
Neg logit contributions
-0.098
enegger-0.094
igham-0.090
-0.088
 NIC-0.088
Tokenoo
Token ID2238
Feature activation+2.40e-01

Pos logit contributions
Ore+10.629
lining+10.011
ppo+9.891
 Isis+9.656
 cherry+9.595
Neg logit contributions
-12.038
enegger-11.753
-11.198
 Eag-11.005
igham-10.383
Token-
Token ID12
Feature activation+4.01e-01

Pos logit contributions
Ore+1.899
 cherry+1.795
 Isis+1.782
lining+1.712
ppo+1.704
Neg logit contributions
-2.670
enegger-2.590
igham-2.467
-2.410
 NIC-2.400
Tokenfer
Token ID2232
Feature activation-8.72e-03

Pos logit contributions
Ore+3.023
 cherry+2.892
 Isis+2.827
lining+2.774
ppo+2.691
Neg logit contributions
-4.557
enegger-4.398
igham-4.164
-4.156
 NIC-4.118
Token-
Token ID12
Feature activation-1.21e-01

Pos logit contributions
+0.089
enegger+0.086
igham+0.082
+0.080
 NIC+0.079
Neg logit contributions
Ore-0.077
 cherry-0.073
 Isis-0.073
lining-0.070
ppo-0.070
Tokenah
Token ID993
Feature activation+3.99e-01

Pos logit contributions
+1.216
enegger+1.170
igham+1.119
+1.084
 NIC+1.076
Neg logit contributions
Ore-1.073
 Isis-1.022
 cherry-1.022
lining-0.981
ppo-0.976
Tokenert
Token ID861
Feature activation+2.67e-01

Pos logit contributions
+0.317
enegger+0.305
igham+0.290
+0.279
 NIC+0.278
Neg logit contributions
Ore-0.319
 cherry-0.304
 Isis-0.304
lining-0.293
ppo-0.291
Token of
Token ID286
Feature activation+1.12e-01

Pos logit contributions
Ore+2.248
 cherry+2.134
 Isis+2.115
lining+2.045
ppo+2.042
Neg logit contributions
-2.816
enegger-2.680
igham-2.566
-2.561
 NIC-2.495
Token the
Token ID262
Feature activation+2.13e-01

Pos logit contributions
Ore+0.978
 Isis+0.929
 cherry+0.929
lining+0.890
ppo+0.885
Neg logit contributions
-1.154
enegger-1.110
igham-1.057
-1.038
 NIC-1.018
Token University
Token ID2059
Feature activation+5.39e-01

Pos logit contributions
Ore+2.050
 Isis+1.969
 cherry+1.958
ppo+1.873
lining+1.867
Neg logit contributions
-1.996
enegger-1.913
igham-1.798
-1.792
 NIC-1.708
Token of
Token ID286
Feature activation+4.62e-01

Pos logit contributions
Ore+3.820
 Isis+3.695
 cherry+3.596
 Pike+3.340
lining+3.318
Neg logit contributions
-6.240
enegger-6.203
-5.902
igham-5.853
 NIC-5.501
Token Gu
Token ID1962
Feature activation+1.33e+00

Pos logit contributions
Ore+3.978
 Isis+3.852
 cherry+3.717
ppo+3.573
lining+3.530
Neg logit contributions
-4.738
enegger-4.576
-4.428
igham-4.414
 NIC-4.074
Tokenel
Token ID417
Feature activation+3.35e-02

Pos logit contributions
 Isis+8.327
Ore+8.301
ppo+7.878
lining+7.548
ifier+7.241
Neg logit contributions
-14.656
-14.630
enegger-13.571
-13.396
Interstitial-13.274
Tokenph
Token ID746
Feature activation-3.01e-02

Pos logit contributions
Ore+0.315
 cherry+0.300
 Isis+0.300
lining+0.290
ppo+0.288
Neg logit contributions
-0.324
enegger-0.311
igham-0.296
-0.287
 NIC-0.285
Token in
Token ID287
Feature activation+3.34e-01

Pos logit contributions
+0.296
enegger+0.285
igham+0.271
+0.263
 NIC+0.261
Neg logit contributions
Ore-0.278
 cherry-0.264
 Isis-0.264
lining-0.255
ppo-0.253
Token Ontario
Token ID10553
Feature activation+7.10e-02

Pos logit contributions
Ore+2.622
 Isis+2.516
 cherry+2.497
lining+2.399
ppo+2.355
Neg logit contributions
-3.735
enegger-3.599
igham-3.413
-3.376
 NIC-3.260
Token,
Token ID11
Feature activation-1.87e-01

Pos logit contributions
Ore+0.616
 cherry+0.586
 Isis+0.585
lining+0.562
ppo+0.556
Neg logit contributions
-0.738
enegger-0.712
igham-0.674
-0.660
 NIC-0.653
Token,
Token ID11
Feature activation+2.28e-01

Pos logit contributions
Ore+3.788
 cherry+3.686
 Isis+3.643
lining+3.539
ppo+3.401
Neg logit contributions
-4.610
enegger-4.492
igham-4.252
-4.215
 NIC-4.053
Token including
Token ID1390
Feature activation-1.03e-01

Pos logit contributions
Ore+2.073
 cherry+1.997
 Isis+1.978
lining+1.916
ppo+1.878
Neg logit contributions
-2.253
enegger-2.190
igham-2.077
-2.021
 NIC-1.980
Token last
Token ID938
Feature activation+2.49e-01

Pos logit contributions
+1.044
enegger+0.984
igham+0.950
 NIC+0.931
+0.923
Neg logit contributions
Ore-0.909
 Isis-0.848
 cherry-0.846
ppo-0.822
lining-0.817
Token week
Token ID1285
Feature activation+3.38e-02

Pos logit contributions
Ore+1.933
 cherry+1.852
 Isis+1.848
lining+1.761
ppo+1.735
Neg logit contributions
-2.794
enegger-2.730
igham-2.590
-2.523
 NIC-2.481
Token against
Token ID1028
Feature activation+2.92e-01

Pos logit contributions
Ore+0.304
 cherry+0.288
 Isis+0.288
lining+0.278
ppo+0.276
Neg logit contributions
-0.341
enegger-0.327
igham-0.312
-0.304
 NIC-0.302
Token San
Token ID2986
Feature activation+1.32e+00

Pos logit contributions
Ore+2.429
 cherry+2.359
 Isis+2.350
lining+2.241
ppo+2.197
Neg logit contributions
-3.082
enegger-3.007
igham-2.861
-2.792
 NIC-2.693
Token Diego
Token ID9500
Feature activation+4.36e-01

Pos logit contributions
Ore+7.253
 Isis+6.871
 cherry+6.453
lining+6.367
ppo+6.284
Neg logit contributions
enegger-15.708
-15.622
igham-14.993
-14.358
 NIC-13.734
Token when
Token ID618
Feature activation+3.45e-02

Pos logit contributions
Ore+3.575
 Isis+3.448
 cherry+3.441
lining+3.296
ppo+3.229
Neg logit contributions
-4.581
enegger-4.562
igham-4.274
-4.165
 NIC-4.070
Token he
Token ID339
Feature activation-3.48e-01

Pos logit contributions
Ore+0.309
 cherry+0.293
 Isis+0.292
lining+0.282
ppo+0.280
Neg logit contributions
-0.349
enegger-0.334
igham-0.319
-0.311
 NIC-0.309
Token scored
Token ID7781
Feature activation+1.95e-01

Pos logit contributions
+3.139
enegger+2.919
 NIC+2.766
igham+2.752
 Eag+2.696
Neg logit contributions
Ore-3.443
 Isis-3.158
lining-3.091
 cherry-3.090
ppo-3.084
Token just
Token ID655
Feature activation+2.56e-01

Pos logit contributions
Ore+1.517
 cherry+1.442
 Isis+1.433
lining+1.372
ppo+1.354
Neg logit contributions
-2.200
enegger-2.138
igham-2.042
-2.004
 NIC-1.966
Token
Token ID198
Feature activation+5.95e-02

Pos logit contributions
+2.613
enegger+2.365
 NIC+2.299
igham+2.272
 Eag+2.213
Neg logit contributions
Ore-2.276
 cherry-2.182
 Isis-2.178
lining-2.106
 rall-2.104
Tokenas
Token ID292
Feature activation+6.40e-02

Pos logit contributions
Ore+0.554
 cherry+0.526
 Isis+0.525
lining+0.508
ppo+0.504
Neg logit contributions
-0.580
enegger-0.560
igham-0.532
-0.516
 NIC-0.513
Tokend
Token ID67
Feature activation+4.54e-02

Pos logit contributions
Ore+0.566
 cherry+0.538
 Isis+0.536
lining+0.517
ppo+0.514
Neg logit contributions
-0.652
enegger-0.630
igham-0.599
-0.584
 NIC-0.579
Token
Token ID198
Feature activation-7.35e-03

Pos logit contributions
Ore+0.413
 cherry+0.392
 Isis+0.391
lining+0.378
ppo+0.375
Neg logit contributions
-0.451
enegger-0.434
igham-0.413
-0.403
 NIC-0.399
Token
Token ID198
Feature activation+1.42e-01

Pos logit contributions
+0.080
enegger+0.076
igham+0.073
 NIC+0.071
+0.071
Neg logit contributions
Ore-0.060
 cherry-0.057
 Isis-0.057
lining-0.055
ppo-0.054
TokenGu
Token ID8205
Feature activation+1.31e+00

Pos logit contributions
Ore+1.319
 cherry+1.243
 Isis+1.240
lining+1.210
ppo+1.198
Neg logit contributions
-1.380
enegger-1.346
igham-1.273
-1.235
 NIC-1.233
TokenM
Token ID44
Feature activation+2.11e-01

Pos logit contributions
Ore+11.135
ppo+10.478
ifier+10.405
 Isis+10.350
Bee+9.911
Neg logit contributions
enegger-11.033
-10.646
-9.782
 NIC-9.477
igham-9.300
Tokenih
Token ID4449
Feature activation+4.01e-01

Pos logit contributions
Ore+1.363
 Isis+1.264
 cherry+1.261
lining+1.187
ppo+1.175
Neg logit contributions
-2.657
enegger-2.619
igham-2.482
-2.468
 NIC-2.441
Tokeno
Token ID78
Feature activation+2.83e-02

Pos logit contributions
Ore+3.284
 cherry+3.079
 Isis+3.079
lining+2.966
ppo+2.878
Neg logit contributions
enegger-4.309
-4.245
igham-4.079
-3.925
 NIC-3.868
Token
Token ID198
Feature activation-1.32e-01

Pos logit contributions
Ore+0.243
 cherry+0.230
 Isis+0.230
lining+0.221
ppo+0.220
Neg logit contributions
-0.296
enegger-0.286
igham-0.273
-0.266
 NIC-0.264
Token
Token ID198
Feature activation-7.87e-02

Pos logit contributions
+1.379
enegger+1.284
igham+1.233
 NIC+1.225
+1.196
Neg logit contributions
Ore-1.116
 Isis-1.061
 cherry-1.060
lining-1.027
ppo-1.021
Token such
Token ID884
Feature activation+3.34e-01

Pos logit contributions
Ore+4.112
 cherry+3.934
 Isis+3.919
lining+3.744
ppo+3.676
Neg logit contributions
-5.357
enegger-5.218
igham-5.017
-4.930
 Eag-4.720
Token as
Token ID355
Feature activation+4.02e-01

Pos logit contributions
Ore+2.853
 cherry+2.753
 Isis+2.737
lining+2.629
ppo+2.532
Neg logit contributions
-3.448
enegger-3.376
igham-3.216
-3.192
 Eag-3.037
Token
Token ID198
Feature activation-1.54e-02

Pos logit contributions
Ore+3.737
 cherry+3.632
 Isis+3.595
lining+3.463
ppo+3.392
Neg logit contributions
-3.870
enegger-3.740
igham-3.551
-3.470
 Eag-3.309
Token
Token ID198
Feature activation+1.85e-01

Pos logit contributions
+0.168
enegger+0.160
igham+0.153
 NIC+0.150
+0.149
Neg logit contributions
Ore-0.126
 cherry-0.119
 Isis-0.119
lining-0.114
ppo-0.114
Tokenhang
Token ID33255
Feature activation+4.04e-01

Pos logit contributions
Ore+1.717
 cherry+1.621
 Isis+1.610
lining+1.582
ppo+1.558
Neg logit contributions
-1.804
enegger-1.750
igham-1.661
-1.613
 NIC-1.597
Token gl
Token ID1278
Feature activation+1.30e+00

Pos logit contributions
Ore+3.409
 cherry+3.344
lining+3.291
 Isis+3.253
ppo+3.148
Neg logit contributions
-4.137
enegger-4.018
igham-3.804
-3.769
 Eag-3.677
Tokeniders
Token ID4157
Feature activation+3.73e-01

Pos logit contributions
Ore+6.277
 Isis+6.138
ppo+6.019
ifier+5.830
 cherry+5.650
Neg logit contributions
enegger-15.479
-15.434
-15.246
 Eag-14.344
 NIC-14.154
Token.
Token ID13
Feature activation+2.38e-01

Pos logit contributions
Ore+3.105
 cherry+2.970
 Isis+2.966
lining+2.876
ppo+2.813
Neg logit contributions
-3.927
enegger-3.796
igham-3.642
-3.595
 NIC-3.455
Token However
Token ID2102
Feature activation+2.12e-01

Pos logit contributions
Ore+1.987
 Isis+1.887
 cherry+1.861
lining+1.777
ppo+1.773
Neg logit contributions
-2.546
enegger-2.482
igham-2.385
-2.317
 NIC-2.245
Token,
Token ID11
Feature activation+2.36e-01

Pos logit contributions
Ore+1.824
 cherry+1.747
 Isis+1.743
lining+1.680
ppo+1.662
Neg logit contributions
-2.200
enegger-2.123
igham-2.024
-1.980
 NIC-1.940
Token maybe
Token ID3863
Feature activation+3.42e-01

Pos logit contributions
Ore+2.111
 cherry+2.028
 Isis+2.023
lining+1.947
ppo+1.923
Neg logit contributions
-2.372
enegger-2.293
igham-2.178
-2.139
 NIC-2.075
Token,
Token ID11
Feature activation+1.49e-03

Pos logit contributions
Ore+1.280
 cherry+1.223
 Isis+1.220
lining+1.174
ppo+1.162
Neg logit contributions
-1.463
enegger-1.413
igham-1.346
-1.313
 NIC-1.292
Token or
Token ID393
Feature activation-5.02e-02

Pos logit contributions
Ore+0.014
 cherry+0.013
 Isis+0.013
lining+0.013
ppo+0.013
Neg logit contributions
-0.015
enegger-0.014
igham-0.013
 NIC-0.013
-0.013
Token with
Token ID351
Feature activation-1.80e-01

Pos logit contributions
+0.481
enegger+0.459
igham+0.440
 NIC+0.429
+0.426
Neg logit contributions
Ore-0.474
 Isis-0.448
 cherry-0.448
lining-0.436
ppo-0.434
Token your
Token ID534
Feature activation-1.06e-01

Pos logit contributions
+1.745
enegger+1.657
igham+1.593
 NIC+1.576
 Eag+1.543
Neg logit contributions
Ore-1.671
 Isis-1.567
 cherry-1.564
ppo-1.536
lining-1.530
Token friends
Token ID2460
Feature activation+2.59e-01

Pos logit contributions
+1.079
enegger+1.033
igham+0.988
 NIC+0.976
+0.954
Neg logit contributions
Ore-0.929
 Isis-0.871
 cherry-0.868
lining-0.847
ppo-0.847
Token or
Token ID393
Feature activation+1.29e+00

Pos logit contributions
Ore+2.247
 cherry+2.158
 Isis+2.150
lining+2.069
ppo+2.041
Neg logit contributions
-2.654
enegger-2.566
igham-2.444
-2.385
 Eag-2.340
Token roomm
Token ID26255
Feature activation+2.10e-01

Pos logit contributions
 cherry+8.240
 Isis+8.218
Ore+8.145
lining+7.329
 widow+7.188
Neg logit contributions
enegger-13.931
-13.849
igham-13.076
-12.893
Interstitial-11.802
Tokenates
Token ID689
Feature activation-1.25e-01

Pos logit contributions
Ore+1.497
 cherry+1.390
 Isis+1.385
lining+1.332
ppo+1.323
Neg logit contributions
-2.502
enegger-2.459
igham-2.333
-2.307
 NIC-2.275
Token,
Token ID11
Feature activation-1.95e-01

Pos logit contributions
+1.208
enegger+1.156
igham+1.100
 NIC+1.069
+1.066
Neg logit contributions
Ore-1.169
 Isis-1.103
 cherry-1.102
lining-1.068
ppo-1.064
Token for
Token ID329
Feature activation+6.33e-02

Pos logit contributions
+1.852
enegger+1.765
igham+1.682
 NIC+1.654
 Eag+1.629
Neg logit contributions
Ore-1.832
 cherry-1.726
 Isis-1.722
ppo-1.695
lining-1.687
Token example
Token ID1672
Feature activation-1.41e-01

Pos logit contributions
Ore+0.595
 cherry+0.568
 Isis+0.567
lining+0.548
ppo+0.543
Neg logit contributions
-0.611
enegger-0.587
igham-0.557
-0.542
 NIC-0.536
Token so
Token ID523
Feature activation-6.56e-03

Pos logit contributions
Ore+0.367
 Isis+0.347
 cherry+0.347
lining+0.335
ppo+0.333
Neg logit contributions
-0.407
enegger-0.392
igham-0.373
-0.363
 NIC-0.362
Token on
Token ID319
Feature activation-2.65e-01

Pos logit contributions
+0.067
enegger+0.065
igham+0.062
+0.060
 NIC+0.060
Neg logit contributions
Ore-0.058
 cherry-0.055
 Isis-0.055
lining-0.053
ppo-0.052
Token
Token ID960
Feature activation+6.11e-01

Pos logit contributions
+2.873
enegger+2.768
igham+2.650
+2.581
 NIC+2.564
Neg logit contributions
Ore-2.149
 Isis-2.027
 cherry-2.002
ppo-1.922
lining-1.920
Tokenyou
Token ID5832
Feature activation+6.15e-02

Pos logit contributions
Ore+5.216
 cherry+4.727
lining+4.710
 Isis+4.644
ppo+4.612
Neg logit contributions
-6.201
enegger-6.141
igham-5.932
-5.712
 NIC-5.678
Token need
Token ID761
Feature activation+7.07e-01

Pos logit contributions
Ore+0.589
 Isis+0.557
 cherry+0.557
lining+0.541
ppo+0.536
Neg logit contributions
-0.583
enegger-0.561
igham-0.531
 NIC-0.514
-0.513
Token Pixel
Token ID11349
Feature activation+1.29e+00

Pos logit contributions
Ore+5.444
 cherry+5.234
 Isis+5.189
lining+5.043
ppo+4.951
Neg logit contributions
-7.507
enegger-7.390
igham-7.141
-6.856
 Eag-6.702
Tokenpipe
Token ID34360
Feature activation+1.53e-01

Pos logit contributions
Ore+6.360
ppo+5.985
 Isis+5.849
 Pike+5.770
lining+5.720
Neg logit contributions
-15.451
enegger-15.442
igham-15.047
-14.792
 Eag-14.600
Token.
Token ID13
Feature activation+4.16e-01

Pos logit contributions
Ore+1.355
 cherry+1.296
 Isis+1.287
lining+1.244
ppo+1.229
Neg logit contributions
-1.567
enegger-1.506
igham-1.440
-1.407
 NIC-1.379
Token Shoot
Token ID17011
Feature activation-5.78e-02

Pos logit contributions
Ore+3.234
 Isis+3.104
 cherry+3.042
ppo+2.900
lining+2.867
Neg logit contributions
-4.627
enegger-4.505
igham-4.409
-4.260
 NIC-4.058
Token your
Token ID534
Feature activation-8.87e-02

Pos logit contributions
+0.573
enegger+0.554
igham+0.523
+0.510
 NIC+0.509
Neg logit contributions
Ore-0.526
 Isis-0.497
 cherry-0.495
lining-0.480
ppo-0.477
Token photo
Token ID4590
Feature activation-4.67e-01

Pos logit contributions
+0.839
enegger+0.810
igham+0.758
 NIC+0.747
+0.733
Neg logit contributions
Ore-0.849
 Isis-0.799
 cherry-0.790
lining-0.775
ppo-0.772
Token When
Token ID1649
Feature activation+1.70e-02

Pos logit contributions
Ore+0.528
 Isis+0.501
 cherry+0.501
lining+0.481
ppo+0.477
Neg logit contributions
-0.639
enegger-0.616
igham-0.589
-0.574
 NIC-0.566
Token Trump
Token ID1301
Feature activation-1.25e-01

Pos logit contributions
Ore+0.158
 cherry+0.150
 Isis+0.149
lining+0.145
ppo+0.144
Neg logit contributions
-0.166
enegger-0.160
igham-0.152
-0.148
 NIC-0.147
Token named
Token ID3706
Feature activation+2.13e-01

Pos logit contributions
+1.205
enegger+1.159
igham+1.098
 NIC+1.061
+1.061
Neg logit contributions
Ore-1.173
 Isis-1.110
 cherry-1.105
lining-1.073
ppo-1.069
Token his
Token ID465
Feature activation+9.15e-02

Pos logit contributions
Ore+1.952
 cherry+1.882
 Isis+1.880
lining+1.803
ppo+1.774
Neg logit contributions
-2.081
enegger-2.002
igham-1.914
-1.876
 NIC-1.814
Token vice
Token ID7927
Feature activation+2.26e-01

Pos logit contributions
Ore+0.854
 cherry+0.814
 Isis+0.812
lining+0.785
ppo+0.779
Neg logit contributions
-0.889
enegger-0.854
igham-0.813
-0.791
 NIC-0.782
Token presidential
Token ID4787
Feature activation+1.28e+00

Pos logit contributions
Ore+1.751
 cherry+1.681
 Isis+1.657
lining+1.590
ppo+1.580
Neg logit contributions
-2.503
enegger-2.463
igham-2.370
-2.300
 NIC-2.257
Token pick
Token ID2298
Feature activation+2.22e-01

Pos logit contributions
 cherry+7.381
 Isis+7.132
Ore+6.906
lining+6.750
 pup+6.604
Neg logit contributions
-14.456
enegger-14.021
-13.955
igham-13.880
-12.890
Token,
Token ID11
Feature activation+3.44e-01

Pos logit contributions
Ore+1.953
 Isis+1.876
 cherry+1.876
lining+1.800
ppo+1.763
Neg logit contributions
-2.254
enegger-2.187
igham-2.066
-2.025
 NIC-1.972
Token Gov
Token ID10964
Feature activation+4.38e-01

Pos logit contributions
Ore+3.155
 cherry+3.046
 Isis+3.042
lining+2.888
ppo+2.808
Neg logit contributions
-3.319
enegger-3.242
igham-3.044
-3.007
 NIC-2.874
Token.
Token ID13
Feature activation+4.01e-01

Pos logit contributions
Ore+3.591
 Isis+3.318
 cherry+3.293
lining+3.276
ppo+3.153
Neg logit contributions
-4.644
enegger-4.516
-4.324
igham-4.305
 NIC-4.188
Token Mike
Token ID4995
Feature activation+4.14e-01

Pos logit contributions
Ore+2.979
 Isis+2.885
 cherry+2.833
 Pike+2.673
lining+2.667
Neg logit contributions
enegger-4.524
-4.510
igham-4.297
-4.267
 NIC-3.969
Token pave
Token ID23000
Feature activation-1.47e-01

Pos logit contributions
+0.519
enegger+0.499
igham+0.473
 NIC+0.460
+0.459
Neg logit contributions
Ore-0.487
 Isis-0.460
 cherry-0.457
lining-0.444
ppo-0.442
Token the
Token ID262
Feature activation+2.82e-02

Pos logit contributions
+1.472
enegger+1.410
igham+1.337
+1.319
 NIC+1.298
Neg logit contributions
Ore-1.324
 cherry-1.252
 Isis-1.244
ppo-1.202
lining-1.198
Token way
Token ID835
Feature activation+3.70e-02

Pos logit contributions
Ore+0.200
 cherry+0.187
 Isis+0.187
lining+0.178
ppo+0.177
Neg logit contributions
-0.337
enegger-0.326
igham-0.313
-0.306
 NIC-0.305
Token for
Token ID329
Feature activation-1.15e-01

Pos logit contributions
Ore+0.327
 cherry+0.311
 Isis+0.310
lining+0.299
ppo+0.297
Neg logit contributions
-0.378
enegger-0.364
igham-0.347
-0.338
 NIC-0.335
Token re
Token ID302
Feature activation+8.78e-01

Pos logit contributions
+1.125
enegger+1.074
igham+1.029
+1.002
 NIC+0.998
Neg logit contributions
Ore-1.065
 cherry-1.000
 Isis-0.999
ppo-0.971
lining-0.969
Token-
Token ID12
Feature activation+1.28e+00

Pos logit contributions
Ore+7.278
lining+7.139
 cherry+7.001
 Isis+6.834
ifier+6.625
Neg logit contributions
enegger-8.321
-8.169
-7.761
igham-7.745
 NIC-7.633
Tokenestablish
Token ID40037
Feature activation+3.94e-01

Pos logit contributions
Ore+10.487
lining+10.295
 cherry+10.077
pec+9.533
ifier+9.337
Neg logit contributions
enegger-11.110
-10.782
-10.632
 NIC-10.487
igham-10.251
Tokening
Token ID278
Feature activation+1.38e-01

Pos logit contributions
Ore+2.911
 cherry+2.772
 Isis+2.752
lining+2.726
ppo+2.543
Neg logit contributions
-4.492
enegger-4.399
igham-4.188
-4.139
 NIC-4.076
Token a
Token ID257
Feature activation-3.46e-01

Pos logit contributions
Ore+1.242
 cherry+1.187
 Isis+1.183
lining+1.144
ppo+1.125
Neg logit contributions
-1.388
enegger-1.344
igham-1.277
-1.241
 NIC-1.231
Token balance
Token ID5236
Feature activation-1.52e-02

Pos logit contributions
+3.271
enegger+3.126
igham+2.981
+2.940
 NIC+2.905
Neg logit contributions
Ore-3.268
 Isis-3.054
 cherry-3.007
ppo-2.975
lining-2.935
Token between
Token ID1022
Feature activation-6.33e-02

Pos logit contributions
+0.149
enegger+0.143
igham+0.136
+0.133
 NIC+0.132
Neg logit contributions
Ore-0.141
 cherry-0.134
 Isis-0.134
lining-0.129
ppo-0.128
Token his
Token ID465
Feature activation+5.83e-01

Pos logit contributions
Ore+1.958
 Isis+1.874
 cherry+1.863
lining+1.793
ppo+1.786
Neg logit contributions
-2.154
enegger-2.094
igham-1.981
-1.928
 NIC-1.896
Token prison
Token ID3770
Feature activation+4.92e-01

Pos logit contributions
Ore+4.870
 cherry+4.780
 Isis+4.746
ppo+4.444
lining+4.441
Neg logit contributions
-5.920
enegger-5.817
-5.548
igham-5.521
 NIC-5.176
Token,
Token ID11
Feature activation+8.68e-02

Pos logit contributions
Ore+3.795
 Isis+3.668
 cherry+3.623
lining+3.433
ppo+3.416
Neg logit contributions
-5.490
enegger-5.328
-5.046
igham-5.014
 NIC-4.784
Token Worm
Token ID28505
Feature activation+2.22e-01

Pos logit contributions
Ore+0.802
 Isis+0.764
 cherry+0.764
lining+0.737
ppo+0.730
Neg logit contributions
-0.851
enegger-0.820
igham-0.778
-0.759
 NIC-0.749
Tokent
Token ID83
Feature activation+1.65e-01

Pos logit contributions
Ore+2.112
 Isis+2.011
 cherry+2.004
lining+1.954
ppo+1.943
Neg logit contributions
-2.101
enegger-2.018
igham-1.923
-1.900
 NIC-1.855
Tokenong
Token ID506
Feature activation+1.28e+00

Pos logit contributions
Ore+1.674
 Isis+1.593
 cherry+1.589
lining+1.550
ppo+1.539
Neg logit contributions
-1.479
enegger-1.412
igham-1.332
-1.313
 NIC-1.292
Tokenue
Token ID518
Feature activation+3.49e-01

Pos logit contributions
Ore+3.868
 cherry+2.999
ifier+2.837
ppo+2.802
 Isis+2.770
Neg logit contributions
enegger-18.785
-18.403
-18.101
-17.934
 NIC-17.668
Token drops
Token ID10532
Feature activation-1.17e-01

Pos logit contributions
Ore+3.076
 Isis+2.993
 cherry+2.982
lining+2.834
ppo+2.825
Neg logit contributions
-3.514
enegger-3.375
igham-3.232
-3.193
 NIC-3.093
Token a
Token ID257
Feature activation+1.74e-02

Pos logit contributions
+1.143
enegger+1.087
igham+1.046
 NIC+1.012
 Eag+1.011
Neg logit contributions
Ore-1.069
 cherry-1.011
 Isis-1.008
lining-0.976
ppo-0.975
Token sphere
Token ID16558
Feature activation-5.94e-02

Pos logit contributions
Ore+0.162
 Isis+0.154
 cherry+0.154
lining+0.149
ppo+0.148
Neg logit contributions
-0.169
enegger-0.162
igham-0.155
-0.150
 NIC-0.149
Token to
Token ID284
Feature activation-2.55e-01

Pos logit contributions
+0.604
enegger+0.578
igham+0.553
+0.537
 NIC+0.536
Neg logit contributions
Ore-0.527
 cherry-0.500
 Isis-0.498
lining-0.480
ppo-0.480
Token with
Token ID351
Feature activation-4.25e-01

Pos logit contributions
Ore+2.774
 cherry+2.671
 Isis+2.610
lining+2.592
ppo+2.552
Neg logit contributions
-3.265
enegger-3.179
igham-3.021
-2.946
 Eag-2.932
Token Blake
Token ID13307
Feature activation+3.59e-01

Pos logit contributions
+4.238
enegger+3.901
igham+3.816
 NIC+3.775
+3.638
Neg logit contributions
Ore-3.772
 cherry-3.494
 Isis-3.490
ppo-3.434
lining-3.398
Token Wheeler
Token ID27512
Feature activation-1.53e-01

Pos logit contributions
Ore+2.696
 cherry+2.581
 Isis+2.574
lining+2.478
ppo+2.439
Neg logit contributions
-4.090
enegger-3.952
igham-3.810
-3.709
 NIC-3.631
Token and
Token ID290
Feature activation+5.26e-02

Pos logit contributions
+1.472
enegger+1.409
igham+1.341
+1.302
 NIC+1.295
Neg logit contributions
Ore-1.440
 Isis-1.366
 cherry-1.362
ppo-1.314
lining-1.313
Token Mark
Token ID2940
Feature activation+4.21e-01

Pos logit contributions
Ore+0.515
 cherry+0.490
 Isis+0.489
lining+0.474
ppo+0.471
Neg logit contributions
-0.488
enegger-0.467
igham-0.443
-0.431
 NIC-0.428
Token Sche
Token ID10011
Feature activation+1.28e+00

Pos logit contributions
Ore+3.532
 Isis+3.405
 cherry+3.312
ppo+3.247
lining+3.216
Neg logit contributions
-4.485
enegger-4.289
igham-4.000
-3.984
 NIC-3.818
Tokenife
Token ID901
Feature activation-1.38e-01

Pos logit contributions
Ore+5.108
ppo+5.050
ifier+4.672
 cherry+4.530
 Isis+4.236
Neg logit contributions
enegger-17.307
-16.767
-16.693
 Eag-16.050
 NIC-15.849
Tokenle
Token ID293
Feature activation-2.08e-02

Pos logit contributions
+1.402
enegger+1.320
igham+1.273
+1.218
 NIC+1.209
Neg logit contributions
Ore-1.228
 Isis-1.178
 cherry-1.162
lining-1.114
ppo-1.106
Token has
Token ID468
Feature activation+1.30e-01

Pos logit contributions
+0.205
enegger+0.197
igham+0.188
+0.182
 NIC+0.181
Neg logit contributions
Ore-0.192
 cherry-0.182
 Isis-0.182
lining-0.176
ppo-0.175
Token been
Token ID587
Feature activation+3.14e-02

Pos logit contributions
Ore+1.203
 cherry+1.149
 Isis+1.144
lining+1.105
ppo+1.094
Neg logit contributions
-1.270
enegger-1.224
igham-1.161
-1.134
 NIC-1.120
Token strong
Token ID1913
Feature activation-8.17e-02

Pos logit contributions
Ore+0.283
 cherry+0.268
 Isis+0.268
lining+0.259
ppo+0.257
Neg logit contributions
-0.316
enegger-0.303
igham-0.289
-0.281
 NIC-0.280
Token opponents
Token ID7691
Feature activation-1.16e-01

Pos logit contributions
+1.467
enegger+1.382
igham+1.324
 NIC+1.313
 Eag+1.293
Neg logit contributions
Ore-1.450
 cherry-1.346
 Isis-1.344
ppo-1.320
lining-1.319
Token physically
Token ID10170
Feature activation-1.18e-01

Pos logit contributions
+1.104
enegger+1.053
igham+1.008
 NIC+0.984
+0.970
Neg logit contributions
Ore-1.109
 Isis-1.039
 cherry-1.034
ppo-1.011
lining-1.011
Token and
Token ID290
Feature activation-7.80e-02

Pos logit contributions
+1.132
enegger+1.082
igham+1.030
 NIC+0.998
+0.996
Neg logit contributions
Ore-1.122
 Isis-1.059
 cherry-1.055
ppo-1.024
lining-1.022
Token gets
Token ID3011
Feature activation+1.63e-01

Pos logit contributions
+0.679
enegger+0.650
igham+0.617
 NIC+0.596
+0.593
Neg logit contributions
Ore-0.803
 Isis-0.762
 cherry-0.759
lining-0.740
ppo-0.740
Token under
Token ID739
Feature activation-4.25e-01

Pos logit contributions
Ore+1.485
 cherry+1.424
 Isis+1.417
lining+1.362
ppo+1.351
Neg logit contributions
-1.625
enegger-1.569
igham-1.489
-1.451
 NIC-1.427
Token their
Token ID511
Feature activation-1.41e+00

Pos logit contributions
+3.853
enegger+3.582
igham+3.449
 NIC+3.446
 Eag+3.425
Neg logit contributions
Ore-4.116
 Isis-3.827
 cherry-3.813
ppo-3.706
lining-3.674
Token skin
Token ID4168
Feature activation-3.38e-01

Pos logit contributions
+7.529
 NIC+7.474
enegger+7.355
 MAC+6.677
 Eag+6.552
Neg logit contributions
Ore-15.436
 Isis-14.184
ppo-14.112
lining-13.756
inctions-13.750
Token between
Token ID1022
Feature activation-2.01e-01

Pos logit contributions
+3.014
enegger+2.889
igham+2.728
 NIC+2.680
 Eag+2.603
Neg logit contributions
Ore-3.340
 Isis-3.123
ppo-3.090
 cherry-3.073
lining-2.991
Token plays
Token ID5341
Feature activation+2.07e-01

Pos logit contributions
+2.003
enegger+1.892
igham+1.825
 NIC+1.796
 Eag+1.760
Neg logit contributions
Ore-1.808
 Isis-1.686
 cherry-1.679
ppo-1.649
lining-1.648
Token.
Token ID13
Feature activation+9.31e-02

Pos logit contributions
Ore+1.784
 cherry+1.721
 Isis+1.703
lining+1.646
ppo+1.616
Neg logit contributions
-2.136
enegger-2.062
igham-1.964
-1.932
 NIC-1.894
Token And
Token ID843
Feature activation-1.12e-02

Pos logit contributions
Ore+0.762
 Isis+0.722
 cherry+0.721
lining+0.690
ppo+0.685
Neg logit contributions
-1.011
enegger-0.978
igham-0.936
-0.914
 NIC-0.900
Token it
Token ID340
Feature activation+3.12e-01

Pos logit contributions
Ore+0.766
 cherry+0.730
 Isis+0.728
lining+0.703
ppo+0.697
Neg logit contributions
-0.836
enegger-0.805
igham-0.766
-0.746
 NIC-0.738
Token is
Token ID318
Feature activation+2.43e-01

Pos logit contributions
Ore+2.625
 cherry+2.560
 Isis+2.512
lining+2.424
ppo+2.400
Neg logit contributions
-3.203
enegger-3.114
igham-2.990
-2.917
 Eag-2.884
Token impossible
Token ID5340
Feature activation+3.14e-01

Pos logit contributions
Ore+2.206
 cherry+2.123
 Isis+2.107
lining+2.024
ppo+2.004
Neg logit contributions
-2.404
enegger-2.324
igham-2.221
-2.168
 NIC-2.107
Token to
Token ID284
Feature activation-1.02e-01

Pos logit contributions
Ore+2.668
 cherry+2.571
 Isis+2.530
lining+2.448
ppo+2.418
Neg logit contributions
-3.241
enegger-3.119
igham-3.011
 Eag-2.904
-2.897
Token dis
Token ID595
Feature activation-3.47e-01

Pos logit contributions
+0.974
enegger+0.928
igham+0.892
 NIC+0.877
+0.857
Neg logit contributions
Ore-0.957
 Isis-0.901
 cherry-0.882
lining-0.873
ppo-0.867
Tokenamb
Token ID4131
Feature activation-1.40e+00

Pos logit contributions
+3.375
enegger+3.213
igham+3.089
 NIC+2.967
 Eag+2.930
Neg logit contributions
Ore-3.148
 Isis-3.022
 cherry-2.943
ppo-2.881
lining-2.814
Tokenig
Token ID328
Feature activation-8.30e-02

Pos logit contributions
igham+6.643
+6.212
icated+5.091
estic+5.033
blow+4.971
Neg logit contributions
Ore-16.220
 Isis-16.145
 rall-15.961
ppo-15.933
 cherry-15.735
Tokenuate
Token ID4985
Feature activation+1.91e-01

Pos logit contributions
+0.970
enegger+0.936
igham+0.899
+0.880
 NIC+0.875
Neg logit contributions
Ore-0.608
 Isis-0.573
 cherry-0.572
lining-0.548
ppo-0.543
Token any
Token ID597
Feature activation+1.65e-02

Pos logit contributions
Ore+1.708
 cherry+1.639
 Isis+1.624
lining+1.575
ppo+1.549
Neg logit contributions
-1.927
enegger-1.862
igham-1.768
-1.719
 NIC-1.682
Token single
Token ID2060
Feature activation-3.09e-01

Pos logit contributions
Ore+0.148
 Isis+0.141
 cherry+0.140
lining+0.135
ppo+0.135
Neg logit contributions
-0.167
enegger-0.160
igham-0.153
-0.149
 NIC-0.148
Token measurement
Token ID15558
Feature activation-3.60e-01

Pos logit contributions
+2.972
enegger+2.806
 NIC+2.727
igham+2.694
+2.632
Neg logit contributions
Ore-2.854
 Isis-2.687
ppo-2.636
 cherry-2.625
lining-2.557
Token their
Token ID511
Feature activation-4.69e-01

Pos logit contributions
+0.950
enegger+0.911
igham+0.870
 NIC+0.847
+0.845
Neg logit contributions
Ore-0.825
 cherry-0.776
 Isis-0.773
lining-0.751
ppo-0.750
Token mind
Token ID2000
Feature activation+3.48e-02

Pos logit contributions
+4.336
enegger+4.122
 NIC+3.944
igham+3.847
 Eag+3.801
Neg logit contributions
Ore-4.422
 Isis-4.047
ppo-4.013
 cherry-3.985
lining-3.985
Token.
Token ID13
Feature activation+4.85e-02

Pos logit contributions
Ore+0.314
 cherry+0.298
 Isis+0.297
lining+0.287
ppo+0.285
Neg logit contributions
-0.350
enegger-0.336
igham-0.320
-0.312
 NIC-0.309
Token Get
Token ID3497
Feature activation-1.76e-01

Pos logit contributions
Ore+0.402
 cherry+0.380
 Isis+0.379
lining+0.365
ppo+0.362
Neg logit contributions
-0.522
enegger-0.503
igham-0.481
-0.469
 NIC-0.466
Token under
Token ID739
Feature activation-2.97e-01

Pos logit contributions
+1.690
enegger+1.595
igham+1.533
 NIC+1.501
+1.483
Neg logit contributions
Ore-1.662
 cherry-1.550
 Isis-1.543
lining-1.512
ppo-1.502
Token their
Token ID511
Feature activation-1.40e+00

Pos logit contributions
+2.878
enegger+2.725
igham+2.625
 NIC+2.562
+2.531
Neg logit contributions
Ore-2.754
 cherry-2.573
 Isis-2.563
ppo-2.483
lining-2.461
Token skin
Token ID4168
Feature activation-1.91e-01

Pos logit contributions
+9.873
 NIC+9.448
enegger+9.319
 Eag+8.819
 MAC+8.502
Neg logit contributions
Ore-13.174
ppo-11.907
 Isis-11.866
lining-11.600
inctions-11.510
Token.
Token ID13
Feature activation+5.83e-02

Pos logit contributions
+1.804
enegger+1.726
igham+1.638
 NIC+1.596
+1.572
Neg logit contributions
Ore-1.809
 Isis-1.701
 cherry-1.694
ppo-1.653
lining-1.631
Token I
Token ID314
Feature activation-2.32e-01

Pos logit contributions
Ore+0.496
 cherry+0.470
 Isis+0.469
lining+0.452
ppo+0.448
Neg logit contributions
-0.615
enegger-0.593
igham-0.567
-0.552
 NIC-0.547
Token talk
Token ID1561
Feature activation-1.11e-01

Pos logit contributions
+2.159
enegger+2.064
igham+1.988
 NIC+1.937
 Eag+1.864
Neg logit contributions
Ore-2.250
 Isis-2.069
 cherry-2.029
lining-2.022
ppo-1.989
Token my
Token ID616
Feature activation+1.85e-03

Pos logit contributions
+1.072
enegger+1.024
igham+0.974
 NIC+0.952
+0.940
Neg logit contributions
Ore-1.036
 cherry-0.975
 Isis-0.973
ppo-0.953
lining-0.946
Tokenag
Token ID363
Feature activation-1.65e-01

Pos logit contributions
+0.295
enegger+0.283
igham+0.269
+0.261
 NIC+0.259
Neg logit contributions
Ore-0.293
 cherry-0.279
 Isis-0.279
lining-0.270
ppo-0.267
Tokenawa
Token ID6909
Feature activation-4.10e-01

Pos logit contributions
+1.603
enegger+1.526
igham+1.469
 NIC+1.417
+1.417
Neg logit contributions
Ore-1.543
 cherry-1.463
 Isis-1.462
lining-1.412
ppo-1.394
Token,
Token ID11
Feature activation-7.43e-01

Pos logit contributions
+3.911
enegger+3.651
igham+3.564
 NIC+3.497
+3.444
Neg logit contributions
Ore-3.752
 Isis-3.510
lining-3.488
 cherry-3.470
ppo-3.413
Token ip
Token ID20966
Feature activation-5.57e-01

Pos logit contributions
+7.131
 NIC+6.587
enegger+6.503
igham+6.434
 Eag+6.325
Neg logit contributions
Ore-6.235
lining-5.816
ppo-5.737
 Isis-5.730
 cherry-5.709
Tokenag
Token ID363
Feature activation-3.39e-01

Pos logit contributions
+5.187
igham+4.830
enegger+4.811
 NIC+4.488
+4.479
Neg logit contributions
Ore-5.077
 Isis-4.920
 cherry-4.870
lining-4.680
Bee-4.633
Tokenpat
Token ID8071
Feature activation-1.35e+00

Pos logit contributions
+3.139
enegger+3.003
igham+2.889
+2.754
 NIC+2.745
Neg logit contributions
Ore-3.251
 Isis-3.090
 cherry-3.082
lining-2.990
ppo-2.935
Tokenul
Token ID377
Feature activation-5.27e-01

Pos logit contributions
+12.264
igham+11.653
 NIC+11.314
enegger+11.239
 Eag+10.785
Neg logit contributions
Ore-9.760
 Isis-9.055
 cherry-8.763
lining-8.721
Bee-8.715
Tokenoy
Token ID726
Feature activation-4.07e-01

Pos logit contributions
+5.141
enegger+4.818
igham+4.742
+4.507
 NIC+4.506
Neg logit contributions
Ore-4.656
 Isis-4.368
 cherry-4.335
lining-4.261
ppo-4.169
Token lang
Token ID42392
Feature activation-1.74e-01

Pos logit contributions
+3.942
enegger+3.724
igham+3.590
 NIC+3.511
+3.460
Neg logit contributions
Ore-3.690
 cherry-3.463
 Isis-3.458
lining-3.397
ppo-3.332
Token n
Token ID299
Feature activation-4.22e-01

Pos logit contributions
+1.722
enegger+1.639
igham+1.572
 NIC+1.533
+1.528
Neg logit contributions
Ore-1.584
 cherry-1.485
 Isis-1.485
lining-1.454
ppo-1.439
Tokenatin
Token ID10680
Feature activation-4.54e-01

Pos logit contributions
+3.614
enegger+3.463
igham+3.393
+3.184
 NIC+3.159
Neg logit contributions
Ore-4.208
 cherry-4.063
 Isis-4.022
lining-3.932
ppo-3.785
Token comic
Token ID9048
Feature activation+5.83e-02

Pos logit contributions
+3.253
enegger+3.095
 NIC+3.004
igham+2.917
 Eag+2.901
Neg logit contributions
Ore-3.400
 Isis-3.250
 cherry-3.175
ppo-3.151
lining-3.106
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
Ore+0.520
 cherry+0.495
 Isis+0.493
lining+0.477
ppo+0.472
Neg logit contributions
-0.592
enegger-0.568
igham-0.543
-0.530
 NIC-0.523
Token Ex
Token ID1475
Feature activation-1.87e-01

Pos logit contributions
+1.301
enegger+1.241
igham+1.178
 NIC+1.160
+1.156
Neg logit contributions
Ore-1.125
 cherry-1.073
 Isis-1.072
lining-1.043
ppo-1.031
Tokenceptions
Token ID11755
Feature activation-8.22e-01

Pos logit contributions
+1.883
enegger+1.782
igham+1.712
+1.673
 NIC+1.667
Neg logit contributions
Ore-1.659
 Isis-1.571
 cherry-1.569
ppo-1.512
lining-1.506
Token to
Token ID284
Feature activation-4.59e-01

Pos logit contributions
+6.729
enegger+6.399
igham+6.333
 NIC+6.153
 Eag+5.965
Neg logit contributions
Ore-7.733
 Isis-7.336
lining-7.209
ppo-7.128
 cherry-7.028
Token this
Token ID428
Feature activation-1.32e+00

Pos logit contributions
+4.113
enegger+3.826
igham+3.777
 NIC+3.716
 Eag+3.645
Neg logit contributions
Ore-4.422
 Isis-4.154
ppo-4.111
 cherry-4.058
lining-3.986
Token include
Token ID2291
Feature activation-4.22e-01

Pos logit contributions
+8.335
 NIC+8.007
 Credit+7.438
igham+7.431
 Eag+7.407
Neg logit contributions
Ore-12.808
ppo-12.473
 Isis-11.616
lining-11.522
Bee-11.473
Token "
Token ID366
Feature activation-1.69e-01

Pos logit contributions
+4.100
enegger+3.859
 NIC+3.758
 Eag+3.721
igham+3.699
Neg logit contributions
Ore-3.701
 Isis-3.510
ppo-3.451
 cherry-3.424
lining-3.387
TokenThe
Token ID464
Feature activation-8.74e-02

Pos logit contributions
+1.718
enegger+1.630
igham+1.556
+1.517
 NIC+1.508
Neg logit contributions
Ore-1.483
 Isis-1.439
 cherry-1.431
ppo-1.368
lining-1.366
Token C
Token ID327
Feature activation-4.51e-01

Pos logit contributions
+0.870
enegger+0.835
igham+0.795
 NIC+0.772
+0.770
Neg logit contributions
Ore-0.790
 cherry-0.749
 Isis-0.749
lining-0.726
ppo-0.719
TokenMC
Token ID9655
Feature activation-3.55e-01

Pos logit contributions
+4.417
enegger+4.213
igham+4.052
 Eag+3.902
 NIC+3.866
Neg logit contributions
Ore-3.915
 cherry-3.820
 Isis-3.797
lining-3.652
ppo-3.494
Token our
Token ID674
Feature activation-4.10e-01

Pos logit contributions
+2.929
enegger+2.760
 NIC+2.708
igham+2.689
 Eag+2.584
Neg logit contributions
Ore-3.091
 cherry-2.871
 Isis-2.861
ppo-2.858
lining-2.806
Token senior
Token ID4664
Feature activation+8.39e-02

Pos logit contributions
+3.776
enegger+3.571
 NIC+3.505
igham+3.451
 Eag+3.320
Neg logit contributions
Ore-3.930
 Isis-3.622
ppo-3.600
 cherry-3.590
lining-3.538
Token civil
Token ID3026
Feature activation-7.72e-01

Pos logit contributions
Ore+0.807
 cherry+0.775
 Isis+0.774
lining+0.745
ppo+0.736
Neg logit contributions
-0.790
enegger-0.763
igham-0.717
-0.702
 NIC-0.686
Token servants
Token ID17523
Feature activation-2.63e-01

Pos logit contributions
+3.907
enegger+3.401
 NIC+3.375
igham+3.338
 Eag+2.881
Neg logit contributions
Ore-10.107
ppo-9.715
 cherry-9.693
lining-9.596
 Isis-9.447
Token,
Token ID11
Feature activation-9.46e-01

Pos logit contributions
+2.483
enegger+2.395
igham+2.289
 NIC+2.221
+2.198
Neg logit contributions
Ore-2.507
 Isis-2.340
 cherry-2.327
ppo-2.287
lining-2.258
Token being
Token ID852
Feature activation-1.27e+00

Pos logit contributions
+7.418
 NIC+7.039
igham+6.765
enegger+6.753
 Ghana+6.538
Neg logit contributions
Ore-9.306
ppo-8.487
 Isis-8.205
lining-8.005
Cola-7.959
Token fully
Token ID3938
Feature activation-1.25e+00

Pos logit contributions
+7.926
 NIC+7.708
igham+7.070
 Ghana+7.040
 Eag+6.737
Neg logit contributions
Ore-13.168
ppo-12.401
Cola-12.080
lining-11.850
 Isis-11.716
Token bilingual
Token ID48116
Feature activation-1.88e-01

Pos logit contributions
+7.732
 NIC+7.248
 Ghana+6.819
 Eag+6.490
igham+6.467
Neg logit contributions
Ore-13.511
ppo-12.670
Cola-12.231
 cherry-12.009
 Isis-11.980
Token."
Token ID526
Feature activation-7.83e-02

Pos logit contributions
+1.803
enegger+1.727
igham+1.651
 NIC+1.611
+1.579
Neg logit contributions
Ore-1.768
 cherry-1.655
 Isis-1.654
ppo-1.617
lining-1.601
Token
Token ID198
Feature activation-2.81e-01

Pos logit contributions
+0.855
enegger+0.826
igham+0.789
+0.771
 NIC+0.766
Neg logit contributions
Ore-0.637
 cherry-0.601
 Isis-0.598
lining-0.576
ppo-0.571
Token
Token ID198
Feature activation-1.48e-01

Pos logit contributions
+2.755
enegger+2.534
 NIC+2.447
igham+2.405
 Eag+2.358
Neg logit contributions
Ore-2.494
 cherry-2.388
 Isis-2.365
 rall-2.342
lining-2.337
Token to
Token ID284
Feature activation+2.56e-01

Pos logit contributions
Ore+0.503
 cherry+0.478
 Isis+0.477
lining+0.461
ppo+0.458
Neg logit contributions
-0.546
enegger-0.525
igham-0.500
-0.487
 NIC-0.482
Token be
Token ID307
Feature activation-3.64e-01

Pos logit contributions
Ore+2.142
 cherry+2.071
 Isis+2.063
lining+1.964
ppo+1.950
Neg logit contributions
-2.726
enegger-2.647
igham-2.512
-2.447
 NIC-2.402
Token known
Token ID1900
Feature activation-1.27e-01

Pos logit contributions
+3.388
enegger+3.223
igham+3.114
 NIC+3.066
+2.999
Neg logit contributions
Ore-3.386
 cherry-3.145
 Isis-3.137
lining-3.106
ppo-3.075
Token as
Token ID355
Feature activation-1.55e-01

Pos logit contributions
+1.187
enegger+1.138
igham+1.081
+1.057
 NIC+1.050
Neg logit contributions
Ore-1.224
 cherry-1.159
 Isis-1.152
ppo-1.125
lining-1.121
Token the
Token ID262
Feature activation-3.24e-01

Pos logit contributions
+1.522
enegger+1.459
igham+1.386
 NIC+1.370
+1.360
Neg logit contributions
Ore-1.414
 cherry-1.337
 Isis-1.318
lining-1.294
ppo-1.293
Token Feder
Token ID35089
Feature activation-1.26e+00

Pos logit contributions
+3.010
enegger+2.881
 NIC+2.745
igham+2.733
 Eag+2.693
Neg logit contributions
Ore-3.067
 cherry-2.866
 Isis-2.835
lining-2.820
ppo-2.812
Tokenated
Token ID515
Feature activation-7.29e-01

Pos logit contributions
+7.855
igham+7.608
enegger+7.000
 NIC+6.820
 Eag+6.617
Neg logit contributions
Ore-13.443
 cherry-12.840
 Isis-12.410
lining-12.140
ppo-12.135
Token Islands
Token ID12010
Feature activation-1.36e-01

Pos logit contributions
+7.227
enegger+6.779
 NIC+6.755
 Eag+6.660
igham+6.578
Neg logit contributions
Ore-5.980
 cherry-5.610
ppo-5.493
lining-5.462
 Isis-5.350
Token of
Token ID286
Feature activation-1.89e-01

Pos logit contributions
+1.375
enegger+1.318
igham+1.259
+1.226
 NIC+1.225
Neg logit contributions
Ore-1.209
 cherry-1.145
 Isis-1.138
lining-1.104
ppo-1.103
Token The
Token ID383
Feature activation+9.97e-02

Pos logit contributions
+1.824
enegger+1.760
igham+1.684
 NIC+1.641
+1.626
Neg logit contributions
Ore-1.756
 cherry-1.670
 Isis-1.644
lining-1.624
ppo-1.612
Token Former
Token ID14466
Feature activation-1.74e-01

Pos logit contributions
Ore+0.983
 Isis+0.941
 cherry+0.939
lining+0.907
ppo+0.904
Neg logit contributions
-0.915
enegger-0.878
igham-0.829
-0.812
 NIC-0.793
Token").
Token ID11074
Feature activation-5.23e-01

Pos logit contributions
Ore+0.062
 cherry+0.058
 Isis+0.058
lining+0.055
ppo+0.055
Neg logit contributions
-0.098
enegger-0.095
igham-0.091
-0.089
 NIC-0.089
Token Male
Token ID12674
Feature activation-1.05e+00

Pos logit contributions
+4.993
 NIC+4.539
enegger+4.525
 Eag+4.426
igham+4.309
Neg logit contributions
Ore-4.741
 cherry-4.477
lining-4.475
ppo-4.338
 Isis-4.273
Token-
Token ID12
Feature activation-6.83e-01

Pos logit contributions
+8.270
 NIC+7.533
enegger+7.390
+7.243
igham+7.053
Neg logit contributions
Ore-9.993
ppo-9.108
 Isis-9.087
 cherry-9.015
lining-8.997
Tokento
Token ID1462
Feature activation-6.75e-01

Pos logit contributions
+5.401
enegger+4.902
+4.661
igham+4.659
 NIC+4.530
Neg logit contributions
Ore-7.135
 cherry-6.928
 Isis-6.921
ppo-6.597
 Pike-6.565
Token-
Token ID12
Feature activation-6.22e-01

Pos logit contributions
+5.485
enegger+4.933
igham+4.711
 NIC+4.641
+4.569
Neg logit contributions
Ore-6.874
 cherry-6.525
 Isis-6.449
lining-6.331
ppo-6.258
Tokenfemale
Token ID24724
Feature activation-1.26e+00

Pos logit contributions
+6.173
enegger+5.608
+5.496
igham+5.363
 NIC+5.317
Neg logit contributions
Ore-5.323
 cherry-5.165
 Isis-5.027
lining-4.852
ppo-4.849
Token (
Token ID357
Feature activation-9.17e-01

Pos logit contributions
+8.879
 NIC+8.525
GBT+7.802
 Eag+7.579
 Ghana+7.561
Neg logit contributions
Ore-12.296
Cola-11.274
ppo-11.172
Bee-11.084
lining-11.048
TokenM
Token ID44
Feature activation-4.80e-01

Pos logit contributions
+7.465
enegger+6.550
 NIC+6.439
GBT+6.374
igham+6.344
Neg logit contributions
 cherry-8.699
Ore-8.573
 Isis-8.458
lining-8.164
ppo-7.983
TokenTF
Token ID10234
Feature activation-5.36e-01

Pos logit contributions
+3.601
enegger+3.236
igham+3.119
+3.079
 NIC+3.066
Neg logit contributions
Ore-5.244
 cherry-5.235
 Isis-5.103
lining-5.021
ppo-4.920
Token)
Token ID8
Feature activation-1.15e+00

Pos logit contributions
+5.170
enegger+4.917
igham+4.591
 NIC+4.588
+4.560
Neg logit contributions
Ore-4.843
 Isis-4.604
 cherry-4.541
lining-4.473
ppo-4.466
Token transgender
Token ID10637
Feature activation-4.40e-01

Pos logit contributions
+7.800
 NIC+6.994
enegger+6.638
+6.493
 Eag+6.400
Neg logit contributions
Ore-12.138
Cola-11.209
Bee-11.112
ppo-11.081
lining-11.045
Token
Token ID198
Feature activation-1.50e-01

Pos logit contributions
+1.062
enegger+1.021
igham+0.970
 NIC+0.956
+0.954
Neg logit contributions
Ore-0.842
 cherry-0.797
 Isis-0.785
lining-0.770
ppo-0.756
Token
Token ID198
Feature activation-6.78e-02

Pos logit contributions
+1.559
enegger+1.441
 NIC+1.386
igham+1.381
+1.348
Neg logit contributions
Ore-1.281
 cherry-1.227
 Isis-1.219
lining-1.190
ppo-1.178
TokenS
Token ID50
Feature activation-5.58e-01

Pos logit contributions
+0.653
enegger+0.613
igham+0.585
+0.578
 NIC+0.567
Neg logit contributions
Ore-0.634
 cherry-0.617
 Isis-0.613
lining-0.589
ppo-0.583
Tokenpor
Token ID1819
Feature activation-2.79e-01

Pos logit contributions
+4.654
enegger+4.486
igham+4.295
+4.097
 NIC+3.977
Neg logit contributions
 Isis-5.496
 cherry-5.488
Ore-5.482
lining-5.081
 Pike-5.075
Tokenadic
Token ID23876
Feature activation-2.03e-01

Pos logit contributions
+2.352
enegger+2.259
igham+2.159
 NIC+2.084
+2.070
Neg logit contributions
Ore-2.906
 cherry-2.768
 Isis-2.750
lining-2.663
ppo-2.621
Token gunfire
Token ID29276
Feature activation-1.26e+00

Pos logit contributions
+2.181
enegger+2.100
igham+2.015
 NIC+1.981
+1.976
Neg logit contributions
Ore-1.661
 cherry-1.520
 Isis-1.515
ppo-1.473
lining-1.472
Token rocked
Token ID36872
Feature activation+2.01e-01

Pos logit contributions
+8.414
enegger+7.527
 NIC+7.423
 Eag+7.371
igham+7.209
Neg logit contributions
Ore-12.745
Cola-11.614
 Isis-11.062
ppo-11.060
Bee-11.060
Token the
Token ID262
Feature activation-1.72e-01

Pos logit contributions
Ore+1.696
 Isis+1.633
 cherry+1.632
lining+1.564
ppo+1.548
Neg logit contributions
-2.117
enegger-2.030
igham-1.941
-1.900
 NIC-1.860
Token new
Token ID649
Feature activation-3.36e-01

Pos logit contributions
+1.633
enegger+1.571
igham+1.485
 NIC+1.475
 Eag+1.445
Neg logit contributions
Ore-1.638
 cherry-1.505
 Isis-1.501
lining-1.480
ppo-1.471
Token nation
Token ID3277
Feature activation+1.21e-01

Pos logit contributions
+3.162
enegger+3.028
igham+2.850
 NIC+2.835
 Eag+2.759
Neg logit contributions
Ore-3.216
 cherry-2.951
 Isis-2.922
lining-2.895
ppo-2.892
Token
Token ID447
Feature activation-3.82e-02

Pos logit contributions
Ore+1.077
 cherry+1.033
 Isis+1.031
lining+1.001
ppo+0.985
Neg logit contributions
-1.228
enegger-1.189
igham-1.125
-1.103
 NIC-1.085
Token v
Token ID410
Feature activation-2.69e-01

Pos logit contributions
+3.013
enegger+2.837
igham+2.695
 NIC+2.664
 Eag+2.632
Neg logit contributions
Ore-2.962
 Isis-2.839
 cherry-2.754
lining-2.711
ppo-2.709
Token.
Token ID13
Feature activation+4.83e-02

Pos logit contributions
+2.588
enegger+2.477
igham+2.345
+2.294
 NIC+2.261
Neg logit contributions
Ore-2.503
 Isis-2.413
 cherry-2.380
ppo-2.300
lining-2.300
Tokennormal
Token ID11265
Feature activation+3.41e-01

Pos logit contributions
Ore+0.437
 cherry+0.415
 Isis+0.413
lining+0.401
ppo+0.397
Neg logit contributions
-0.483
enegger-0.465
igham-0.443
-0.432
 NIC-0.428
Token *
Token ID1635
Feature activation-4.47e-01

Pos logit contributions
Ore+3.038
 cherry+2.826
 Isis+2.770
lining+2.756
ppo+2.697
Neg logit contributions
-3.404
enegger-3.340
igham-3.177
 NIC-3.078
 Eag-3.059
Token 1
Token ID352
Feature activation-6.52e-01

Pos logit contributions
+4.130
enegger+3.884
igham+3.647
 NIC+3.605
+3.589
Neg logit contributions
Ore-4.215
 Isis-4.070
 cherry-3.947
ppo-3.863
lining-3.829
Token;
Token ID26
Feature activation-1.25e+00

Pos logit contributions
+5.858
enegger+5.503
 NIC+5.218
+5.116
igham+5.114
Neg logit contributions
Ore-5.964
 Isis-5.882
 cherry-5.671
ppo-5.584
lining-5.475
Token }
Token ID1782
Feature activation-3.69e-01

Pos logit contributions
+8.813
enegger+7.633
 NIC+7.604
 Eag+7.517
igham+7.493
Neg logit contributions
Ore-12.097
 Isis-11.958
ppo-11.385
Bee-11.308
lining-11.075
Token 1
Token ID352
Feature activation-4.72e-01

Pos logit contributions
+3.672
enegger+3.423
igham+3.293
 NIC+3.271
+3.248
Neg logit contributions
Ore-3.265
 Isis-3.120
 cherry-3.003
ppo-2.974
lining-2.956
Token 2
Token ID362
Feature activation-8.12e-01

Pos logit contributions
+5.038
enegger+4.709
 NIC+4.556
+4.534
igham+4.522
Neg logit contributions
Ore-3.852
 Isis-3.644
 cherry-3.499
ppo-3.443
lining-3.411
Token 3
Token ID513
Feature activation-5.14e-01

Pos logit contributions
+6.995
enegger+6.678
igham+6.358
 NIC+6.267
+6.225
Neg logit contributions
Ore-7.703
 Isis-7.289
ppo-7.083
 cherry-7.048
lining-6.882
Token void
Token ID7951
Feature activation-1.36e-01

Pos logit contributions
+4.911
enegger+4.578
+4.444
igham+4.408
 NIC+4.369
Neg logit contributions
Ore-4.667
 Isis-4.425
ppo-4.340
 cherry-4.238
lining-4.234
Token
Token ID447
Feature activation-2.34e-02

Pos logit contributions
+3.525
enegger+3.238
+3.074
igham+3.068
 NIC+3.046
Neg logit contributions
Ore-2.849
 cherry-2.756
 Isis-2.740
lining-2.675
ppo-2.646
Token
Token ID247
Feature activation-1.54e-02

Pos logit contributions
+0.312
enegger+0.300
igham+0.292
+0.285
 NIC+0.283
Neg logit contributions
Ore-0.134
 cherry-0.123
 Isis-0.123
lining-0.117
ppo-0.115
Tokent
Token ID83
Feature activation-6.98e-01

Pos logit contributions
+0.143
enegger+0.137
igham+0.130
+0.126
 NIC+0.125
Neg logit contributions
Ore-0.151
 cherry-0.144
 Isis-0.144
lining-0.140
ppo-0.138
Token know
Token ID760
Feature activation-3.24e-01

Pos logit contributions
+5.746
enegger+5.543
 NIC+5.274
igham+4.997
 Ghana+4.909
Neg logit contributions
Ore-7.072
 Isis-6.358
lining-6.327
ppo-6.316
Bee-6.249
Token how
Token ID703
Feature activation-7.81e-01

Pos logit contributions
+3.021
enegger+2.867
 NIC+2.691
igham+2.685
+2.656
Neg logit contributions
Ore-3.063
 cherry-2.848
ppo-2.842
lining-2.827
 Isis-2.820
Token to
Token ID284
Feature activation-1.25e+00

Pos logit contributions
+6.350
+5.832
enegger+5.825
 NIC+5.465
igham+5.293
Neg logit contributions
Ore-7.963
ppo-7.420
lining-7.353
 cherry-7.338
 Isis-7.183
Token behave
Token ID17438
Feature activation-6.45e-01

Pos logit contributions
+9.629
 NIC+8.795
enegger+8.648
 Ghana+8.409
+8.143
Neg logit contributions
Ore-11.828
Cola-10.439
lining-10.237
 Isis-10.206
ppo-10.205
Token in
Token ID287
Feature activation-4.72e-01

Pos logit contributions
+5.486
enegger+5.350
+4.859
igham+4.832
 NIC+4.747
Neg logit contributions
Ore-6.425
 cherry-5.948
 Isis-5.910
lining-5.896
ppo-5.873
Token the
Token ID262
Feature activation-3.32e-01

Pos logit contributions
+4.383
enegger+4.234
 NIC+3.996
+3.977
igham+3.972
Neg logit contributions
Ore-4.398
 cherry-4.005
ppo-3.985
 Isis-3.950
lining-3.900
Token 21
Token ID2310
Feature activation+2.15e-01

Pos logit contributions
+3.106
enegger+2.983
 NIC+2.815
igham+2.786
+2.765
Neg logit contributions
Ore-3.176
 cherry-2.921
 Isis-2.901
lining-2.879
ppo-2.871
Tokenst
Token ID301
Feature activation-1.03e-01

Pos logit contributions
Ore+1.581
 cherry+1.499
 Isis+1.496
lining+1.439
ppo+1.412
Neg logit contributions
-2.472
enegger-2.426
igham-2.334
-2.253
 Eag-2.224
Token Ferdinand
Token ID44312
Feature activation-2.36e-01

Pos logit contributions
+1.436
enegger+1.388
igham+1.315
 NIC+1.279
 Eag+1.271
Neg logit contributions
Ore-1.464
 cherry-1.391
 Isis-1.370
lining-1.337
ppo-1.330
Token's
Token ID338
Feature activation+4.93e-02

Pos logit contributions
+2.176
enegger+2.046
igham+1.987
 NIC+1.940
 Eag+1.906
Neg logit contributions
Ore-2.293
 Isis-2.143
 cherry-2.133
lining-2.097
ppo-2.096
Token deep
Token ID2769
Feature activation-9.04e-02

Pos logit contributions
Ore+0.445
 Isis+0.418
 cherry+0.417
lining+0.405
ppo+0.404
Neg logit contributions
-0.495
enegger-0.474
igham-0.452
 NIC-0.440
-0.439
Token cross
Token ID3272
Feature activation-2.80e-01

Pos logit contributions
+0.924
enegger+0.879
igham+0.831
 NIC+0.824
+0.812
Neg logit contributions
Ore-0.806
 Isis-0.751
 cherry-0.745
ppo-0.728
lining-0.725
Token,
Token ID11
Feature activation-1.80e-01

Pos logit contributions
+2.654
enegger+2.494
igham+2.431
 NIC+2.356
 Eag+2.343
Neg logit contributions
Ore-2.652
 cherry-2.475
 Isis-2.474
ppo-2.423
lining-2.392
Token Lor
Token ID26068
Feature activation-1.25e+00

Pos logit contributions
+1.713
enegger+1.631
igham+1.574
 NIC+1.541
 Eag+1.525
Neg logit contributions
Ore-1.698
 cherry-1.587
 Isis-1.580
ppo-1.551
lining-1.544
Tokenik
Token ID1134
Feature activation-1.41e-01

Pos logit contributions
igham+9.210
+8.922
 Ghana+8.238
enegger+8.181
 NIC+8.165
Neg logit contributions
Ore-11.483
 pid-11.103
 Isis-10.901
 cherry-10.772
Cola-10.360
Token Can
Token ID1680
Feature activation-1.42e-01

Pos logit contributions
+1.324
enegger+1.254
igham+1.212
 NIC+1.189
 Eag+1.162
Neg logit contributions
Ore-1.337
 cherry-1.275
 Isis-1.263
ppo-1.235
lining-1.229
Tokena
Token ID64
Feature activation-3.62e-01

Pos logit contributions
+1.237
enegger+1.182
igham+1.118
 NIC+1.090
 Eag+1.059
Neg logit contributions
Ore-1.445
 Isis-1.370
 cherry-1.360
lining-1.321
ppo-1.301
Token sent
Token ID1908
Feature activation-3.94e-01

Pos logit contributions
+3.372
enegger+3.191
igham+3.057
 NIC+2.958
 Eag+2.903
Neg logit contributions
Ore-3.476
 Isis-3.235
ppo-3.167
 cherry-3.155
lining-3.133
Token another
Token ID1194
Feature activation-1.64e-01

Pos logit contributions
+3.666
enegger+3.436
 NIC+3.354
igham+3.344
 Eag+3.334
Neg logit contributions
Ore-3.714
 cherry-3.422
 Isis-3.381
ppo-3.377
lining-3.335
Token senior
Token ID4664
Feature activation+8.39e-02

Pos logit contributions
+3.776
enegger+3.571
 NIC+3.505
igham+3.451
 Eag+3.320
Neg logit contributions
Ore-3.930
 Isis-3.622
ppo-3.600
 cherry-3.590
lining-3.538
Token civil
Token ID3026
Feature activation-7.72e-01

Pos logit contributions
Ore+0.807
 cherry+0.775
 Isis+0.774
lining+0.745
ppo+0.736
Neg logit contributions
-0.790
enegger-0.763
igham-0.717
-0.702
 NIC-0.686
Token servants
Token ID17523
Feature activation-2.63e-01

Pos logit contributions
+3.907
enegger+3.401
 NIC+3.375
igham+3.338
 Eag+2.881
Neg logit contributions
Ore-10.107
ppo-9.715
 cherry-9.693
lining-9.596
 Isis-9.447
Token,
Token ID11
Feature activation-9.46e-01

Pos logit contributions
+2.483
enegger+2.395
igham+2.289
 NIC+2.221
+2.198
Neg logit contributions
Ore-2.507
 Isis-2.340
 cherry-2.327
ppo-2.287
lining-2.258
Token being
Token ID852
Feature activation-1.27e+00

Pos logit contributions
+7.418
 NIC+7.039
igham+6.765
enegger+6.753
 Ghana+6.538
Neg logit contributions
Ore-9.306
ppo-8.487
 Isis-8.205
lining-8.005
Cola-7.959
Token fully
Token ID3938
Feature activation-1.25e+00

Pos logit contributions
+7.926
 NIC+7.708
igham+7.070
 Ghana+7.040
 Eag+6.737
Neg logit contributions
Ore-13.168
ppo-12.401
Cola-12.080
lining-11.850
 Isis-11.716
Token bilingual
Token ID48116
Feature activation-1.88e-01

Pos logit contributions
+7.732
 NIC+7.248
 Ghana+6.819
 Eag+6.490
igham+6.467
Neg logit contributions
Ore-13.511
ppo-12.670
Cola-12.231
 cherry-12.009
 Isis-11.980
Token."
Token ID526
Feature activation-7.83e-02

Pos logit contributions
+1.803
enegger+1.727
igham+1.651
 NIC+1.611
+1.579
Neg logit contributions
Ore-1.768
 cherry-1.655
 Isis-1.654
ppo-1.617
lining-1.601
Token
Token ID198
Feature activation-2.81e-01

Pos logit contributions
+0.855
enegger+0.826
igham+0.789
+0.771
 NIC+0.766
Neg logit contributions
Ore-0.637
 cherry-0.601
 Isis-0.598
lining-0.576
ppo-0.571
Token
Token ID198
Feature activation-1.48e-01

Pos logit contributions
+2.755
enegger+2.534
 NIC+2.447
igham+2.405
 Eag+2.358
Neg logit contributions
Ore-2.494
 cherry-2.388
 Isis-2.365
 rall-2.342
lining-2.337
TokenIn
Token ID818
Feature activation-6.90e-02

Pos logit contributions
+1.422
enegger+1.331
igham+1.280
+1.256
 NIC+1.236
Neg logit contributions
Ore-1.375
 cherry-1.358
 Isis-1.338
lining-1.289
ppo-1.280
Token make
Token ID787
Feature activation-2.20e-01

Pos logit contributions
+0.440
enegger+0.423
igham+0.401
 NIC+0.392
+0.390
Neg logit contributions
Ore-0.412
 Isis-0.389
 cherry-0.385
lining-0.375
ppo-0.373
Token them
Token ID606
Feature activation-1.47e-01

Pos logit contributions
+2.161
enegger+2.057
igham+1.951
 NIC+1.910
+1.900
Neg logit contributions
Ore-2.026
 Isis-1.906
 cherry-1.872
lining-1.854
ppo-1.848
Token useful
Token ID4465
Feature activation-2.92e-01

Pos logit contributions
+1.448
enegger+1.391
igham+1.311
 NIC+1.285
+1.276
Neg logit contributions
Ore-1.365
 Isis-1.281
 cherry-1.266
lining-1.241
ppo-1.238
Token.
Token ID13
Feature activation-8.88e-02

Pos logit contributions
+2.766
enegger+2.656
igham+2.483
 NIC+2.464
+2.433
Neg logit contributions
Ore-2.752
 Isis-2.617
 cherry-2.573
lining-2.542
ppo-2.530
Token A
Token ID317
Feature activation-3.09e-01

Pos logit contributions
+0.935
enegger+0.898
igham+0.848
 NIC+0.838
+0.836
Neg logit contributions
Ore-0.755
 cherry-0.712
 Isis-0.709
lining-0.694
ppo-0.685
Token 5
Token ID642
Feature activation-1.23e+00

Pos logit contributions
+2.933
enegger+2.784
igham+2.651
 NIC+2.616
+2.595
Neg logit contributions
Ore-2.930
 Isis-2.793
 cherry-2.699
lining-2.676
ppo-2.669
Token-
Token ID12
Feature activation-9.61e-01

Pos logit contributions
+9.160
 NIC+8.735
enegger+8.600
+8.089
igham+8.028
Neg logit contributions
Ore-11.414
 Isis-10.822
ppo-10.502
lining-10.437
 cherry-10.320
Tokenmic
Token ID9383
Feature activation-3.75e-01

Pos logit contributions
+6.922
enegger+6.534
 NIC+6.193
igham+6.095
+5.995
Neg logit contributions
Ore-9.854
 Isis-9.664
 cherry-9.521
ppo-9.078
 Pike-8.953
Tokenron
Token ID1313
Feature activation-4.10e-02

Pos logit contributions
+1.811
enegger+1.671
igham+1.488
 NIC+1.453
+1.356
Neg logit contributions
Ore-5.147
 Isis-5.047
 cherry-4.966
lining-4.913
ppo-4.874
Token pin
Token ID6757
Feature activation+1.94e-01

Pos logit contributions
+0.424
enegger+0.408
igham+0.389
+0.379
 NIC+0.378
Neg logit contributions
Ore-0.357
 Isis-0.337
 cherry-0.336
lining-0.325
ppo-0.323
Tokenhole
Token ID13207
Feature activation-2.81e-01

Pos logit contributions
Ore+1.406
 cherry+1.329
 Isis+1.300
lining+1.264
ppo+1.239
Neg logit contributions
-2.266
enegger-2.230
igham-2.128
-2.097
 NIC-2.060
TokenYou
Token ID1639
Feature activation+2.71e-02

Pos logit contributions
Ore+2.154
 cherry+2.048
 Isis+2.038
lining+1.979
ppo+1.973
Neg logit contributions
-1.975
enegger-1.920
igham-1.812
-1.745
 NIC-1.739
Token can
Token ID460
Feature activation+3.30e-02

Pos logit contributions
Ore+0.249
 cherry+0.239
 Isis+0.238
lining+0.229
ppo+0.228
Neg logit contributions
-0.266
enegger-0.257
igham-0.244
-0.238
 NIC-0.234
Token buy
Token ID2822
Feature activation+8.89e-02

Pos logit contributions
Ore+0.300
 Isis+0.283
 cherry+0.281
lining+0.278
ppo+0.272
Neg logit contributions
-0.331
enegger-0.314
igham-0.294
 NIC-0.289
-0.289
Token An
Token ID1052
Feature activation-2.26e-01

Pos logit contributions
Ore+0.625
 cherry+0.581
 Isis+0.571
lining+0.562
ppo+0.550
Neg logit contributions
-1.064
enegger-1.018
igham-0.986
-0.969
 NIC-0.968
Token Enemy
Token ID21785
Feature activation-5.73e-01

Pos logit contributions
+2.095
enegger+1.973
 Eag+1.828
igham+1.817
+1.811
Neg logit contributions
Ore-2.176
 cherry-2.111
 Isis-2.083
ppo-2.064
lining-2.044
Token of
Token ID286
Feature activation-1.22e+00

Pos logit contributions
+4.481
 NIC+3.911
+3.755
 Ghana+3.718
igham+3.691
Neg logit contributions
Ore-6.054
ppo-5.728
 cherry-5.688
IFE-5.452
 rall-5.442
Token the
Token ID262
Feature activation-7.66e-01

Pos logit contributions
+7.843
 Ghana+7.122
 Domin+6.848
 NIC+6.666
+6.441
Neg logit contributions
Ore-13.535
 rall-13.192
ppo-12.608
Bee-12.555
liner-12.522
Token State
Token ID1812
Feature activation-4.57e-01

Pos logit contributions
+7.777
 NIC+7.080
 Eag+6.997
enegger+6.974
 Ghana+6.957
Neg logit contributions
Ore-6.636
lining-6.190
ppo-6.025
 Isis-5.894
rir-5.599
Token:
Token ID25
Feature activation-5.78e-01

Pos logit contributions
+4.381
enegger+3.926
 NIC+3.868
+3.866
 Eag+3.751
Neg logit contributions
Ore-4.310
 Isis-3.973
 cherry-3.912
lining-3.906
ppo-3.878
Token The
Token ID383
Feature activation-7.31e-01

Pos logit contributions
+5.232
 NIC+4.917
igham+4.802
 Eag+4.779
 Ghana+4.775
Neg logit contributions
Ore-5.339
 cherry-4.881
Bee-4.830
ppo-4.776
lining-4.709
Token Life
Token ID5155
Feature activation+2.43e-01

Pos logit contributions
+4.899
+4.329
 Forgotten+4.315
 NIC+4.200
igham+4.155
Neg logit contributions
Ore-8.548
ppo-7.843
 pid-7.826
 cherry-7.808
lining-7.778
Token1
Token ID16
Feature activation-5.76e-01

Pos logit contributions
+7.995
enegger+7.572
igham+7.489
 Eag+6.789
 NIC+6.751
Neg logit contributions
Ore-7.864
 Isis-7.806
 cherry-7.536
lining-7.346
 Pike-7.057
Tokendb
Token ID9945
Feature activation-1.05e+00

Pos logit contributions
+5.025
enegger+4.752
igham+4.673
 NIC+4.324
 Eag+4.312
Neg logit contributions
Ore-5.493
 Isis-5.394
 cherry-5.237
lining-5.114
ppo-4.962
Token439
Token ID47106
Feature activation-7.63e-01

Pos logit contributions
+8.960
enegger+8.327
igham+8.293
 Eag+7.499
 NIC+7.444
Neg logit contributions
 Isis-8.955
Ore-8.936
 cherry-8.562
lining-8.352
 rall-8.116
Token70
Token ID2154
Feature activation-7.26e-01

Pos logit contributions
+6.821
enegger+6.449
igham+6.353
 Eag+5.876
 NIC+5.840
Neg logit contributions
Ore-6.746
 Isis-6.674
 cherry-6.456
lining-6.286
 Pike-6.056
Tokende
Token ID2934
Feature activation-7.00e-01

Pos logit contributions
+6.599
enegger+6.163
igham+6.109
 Eag+5.686
 NIC+5.658
Neg logit contributions
Ore-6.445
 Isis-6.310
 cherry-6.092
lining-5.978
 Pike-5.750
Token5
Token ID20
Feature activation-1.20e+00

Pos logit contributions
+6.566
enegger+6.233
igham+6.106
 NIC+5.661
 Eag+5.641
Neg logit contributions
Ore-6.054
 Isis-5.913
 cherry-5.747
lining-5.695
ppo-5.421
Tokene
Token ID68
Feature activation-8.72e-01

Pos logit contributions
+9.397
igham+8.870
enegger+8.826
 Eag+8.022
 NIC+7.799
Neg logit contributions
 Isis-10.489
Ore-10.350
lining-10.000
 cherry-9.969
 rall-9.460
Token4
Token ID19
Feature activation-8.41e-01

Pos logit contributions
+7.881
enegger+7.490
igham+7.393
+6.761
 NIC+6.752
Neg logit contributions
Ore-7.397
 Isis-7.320
lining-7.129
 cherry-7.090
ppo-6.685
Tokencb
Token ID21101
Feature activation-1.14e+00

Pos logit contributions
+7.164
enegger+6.739
igham+6.668
 Eag+6.162
 NIC+6.097
Neg logit contributions
Ore-7.602
 Isis-7.578
 cherry-7.325
lining-7.198
ppo-6.877
Token0
Token ID15
Feature activation-5.49e-01

Pos logit contributions
+9.573
enegger+8.986
igham+8.963
 Eag+8.114
 NIC+8.043
Neg logit contributions
Ore-9.541
 Isis-9.506
 cherry-9.087
lining-9.015
 rall-8.655
Tokenc
Token ID66
Feature activation-6.01e-01

Pos logit contributions
+4.954
enegger+4.688
igham+4.571
 Eag+4.329
 NIC+4.317
Neg logit contributions
Ore-5.136
 Isis-4.983
 cherry-4.879
lining-4.796
ppo-4.658
Token may
Token ID743
Feature activation-4.44e-02

Pos logit contributions
Ore+0.858
 cherry+0.810
 Isis+0.809
lining+0.783
ppo+0.777
Neg logit contributions
-0.968
enegger-0.931
igham-0.886
-0.862
 NIC-0.857
Token legisl
Token ID3560
Feature activation-4.79e-01

Pos logit contributions
+0.426
enegger+0.408
igham+0.387
 NIC+0.380
+0.372
Neg logit contributions
Ore-0.421
 Isis-0.395
 cherry-0.388
lining-0.383
ppo-0.380
Tokenate
Token ID378
Feature activation-2.64e-01

Pos logit contributions
+4.168
igham+3.805
enegger+3.767
 NIC+3.610
 Eag+3.542
Neg logit contributions
Ore-4.771
lining-4.523
 Isis-4.484
 cherry-4.423
ppo-4.363
Token only
Token ID691
Feature activation-2.31e-01

Pos logit contributions
+2.332
enegger+2.219
 NIC+2.109
igham+2.097
 Eag+2.062
Neg logit contributions
Ore-2.643
 Isis-2.451
ppo-2.438
 cherry-2.434
lining-2.404
Token within
Token ID1626
Feature activation-8.53e-01

Pos logit contributions
+2.071
enegger+1.970
igham+1.877
 NIC+1.844
 Eag+1.815
Neg logit contributions
Ore-2.286
 cherry-2.142
 Isis-2.141
ppo-2.112
lining-2.103
Token the
Token ID262
Feature activation-1.19e+00

Pos logit contributions
+6.677
enegger+6.353
 NIC+6.246
 Eag+6.037
igham+5.936
Neg logit contributions
Ore-8.514
ppo-7.766
 cherry-7.718
 Isis-7.686
lining-7.459
Token subject
Token ID2426
Feature activation-6.70e-02

Pos logit contributions
+9.397
 NIC+9.147
enegger+8.963
 Eag+8.838
 Ghana+8.309
Neg logit contributions
Ore-10.713
ppo-9.786
lining-9.509
 cherry-9.489
 Isis-9.375
Token areas
Token ID3006
Feature activation+8.55e-02

Pos logit contributions
+0.671
enegger+0.644
igham+0.616
 NIC+0.601
+0.599
Neg logit contributions
Ore-0.603
 cherry-0.568
 Isis-0.566
ppo-0.550
lining-0.548
Token enumer
Token ID27056
Feature activation-2.55e-01

Pos logit contributions
Ore+0.759
 cherry+0.721
 Isis+0.719
lining+0.694
ppo+0.688
Neg logit contributions
-0.870
enegger-0.838
igham-0.799
-0.778
 NIC-0.771
Tokenated
Token ID515
Feature activation-1.42e-01

Pos logit contributions
+1.994
enegger+1.882
igham+1.774
 NIC+1.710
+1.659
Neg logit contributions
Ore-2.821
 cherry-2.700
 Isis-2.698
lining-2.601
ppo-2.590
Token under
Token ID739
Feature activation+1.46e-01

Pos logit contributions
+1.293
enegger+1.235
igham+1.169
 NIC+1.131
+1.128
Neg logit contributions
Ore-1.407
 cherry-1.330
 Isis-1.329
ppo-1.294
lining-1.292
Token fact
Token ID1109
Feature activation-1.21e-01

Pos logit contributions
+0.023
enegger+0.022
igham+0.021
+0.020
 NIC+0.020
Neg logit contributions
Ore-0.022
 cherry-0.020
 Isis-0.020
lining-0.020
ppo-0.020
Token that
Token ID326
Feature activation-1.22e-01

Pos logit contributions
+1.135
enegger+1.088
igham+1.027
 NIC+0.995
+0.995
Neg logit contributions
Ore-1.172
 cherry-1.109
 Isis-1.101
ppo-1.066
lining-1.066
Token roughly
Token ID7323
Feature activation-1.89e-02

Pos logit contributions
+1.182
enegger+1.130
igham+1.071
 Eag+1.057
 NIC+1.056
Neg logit contributions
Ore-1.138
 cherry-1.061
 Isis-1.056
lining-1.036
ppo-1.032
Token two
Token ID734
Feature activation+2.04e-01

Pos logit contributions
+0.191
enegger+0.183
igham+0.175
 NIC+0.171
 Eag+0.170
Neg logit contributions
Ore-0.169
 cherry-0.157
 Isis-0.157
lining-0.153
ppo-0.153
Token out
Token ID503
Feature activation-6.57e-01

Pos logit contributions
Ore+1.771
 cherry+1.704
 Isis+1.695
lining+1.639
ppo+1.601
Neg logit contributions
-2.103
enegger-2.040
igham-1.940
-1.897
 NIC-1.856
Token of
Token ID286
Feature activation-1.19e+00

Pos logit contributions
+5.593
enegger+5.027
igham+4.854
 NIC+4.783
 Eag+4.779
Neg logit contributions
Ore-6.466
 cherry-6.019
ppo-6.006
 Isis-5.986
 rall-5.966
Token every
Token ID790
Feature activation-1.04e+00

Pos logit contributions
+7.159
 Eag+6.690
enegger+6.656
 NIC+6.493
 Ghana+6.090
Neg logit contributions
Ore-12.729
ppo-12.105
 cherry-11.649
lining-11.639
Cola-11.485
Token five
Token ID1936
Feature activation-6.37e-02

Pos logit contributions
+6.186
 Eag+6.123
 NIC+5.791
enegger+5.584
 Ghana+5.541
Neg logit contributions
Ore-11.285
ppo-10.876
lining-10.562
Cola-10.403
 cherry-10.345
Token Americans
Token ID3399
Feature activation+2.60e-01

Pos logit contributions
+0.601
enegger+0.575
igham+0.545
 Eag+0.538
 NIC+0.537
Neg logit contributions
Ore-0.608
 cherry-0.571
 Isis-0.569
lining-0.558
ppo-0.553
Token knows
Token ID4206
Feature activation+4.06e-01

Pos logit contributions
Ore+2.278
 cherry+2.206
 Isis+2.189
lining+2.100
ppo+2.087
Neg logit contributions
-2.667
enegger-2.548
igham-2.440
-2.389
 NIC-2.336
Token about
Token ID546
Feature activation-5.60e-03

Pos logit contributions
Ore+3.337
 Isis+3.252
 cherry+3.203
lining+3.017
ppo+2.959
Neg logit contributions
-4.319
enegger-4.150
igham-4.023
-3.943
 NIC-3.751
Token(
Token ID7
Feature activation-1.06e-01

Pos logit contributions
+0.179
enegger+0.173
igham+0.167
+0.163
 NIC+0.162
Neg logit contributions
Ore-0.104
 cherry-0.097
 Isis-0.097
lining-0.092
ppo-0.091
Token m
Token ID285
Feature activation-1.97e-01

Pos logit contributions
+1.030
enegger+0.982
igham+0.933
+0.912
 NIC+0.909
Neg logit contributions
Ore-0.989
 Isis-0.945
 cherry-0.942
lining-0.908
ppo-0.902
TokenGrid
Token ID41339
Feature activation+2.85e-01

Pos logit contributions
+1.911
enegger+1.814
igham+1.737
+1.702
 NIC+1.682
Neg logit contributions
Ore-1.814
 cherry-1.754
 Isis-1.746
lining-1.676
ppo-1.671
TokenTemplate
Token ID30800
Feature activation+7.92e-02

Pos logit contributions
Ore+2.397
 cherry+2.230
 Isis+2.216
lining+2.156
ppo+2.116
Neg logit contributions
-3.027
enegger-2.949
igham-2.813
-2.726
 NIC-2.687
Token )
Token ID1267
Feature activation-2.17e-01

Pos logit contributions
Ore+0.671
 cherry+0.634
 Isis+0.632
lining+0.610
ppo+0.605
Neg logit contributions
-0.838
enegger-0.811
igham-0.774
-0.753
 NIC-0.744
Token ;
Token ID2162
Feature activation-1.19e+00

Pos logit contributions
+2.377
enegger+2.275
igham+2.183
+2.140
 NIC+2.126
Neg logit contributions
Ore-1.735
 Isis-1.662
 cherry-1.643
lining-1.579
ppo-1.570
Token density
Token ID12109
Feature activation-5.11e-01

Pos logit contributions
+8.566
 NIC+8.195
 Eag+7.841
enegger+7.545
igham+7.423
Neg logit contributions
 Isis-11.000
Ore-10.907
Bee-10.332
ppo-10.330
lining-10.252
TokenGrid
Token ID41339
Feature activation-9.94e-02

Pos logit contributions
+5.801
enegger+5.389
igham+5.182
+5.153
 NIC+5.111
Neg logit contributions
 Isis-3.653
 cherry-3.610
Ore-3.562
ppo-3.403
lining-3.367
Token.
Token ID13
Feature activation-6.10e-01

Pos logit contributions
+0.978
enegger+0.939
igham+0.891
+0.870
 NIC+0.862
Neg logit contributions
Ore-0.911
 Isis-0.869
 cherry-0.868
lining-0.837
ppo-0.834
TokenInit
Token ID31768
Feature activation+1.51e-01

Pos logit contributions
+5.359
+4.769
enegger+4.632
igham+4.616
 Eag+4.509
Neg logit contributions
 Isis-5.837
Ore-5.701
 cherry-5.689
ppo-5.411
lining-5.398
Token(
Token ID7
Feature activation-2.24e-01

Pos logit contributions
Ore+1.347
 cherry+1.257
 Isis+1.251
lining+1.219
ppo+1.204
Neg logit contributions
-1.537
enegger-1.497
igham-1.420
-1.378
 NIC-1.367
Token like
Token ID588
Feature activation+1.12e-01

Pos logit contributions
Ore+2.419
 cherry+2.343
 Isis+2.339
lining+2.235
ppo+2.179
Neg logit contributions
-3.069
enegger-3.011
igham-2.850
-2.797
 NIC-2.716
Token N
Token ID399
Feature activation-5.17e-01

Pos logit contributions
Ore+1.098
 Isis+1.049
 cherry+1.048
lining+1.012
ppo+1.004
Neg logit contributions
-1.041
enegger-0.998
igham-0.946
-0.921
 NIC-0.905
Tokenairo
Token ID18131
Feature activation-2.39e-02

Pos logit contributions
+5.034
enegger+4.948
igham+4.880
+4.615
 NIC+4.505
Neg logit contributions
Ore-4.372
 cherry-4.271
 Isis-4.148
lining-4.009
 Pike-3.845
Tokenbi
Token ID8482
Feature activation+5.58e-02

Pos logit contributions
+0.262
enegger+0.253
igham+0.242
+0.236
 NIC+0.234
Neg logit contributions
Ore-0.193
 cherry-0.182
 Isis-0.181
lining-0.174
ppo-0.173
Token and
Token ID290
Feature activation-2.12e-01

Pos logit contributions
Ore+0.505
 cherry+0.481
 Isis+0.481
lining+0.464
ppo+0.460
Neg logit contributions
-0.558
enegger-0.537
igham-0.511
-0.498
 NIC-0.492
Token M
Token ID337
Feature activation-1.19e+00

Pos logit contributions
+1.907
enegger+1.841
igham+1.755
 NIC+1.738
 Eag+1.721
Neg logit contributions
Ore-2.053
 cherry-1.941
 Isis-1.918
ppo-1.901
lining-1.892
Tokenomb
Token ID2381
Feature activation-3.40e-01

Pos logit contributions
+8.960
igham+8.959
enegger+8.703
izon+7.950
 Ghana+7.948
Neg logit contributions
 cherry-10.358
Ore-10.353
 Isis-10.065
 Pike-9.666
lining-9.627
Tokenasa
Token ID15462
Feature activation+2.27e-01

Pos logit contributions
+1.866
enegger+1.798
igham+1.714
 Eag+1.493
 NIC+1.482
Neg logit contributions
Ore-4.483
 cherry-4.369
 Isis-4.320
lining-4.210
ppo-4.177
Token to
Token ID284
Feature activation-2.45e-01

Pos logit contributions
Ore+1.980
 cherry+1.893
 Isis+1.888
lining+1.822
ppo+1.800
Neg logit contributions
-2.340
enegger-2.255
igham-2.132
-2.099
 NIC-2.054
Token make
Token ID787
Feature activation+1.82e-01

Pos logit contributions
+2.311
enegger+2.207
igham+2.102
 NIC+2.080
 Eag+2.016
Neg logit contributions
Ore-2.313
 Isis-2.140
 cherry-2.098
lining-2.083
ppo-2.080
Token public
Token ID1171
Feature activation-2.85e-01

Pos logit contributions
Ore+1.547
 cherry+1.482
 Isis+1.479
lining+1.417
ppo+1.396
Neg logit contributions
-1.919
enegger-1.849
igham-1.756
-1.727
 NIC-1.696
Token prev
Token ID8654
Feature activation+5.45e-01

Pos logit contributions
Ore+3.969
 cherry+3.891
 Isis+3.797
lining+3.642
ppo+3.591
Neg logit contributions
-4.092
enegger-4.031
igham-3.788
-3.658
 NIC-3.525
Token_
Token ID62
Feature activation+4.05e-01

Pos logit contributions
Ore+3.958
 Isis+3.576
 cherry+3.568
lining+3.489
ifier+3.309
Neg logit contributions
enegger-6.257
-6.205
igham-5.976
 Eag-5.759
 NIC-5.750
Tokenstate
Token ID5219
Feature activation+7.00e-01

Pos logit contributions
Ore+3.321
 cherry+3.105
 Isis+3.060
lining+3.056
ppo+2.970
Neg logit contributions
-4.293
enegger-4.265
igham-4.066
-3.947
 NIC-3.933
Token :
Token ID1058
Feature activation+4.51e-01

Pos logit contributions
Ore+3.932
 cherry+3.645
 Isis+3.529
lining+3.460
ppo+3.303
Neg logit contributions
enegger-8.814
-8.728
igham-8.571
 Eag-8.298
 NIC-8.145
Token Option
Token ID16018
Feature activation+1.18e-01

Pos logit contributions
Ore+3.802
 cherry+3.717
 Isis+3.637
lining+3.459
ppo+3.387
Neg logit contributions
-4.644
enegger-4.635
igham-4.397
-4.229
 NIC-4.105
Token <
Token ID1279
Feature activation+8.88e-01

Pos logit contributions
Ore+1.047
 cherry+0.993
 Isis+0.988
lining+0.951
ppo+0.939
Neg logit contributions
-1.204
enegger-1.159
igham-1.108
-1.079
 NIC-1.068
Token Board
Token ID5926
Feature activation+4.00e-01

Pos logit contributions
Ore+7.363
 cherry+7.095
 Isis+6.888
 Pike+6.633
lining+6.557
Neg logit contributions
enegger-8.878
-8.723
igham-8.302
-7.842
 NIC-7.591
Token >
Token ID1875
Feature activation+2.47e-01

Pos logit contributions
Ore+3.120
 Isis+2.879
 cherry+2.878
lining+2.744
ppo+2.669
Neg logit contributions
-4.433
enegger-4.367
igham-4.212
 Eag-4.007
-4.003
Token,
Token ID837
Feature activation+2.98e-01

Pos logit contributions
Ore+1.971
 cherry+1.885
 Isis+1.845
lining+1.781
ppo+1.752
Neg logit contributions
-2.712
enegger-2.636
igham-2.526
-2.443
 Eag-2.429
Token //
Token ID3373
Feature activation+4.27e-01

Pos logit contributions
Ore+3.375
 cherry+3.296
 Isis+3.248
lining+3.163
ppo+3.108
Neg logit contributions
-2.259
enegger-2.215
igham-2.059
-1.948
 NIC-1.906
Token The
Token ID383
Feature activation+1.10e-01

Pos logit contributions
Ore+3.696
 Isis+3.557
 cherry+3.555
lining+3.390
ppo+3.333
Neg logit contributions
-4.351
enegger-4.246
igham-4.026
-3.913
 NIC-3.766
Token we
Token ID356
Feature activation+9.14e-02

Pos logit contributions
Ore+2.877
 cherry+2.781
 Isis+2.758
lining+2.645
ppo+2.608
Neg logit contributions
-3.421
enegger-3.285
igham-3.138
-3.074
 Eag-2.980
Token believe
Token ID1975
Feature activation+7.46e-01

Pos logit contributions
Ore+0.838
 Isis+0.792
 cherry+0.790
lining+0.766
ppo+0.759
Neg logit contributions
-0.904
enegger-0.871
igham-0.828
-0.802
 NIC-0.802
Token it
Token ID340
Feature activation+4.93e-01

Pos logit contributions
Ore+5.771
 cherry+5.726
 Isis+5.683
lining+5.402
ppo+5.128
Neg logit contributions
-8.020
enegger-7.796
-7.502
igham-7.464
 Eag-6.970
Token's
Token ID338
Feature activation+1.65e-01

Pos logit contributions
Ore+4.040
 cherry+4.031
 Isis+3.920
lining+3.797
ppo+3.633
Neg logit contributions
-5.165
enegger-5.010
igham-4.793
-4.741
 Eag-4.583
Token vital
Token ID9204
Feature activation+4.52e-01

Pos logit contributions
Ore+1.645
 cherry+1.574
 Isis+1.570
lining+1.521
ppo+1.506
Neg logit contributions
-1.496
enegger-1.434
igham-1.359
-1.322
 NIC-1.301
Token that
Token ID326
Feature activation+8.29e-01

Pos logit contributions
Ore+3.802
 cherry+3.655
 Isis+3.636
lining+3.475
ppo+3.399
Neg logit contributions
-4.726
enegger-4.610
igham-4.383
-4.343
 Eag-4.196
Token we
Token ID356
Feature activation+4.20e-01

Pos logit contributions
Ore+6.202
 Isis+6.133
 cherry+6.130
lining+5.747
ppo+5.462
Neg logit contributions
-8.967
enegger-8.955
-8.550
igham-8.515
 Eag-7.905
Token pursue
Token ID10660
Feature activation+4.65e-01

Pos logit contributions
Ore+3.421
 cherry+3.414
 Isis+3.317
lining+3.184
ppo+3.161
Neg logit contributions
-4.477
enegger-4.329
-4.142
igham-4.122
 Eag-3.966
Token this
Token ID428
Feature activation+4.12e-01

Pos logit contributions
Ore+3.874
 cherry+3.784
 Isis+3.729
lining+3.579
ppo+3.477
Neg logit contributions
-4.881
enegger-4.765
igham-4.507
-4.498
 Eag-4.282
Token common
Token ID2219
Feature activation+3.25e-01

Pos logit contributions
Ore+3.539
 cherry+3.457
 Isis+3.388
lining+3.270
ppo+3.163
Neg logit contributions
-4.251
enegger-4.091
igham-3.928
-3.886
 Eag-3.725
Token ground
Token ID2323
Feature activation+6.40e-01

Pos logit contributions
Ore+2.748
 cherry+2.605
 Isis+2.596
lining+2.523
ppo+2.437
Neg logit contributions
-3.422
enegger-3.284
igham-3.174
-3.144
 Eag-3.039
Token types
Token ID3858
Feature activation-3.88e-02

Pos logit contributions
Ore+0.332
 cherry+0.315
 Isis+0.314
lining+0.303
ppo+0.301
Neg logit contributions
-0.382
enegger-0.367
igham-0.350
-0.341
 NIC-0.339
Token,
Token ID11
Feature activation+1.97e-01

Pos logit contributions
+0.383
enegger+0.366
igham+0.350
 NIC+0.341
+0.339
Neg logit contributions
Ore-0.356
 cherry-0.336
 Isis-0.336
lining-0.325
ppo-0.323
Token (
Token ID357
Feature activation-3.18e-01

Pos logit contributions
Ore+1.762
 cherry+1.683
 Isis+1.675
lining+1.618
ppo+1.600
Neg logit contributions
-1.985
enegger-1.917
igham-1.819
-1.783
 NIC-1.742
TokenB
Token ID33
Feature activation-3.79e-01

Pos logit contributions
+3.107
enegger+2.919
igham+2.826
+2.726
 NIC+2.717
Neg logit contributions
Ore-2.837
 cherry-2.759
 Isis-2.755
ppo-2.606
lining-2.590
Token)
Token ID8
Feature activation+2.83e-01

Pos logit contributions
+3.611
enegger+3.445
igham+3.319
 NIC+3.204
+3.172
Neg logit contributions
Ore-3.523
 Isis-3.315
 cherry-3.296
lining-3.208
ppo-3.184
Token Type
Token ID5994
Feature activation+9.24e-01

Pos logit contributions
Ore+2.536
 cherry+2.445
 Isis+2.424
lining+2.346
ppo+2.307
Neg logit contributions
-2.843
enegger-2.745
igham-2.602
-2.550
 NIC-2.468
Token 1
Token ID352
Feature activation+3.27e-01

Pos logit contributions
Ore+7.109
 cherry+6.981
 Isis+6.949
lining+6.764
ifier+6.661
Neg logit contributions
-9.398
enegger-9.390
igham-8.597
-8.435
 Eag-8.132
Token probe
Token ID12774
Feature activation+2.31e-01

Pos logit contributions
Ore+2.839
 cherry+2.731
 Isis+2.692
lining+2.617
ppo+2.581
Neg logit contributions
-3.336
enegger-3.276
igham-3.083
-3.023
 NIC-2.930
Token test
Token ID1332
Feature activation+4.35e-01

Pos logit contributions
Ore+2.073
 cherry+1.988
 Isis+1.970
lining+1.909
ppo+1.884
Neg logit contributions
-2.311
enegger-2.240
igham-2.119
-2.081
 NIC-2.027
Token (
Token ID357
Feature activation+2.52e-01

Pos logit contributions
Ore+3.666
 cherry+3.540
 Isis+3.482
lining+3.398
ppo+3.342
Neg logit contributions
-4.482
enegger-4.368
igham-4.149
-4.109
 NIC-3.952
Tokentri
Token ID28461
Feature activation+5.86e-01

Pos logit contributions
Ore+2.263
 cherry+2.125
 Isis+2.114
lining+2.077
ppo+2.052
Neg logit contributions
-2.529
enegger-2.468
igham-2.329
-2.283
 NIC-2.248
Token #
Token ID1303
Feature activation+3.43e-01

Pos logit contributions
Ore+1.185
 cherry+1.132
 Isis+1.129
lining+1.089
ppo+1.080
Neg logit contributions
-1.299
enegger-1.250
igham-1.190
-1.159
 NIC-1.143
Tokendeb
Token ID11275
Feature activation-2.97e-01

Pos logit contributions
Ore+3.086
 cherry+2.884
 Isis+2.870
lining+2.804
ppo+2.764
Neg logit contributions
-3.430
enegger-3.328
igham-3.175
-3.078
 NIC-3.059
Tokenates
Token ID689
Feature activation+3.37e-01

Pos logit contributions
+2.789
enegger+2.591
igham+2.563
+2.380
 NIC+2.378
Neg logit contributions
Ore-2.783
 Isis-2.684
 cherry-2.683
lining-2.557
ppo-2.521
Token #
Token ID1303
Feature activation+3.34e-01

Pos logit contributions
Ore+2.752
 cherry+2.617
 Isis+2.595
lining+2.522
ppo+2.512
Neg logit contributions
-3.603
enegger-3.488
igham-3.318
-3.261
 NIC-3.211
TokenOccup
Token ID47658
Feature activation+2.83e-02

Pos logit contributions
Ore+3.078
 cherry+2.881
 Isis+2.861
lining+2.824
ppo+2.778
Neg logit contributions
-3.256
enegger-3.134
igham-3.017
-2.902
 NIC-2.902
Tokeny
Token ID88
Feature activation+9.44e-01

Pos logit contributions
Ore+0.231
 cherry+0.218
 Isis+0.218
lining+0.209
ppo+0.208
Neg logit contributions
-0.308
enegger-0.298
igham-0.284
-0.278
 NIC-0.275
TokenThe
Token ID464
Feature activation+2.17e-01

Pos logit contributions
Ore+8.137
Bee+7.268
 cherry+7.209
 Isis+7.192
lining+7.135
Neg logit contributions
-8.877
enegger-8.717
igham-8.365
 NIC-8.012
-7.906
TokenDeb
Token ID16587
Feature activation-4.49e-01

Pos logit contributions
Ore+1.810
 cherry+1.678
 Isis+1.669
lining+1.633
ppo+1.620
Neg logit contributions
-2.329
enegger-2.272
igham-2.162
-2.099
 NIC-2.095
Tokenates
Token ID689
Feature activation+4.15e-01

Pos logit contributions
+4.076
enegger+3.762
igham+3.737
+3.483
 NIC+3.480
Neg logit contributions
Ore-4.246
 Isis-4.120
 cherry-4.075
lining-3.935
ppo-3.872
Token pic
Token ID8301
Feature activation+1.12e-01

Pos logit contributions
Ore+3.046
 cherry+2.864
 Isis+2.834
lining+2.718
ppo+2.714
Neg logit contributions
-4.753
enegger-4.622
igham-4.456
-4.320
 NIC-4.275
Token.
Token ID13
Feature activation-3.08e-01

Pos logit contributions
Ore+1.008
 cherry+0.957
 Isis+0.956
lining+0.920
ppo+0.913
Neg logit contributions
-1.135
enegger-1.094
igham-1.044
-1.017
 NIC-1.004
Token of
Token ID286
Feature activation-3.13e-01

Pos logit contributions
Ore+2.732
 cherry+2.614
 Isis+2.603
lining+2.451
ppo+2.399
Neg logit contributions
-3.870
enegger-3.805
igham-3.614
-3.513
 NIC-3.485
Token to
Token ID284
Feature activation-1.52e-01

Pos logit contributions
+2.883
enegger+2.740
igham+2.578
+2.554
 NIC+2.501
Neg logit contributions
Ore-3.060
 Isis-2.872
 cherry-2.865
lining-2.811
ppo-2.808
Token secure
Token ID5713
Feature activation-7.98e-03

Pos logit contributions
+1.509
enegger+1.428
igham+1.361
 NIC+1.341
+1.326
Neg logit contributions
Ore-1.392
 Isis-1.292
 cherry-1.267
lining-1.253
ppo-1.247
Token his
Token ID465
Feature activation+1.45e-01

Pos logit contributions
+0.082
enegger+0.079
igham+0.075
+0.073
 NIC+0.073
Neg logit contributions
Ore-0.070
 cherry-0.066
 Isis-0.065
lining-0.063
ppo-0.063
Token re
Token ID302
Feature activation+5.81e-01

Pos logit contributions
Ore+1.272
 cherry+1.218
 Isis+1.213
lining+1.164
ppo+1.156
Neg logit contributions
-1.483
enegger-1.431
igham-1.365
-1.331
 NIC-1.310
Token-
Token ID12
Feature activation+1.01e+00

Pos logit contributions
Ore+4.466
 Isis+4.245
 cherry+4.160
lining+4.158
ppo+4.040
Neg logit contributions
enegger-6.186
-6.124
-5.828
igham-5.826
 NIC-5.669
Tokenelection
Token ID14300
Feature activation+1.80e-02

Pos logit contributions
Ore+4.736
lining+4.431
 cherry+4.116
 Isis+4.050
ifier+3.984
Neg logit contributions
enegger-13.023
-12.946
-12.785
igham-12.635
 NIC-12.496
Token,
Token ID11
Feature activation+1.44e-01

Pos logit contributions
Ore+0.166
 cherry+0.158
 Isis+0.158
lining+0.153
ppo+0.151
Neg logit contributions
-0.177
enegger-0.170
igham-0.162
-0.158
 NIC-0.156
Token she
Token ID673
Feature activation-1.57e-01

Pos logit contributions
Ore+1.258
 Isis+1.202
 cherry+1.200
lining+1.153
ppo+1.140
Neg logit contributions
-1.481
enegger-1.431
igham-1.362
-1.326
 NIC-1.311
Token can
Token ID460
Feature activation+1.73e-01

Pos logit contributions
+1.491
enegger+1.441
igham+1.357
 NIC+1.312
 Eag+1.301
Neg logit contributions
Ore-1.505
 Isis-1.399
 cherry-1.387
ppo-1.367
lining-1.363
Token claim
Token ID1624
Feature activation-3.79e-01

Pos logit contributions
Ore+1.420
 cherry+1.382
 Isis+1.359
lining+1.308
ppo+1.296
Neg logit contributions
-1.856
enegger-1.785
igham-1.721
-1.678
 NIC-1.656
Token public
Token ID1171
Feature activation-6.56e-01

Pos logit contributions
+1.379
enegger+1.310
igham+1.251
 NIC+1.225
+1.218
Neg logit contributions
Ore-1.302
 cherry-1.225
 Isis-1.224
lining-1.191
ppo-1.185
Token property
Token ID3119
Feature activation-9.32e-02

Pos logit contributions
+5.711
enegger+5.336
 NIC+5.094
igham+5.017
 Eag+4.936
Neg logit contributions
Ore-6.359
 Isis-5.975
 cherry-5.841
ppo-5.785
lining-5.783
Token in
Token ID287
Feature activation+4.47e-01

Pos logit contributions
+0.902
enegger+0.862
igham+0.820
+0.801
 NIC+0.796
Neg logit contributions
Ore-0.872
 cherry-0.828
 Isis-0.827
lining-0.801
ppo-0.796
Token Roh
Token ID32694
Feature activation+9.06e-02

Pos logit contributions
Ore+3.502
 Isis+3.425
 cherry+3.411
lining+3.299
ppo+3.187
Neg logit contributions
-4.856
enegger-4.701
igham-4.515
-4.387
 NIC-4.261
Tokent
Token ID83
Feature activation+6.98e-02

Pos logit contributions
Ore+0.883
 cherry+0.842
 Isis+0.839
lining+0.817
ppo+0.810
Neg logit contributions
-0.843
enegger-0.812
igham-0.768
-0.752
 NIC-0.743
Tokenak
Token ID461
Feature activation+3.49e-01

Pos logit contributions
Ore+0.983
 cherry+0.952
 Isis+0.951
lining+0.930
ppo+0.926
Neg logit contributions
-0.346
enegger-0.319
igham-0.287
-0.270
 NIC-0.265
Token city
Token ID1748
Feature activation+1.62e-01

Pos logit contributions
Ore+2.987
 cherry+2.865
 Isis+2.823
lining+2.743
ppo+2.717
Neg logit contributions
-3.598
enegger-3.479
igham-3.303
-3.215
 NIC-3.168
Token and
Token ID290
Feature activation+6.39e-02

Pos logit contributions
Ore+1.439
 cherry+1.374
 Isis+1.367
lining+1.324
ppo+1.310
Neg logit contributions
-1.633
enegger-1.575
igham-1.502
-1.461
 NIC-1.440
Token parts
Token ID3354
Feature activation+9.48e-02

Pos logit contributions
Ore+0.581
 cherry+0.551
 Isis+0.550
lining+0.532
ppo+0.528
Neg logit contributions
-0.636
enegger-0.611
igham-0.583
-0.566
 NIC-0.563
Token of
Token ID286
Feature activation+2.81e-01

Pos logit contributions
Ore+0.779
 cherry+0.740
 Isis+0.738
lining+0.710
ppo+0.703
Neg logit contributions
-1.024
enegger-0.991
igham-0.945
-0.918
 NIC-0.910
Token Roh
Token ID32694
Feature activation+2.35e-01

Pos logit contributions
Ore+2.350
 Isis+2.256
 cherry+2.249
lining+2.168
ppo+2.117
Neg logit contributions
-2.965
enegger-2.872
igham-2.734
-2.668
 NIC-2.607
Token in
Token ID287
Feature activation-4.15e-02

Pos logit contributions
Ore+1.612
 Isis+1.541
 cherry+1.540
lining+1.486
ppo+1.466
Neg logit contributions
-1.845
enegger-1.780
igham-1.697
-1.651
 NIC-1.634
Token time
Token ID640
Feature activation-1.67e-01

Pos logit contributions
+0.398
enegger+0.381
igham+0.362
+0.352
 NIC+0.352
Neg logit contributions
Ore-0.392
 cherry-0.371
 Isis-0.371
lining-0.358
ppo-0.357
Token for
Token ID329
Feature activation+1.80e-01

Pos logit contributions
+1.632
enegger+1.553
igham+1.488
+1.449
 NIC+1.440
Neg logit contributions
Ore-1.537
 Isis-1.457
 cherry-1.456
ppo-1.396
lining-1.390
Token the
Token ID262
Feature activation-2.04e-01

Pos logit contributions
Ore+1.637
 cherry+1.564
 Isis+1.559
lining+1.504
ppo+1.490
Neg logit contributions
-1.792
enegger-1.731
igham-1.647
-1.607
 NIC-1.578
Token season
Token ID1622
Feature activation-1.34e-01

Pos logit contributions
+1.893
enegger+1.801
igham+1.702
 NIC+1.694
 Eag+1.651
Neg logit contributions
Ore-1.963
 Isis-1.844
 cherry-1.829
lining-1.793
ppo-1.786
Token opener
Token ID21996
Feature activation+1.15e-01

Pos logit contributions
+1.310
enegger+1.252
igham+1.192
+1.161
 NIC+1.151
Neg logit contributions
Ore-1.243
 cherry-1.176
 Isis-1.174
lining-1.136
ppo-1.134
Token,
Token ID11
Feature activation-3.34e-02

Pos logit contributions
Ore+1.002
 Isis+0.955
 cherry+0.954
lining+0.920
ppo+0.907
Neg logit contributions
-1.179
enegger-1.144
igham-1.087
-1.060
 NIC-1.048
Token he
Token ID339
Feature activation-3.22e-01

Pos logit contributions
+0.344
enegger+0.331
igham+0.315
+0.307
 NIC+0.306
Neg logit contributions
Ore-0.292
 cherry-0.276
 Isis-0.275
lining-0.266
ppo-0.265
Token replied
Token ID8712
Feature activation-5.84e-01

Pos logit contributions
+2.735
enegger+2.638
igham+2.454
 NIC+2.339
+2.328
Neg logit contributions
Ore-3.377
 Isis-3.184
 cherry-3.114
ppo-3.060
lining-3.057
Token:
Token ID25
Feature activation-2.16e-01

Pos logit contributions
+5.492
enegger+5.094
 NIC+4.859
igham+4.827
+4.775
Neg logit contributions
Ore-5.356
ppo-4.955
 Isis-4.947
 cherry-4.882
lining-4.814
Token
Token ID564
Feature activation-1.34e-01

Pos logit contributions
+1.909
enegger+1.815
igham+1.700
+1.677
 NIC+1.657
Neg logit contributions
Ore-2.195
 cherry-2.090
 Isis-2.088
ppo-2.024
lining-2.022
Token 2
Token ID362
Feature activation+2.88e-01

Pos logit contributions
Ore+1.862
 cherry+1.767
 Isis+1.748
lining+1.658
ppo+1.608
Neg logit contributions
-3.735
enegger-3.630
igham-3.531
-3.403
 Eag-3.368
Token Richard
Token ID6219
Feature activation+4.60e-01

Pos logit contributions
Ore+2.781
 Isis+2.705
 cherry+2.670
lining+2.548
ppo+2.534
Neg logit contributions
-2.689
enegger-2.625
igham-2.474
-2.410
 NIC-2.293
Token Sherman
Token ID23198
Feature activation-1.89e-02

Pos logit contributions
Ore+4.612
 Isis+4.415
 cherry+4.368
 Pike+4.225
lining+4.154
Neg logit contributions
-4.203
enegger-4.069
-3.608
igham-3.579
 NIC-3.487
Token,
Token ID11
Feature activation+4.07e-01

Pos logit contributions
+0.188
enegger+0.181
igham+0.173
+0.168
 NIC+0.167
Neg logit contributions
Ore-0.172
 cherry-0.163
 Isis-0.163
lining-0.158
ppo-0.157
Token Seahawks
Token ID16732
Feature activation+5.11e-01

Pos logit contributions
Ore+2.677
 cherry+2.541
 Isis+2.512
ppo+2.304
lining+2.299
Neg logit contributions
-5.024
enegger-4.982
igham-4.788
-4.666
 NIC-4.529
Token 1
Token ID352
Feature activation+5.52e-01

Pos logit contributions
Ore+4.808
 Isis+4.658
 cherry+4.560
ppo+4.374
 Pike+4.344
Neg logit contributions
-4.761
enegger-4.682
igham-4.429
-4.248
 NIC-4.040
Token AL
Token ID8355
Feature activation-5.61e-02

Pos logit contributions
Ore+3.860
 cherry+3.732
 Isis+3.731
lining+3.497
ppo+3.426
Neg logit contributions
-6.399
enegger-6.363
igham-6.055
-5.772
 Eag-5.689
TokenREAD
Token ID15675
Feature activation-2.58e-01

Pos logit contributions
+0.547
enegger+0.526
igham+0.500
+0.487
 NIC+0.482
Neg logit contributions
Ore-0.522
 cherry-0.496
 Isis-0.495
lining-0.479
ppo-0.475
TokenY
Token ID56
Feature activation+2.85e-01

Pos logit contributions
+3.042
enegger+2.908
igham+2.791
 NIC+2.761
+2.735
Neg logit contributions
Ore-1.885
 cherry-1.759
 Isis-1.757
lining-1.686
ppo-1.664
Token COMP
Token ID24301
Feature activation-4.62e-01

Pos logit contributions
Ore+2.560
 cherry+2.477
 Isis+2.474
lining+2.362
ppo+2.348
Neg logit contributions
-2.807
enegger-2.739
igham-2.600
-2.519
 Eag-2.449
TokenET
Token ID2767
Feature activation-4.47e-01

Pos logit contributions
+3.806
enegger+3.591
 NIC+3.372
igham+3.286
+3.243
Neg logit contributions
Ore-4.813
 cherry-4.710
 Isis-4.662
lining-4.586
ppo-4.467
Token its
Token ID663
Feature activation-9.38e-02

Pos logit contributions
+0.968
enegger+0.925
igham+0.880
 NIC+0.872
 Eag+0.854
Neg logit contributions
Ore-0.935
 Isis-0.878
 cherry-0.872
ppo-0.855
lining-0.847
Token efforts
Token ID4040
Feature activation+2.48e-01

Pos logit contributions
+0.929
enegger+0.888
igham+0.845
 NIC+0.837
+0.820
Neg logit contributions
Ore-0.859
 Isis-0.805
 cherry-0.802
ppo-0.781
lining-0.779
Token in
Token ID287
Feature activation-1.92e-01

Pos logit contributions
Ore+2.158
 cherry+2.082
 Isis+2.065
lining+2.006
ppo+1.953
Neg logit contributions
-2.521
enegger-2.437
igham-2.317
-2.268
 NIC-2.210
Token education
Token ID3707
Feature activation+1.46e-01

Pos logit contributions
+1.824
enegger+1.754
igham+1.656
 NIC+1.654
 Eag+1.634
Neg logit contributions
Ore-1.810
 Isis-1.694
 cherry-1.691
ppo-1.662
lining-1.632
Token,
Token ID11
Feature activation+1.29e-01

Pos logit contributions
Ore+1.295
 cherry+1.235
 Isis+1.230
lining+1.189
ppo+1.170
Neg logit contributions
-1.481
enegger-1.433
igham-1.360
-1.324
 NIC-1.304
Token health
Token ID1535
Feature activation+2.82e-01

Pos logit contributions
Ore+1.171
 cherry+1.117
 Isis+1.115
lining+1.076
ppo+1.064
Neg logit contributions
-1.283
enegger-1.233
igham-1.176
-1.146
 NIC-1.125
Token and
Token ID290
Feature activation+2.57e-01

Pos logit contributions
Ore+2.324
 cherry+2.239
 Isis+2.208
lining+2.164
ppo+2.126
Neg logit contributions
-2.999
enegger-2.893
igham-2.752
-2.718
 Eag-2.640
Token workforce
Token ID16433
Feature activation+1.33e-01

Pos logit contributions
Ore+2.391
 cherry+2.317
 Isis+2.308
lining+2.212
ppo+2.185
Neg logit contributions
-2.476
enegger-2.369
igham-2.261
-2.222
 Eag-2.126
Token matters
Token ID6067
Feature activation+3.55e-01

Pos logit contributions
Ore+1.173
 cherry+1.123
 Isis+1.116
lining+1.080
ppo+1.060
Neg logit contributions
-1.358
enegger-1.318
igham-1.252
-1.226
 NIC-1.201
Token.
Token ID13
Feature activation-1.19e-01

Pos logit contributions
Ore+2.934
 cherry+2.806
 Isis+2.788
lining+2.700
ppo+2.626
Neg logit contributions
-3.742
enegger-3.620
igham-3.456
-3.398
 Eag-3.304
Token
Token ID198
Feature activation+7.14e-02

Pos logit contributions
+1.242
enegger+1.194
igham+1.127
 NIC+1.123
 Eag+1.108
Neg logit contributions
Ore-1.023
 cherry-0.966
 Isis-0.957
lining-0.938
ppo-0.926
Token pay
Token ID1414
Feature activation-9.71e-02

Pos logit contributions
Ore+2.344
 cherry+2.293
 Isis+2.264
lining+2.160
ppo+2.120
Neg logit contributions
-3.219
enegger-3.117
igham-3.001
-2.945
 Eag-2.864
Token a
Token ID257
Feature activation+4.34e-01

Pos logit contributions
+0.923
enegger+0.888
igham+0.841
 NIC+0.825
+0.818
Neg logit contributions
Ore-0.923
 cherry-0.867
 Isis-0.863
ppo-0.849
lining-0.840
Token fixed
Token ID5969
Feature activation+5.58e-02

Pos logit contributions
Ore+3.746
 cherry+3.708
 Isis+3.694
lining+3.520
ppo+3.343
Neg logit contributions
-4.410
enegger-4.294
igham-4.029
-3.980
 Eag-3.824
Token return
Token ID1441
Feature activation+6.78e-02

Pos logit contributions
Ore+0.494
 cherry+0.469
 Isis+0.468
lining+0.452
ppo+0.448
Neg logit contributions
-0.570
enegger-0.549
igham-0.523
-0.510
 NIC-0.505
Token based
Token ID1912
Feature activation+1.27e-01

Pos logit contributions
Ore+0.613
 Isis+0.584
 cherry+0.583
lining+0.563
ppo+0.555
Neg logit contributions
-0.678
enegger-0.654
igham-0.623
-0.608
 NIC-0.598
Token on
Token ID319
Feature activation+2.69e-01

Pos logit contributions
Ore+1.142
 Isis+1.096
 cherry+1.096
lining+1.061
ppo+1.036
Neg logit contributions
-1.274
enegger-1.226
igham-1.172
-1.135
 NIC-1.117
Token the
Token ID262
Feature activation+2.08e-01

Pos logit contributions
Ore+2.275
 Isis+2.199
 cherry+2.194
lining+2.097
ppo+2.039
Neg logit contributions
-2.830
enegger-2.722
igham-2.601
-2.539
 NIC-2.481
Token profit
Token ID7630
Feature activation+3.35e-01

Pos logit contributions
Ore+1.924
 cherry+1.856
 Isis+1.855
lining+1.780
ppo+1.749
Neg logit contributions
-2.027
enegger-1.948
igham-1.850
-1.806
 NIC-1.768
Token generated
Token ID7560
Feature activation-1.82e-01

Pos logit contributions
Ore+2.769
 Isis+2.733
 cherry+2.673
lining+2.567
ppo+2.441
Neg logit contributions
-3.548
enegger-3.474
igham-3.260
-3.201
 Eag-3.092
Token by
Token ID416
Feature activation+1.00e-01

Pos logit contributions
+1.614
enegger+1.543
igham+1.453
 NIC+1.423
+1.407
Neg logit contributions
Ore-1.836
 cherry-1.734
 Isis-1.726
ppo-1.701
lining-1.680
Token an
Token ID281
Feature activation+3.20e-01

Pos logit contributions
Ore+0.877
 cherry+0.833
 Isis+0.832
lining+0.802
ppo+0.794
Neg logit contributions
-1.036
enegger-0.998
igham-0.951
-0.928
 NIC-0.919
Token next
Token ID1306
Feature activation+1.44e-03

Pos logit contributions
Ore+1.354
 cherry+1.299
 Isis+1.292
lining+1.246
ppo+1.228
Neg logit contributions
-1.478
enegger-1.425
igham-1.353
-1.320
 NIC-1.297
Token generation
Token ID5270
Feature activation-2.31e-01

Pos logit contributions
Ore+0.012
 cherry+0.012
 Isis+0.012
lining+0.011
ppo+0.011
Neg logit contributions
-0.015
enegger-0.015
igham-0.014
-0.014
 NIC-0.013
Token sequencing
Token ID32841
Feature activation-2.79e-02

Pos logit contributions
+2.211
enegger+2.066
 NIC+2.019
igham+2.004
 Eag+1.958
Neg logit contributions
Ore-2.164
 Isis-1.994
ppo-1.989
 cherry-1.988
lining-1.965
Token data
Token ID1366
Feature activation-3.65e-01

Pos logit contributions
+0.272
enegger+0.260
igham+0.248
 NIC+0.242
+0.240
Neg logit contributions
Ore-0.259
 Isis-0.245
 cherry-0.245
lining-0.238
ppo-0.237
Token.
Token ID13
Feature activation+2.27e-01

Pos logit contributions
+3.346
enegger+3.156
igham+3.016
 NIC+2.968
 Eag+2.903
Neg logit contributions
Ore-3.488
 Isis-3.299
 cherry-3.280
ppo-3.221
lining-3.196
Token To
Token ID1675
Feature activation-8.77e-02

Pos logit contributions
Ore+1.815
 Isis+1.732
 cherry+1.719
lining+1.630
ppo+1.627
Neg logit contributions
-2.499
enegger-2.434
igham-2.333
-2.271
 NIC-2.211
Token our
Token ID674
Feature activation-9.40e-02

Pos logit contributions
+0.853
enegger+0.809
igham+0.778
 NIC+0.758
+0.757
Neg logit contributions
Ore-0.818
 Isis-0.766
 cherry-0.762
lining-0.746
ppo-0.735
Token knowledge
Token ID3725
Feature activation+2.42e-01

Pos logit contributions
+0.985
enegger+0.947
igham+0.902
 NIC+0.884
+0.881
Neg logit contributions
Ore-0.805
 cherry-0.751
 Isis-0.750
lining-0.728
ppo-0.728
Token,
Token ID11
Feature activation+2.90e-01

Pos logit contributions
Ore+2.071
 cherry+1.985
 Isis+1.972
lining+1.900
ppo+1.874
Neg logit contributions
-2.536
enegger-2.450
igham-2.334
-2.262
 NIC-2.223
Token we
Token ID356
Feature activation-1.68e-01

Pos logit contributions
Ore+2.485
 cherry+2.389
 Isis+2.369
lining+2.272
ppo+2.236
Neg logit contributions
-3.021
enegger-2.938
igham-2.794
-2.722
 NIC-2.649
Token believe
Token ID1975
Feature activation+4.00e-01

Pos logit contributions
+1.609
enegger+1.539
igham+1.484
 NIC+1.447
 Eag+1.412
Neg logit contributions
Ore-1.582
 Isis-1.472
 cherry-1.443
lining-1.431
ppo-1.405
Token'm
Token ID1101
Feature activation+1.45e-01

Pos logit contributions
+1.746
enegger+1.703
igham+1.610
 NIC+1.562
 Eag+1.520
Neg logit contributions
Ore-1.939
 Isis-1.806
 cherry-1.766
lining-1.754
ppo-1.726
Token trying
Token ID2111
Feature activation+3.87e-01

Pos logit contributions
Ore+1.332
 cherry+1.267
 Isis+1.264
lining+1.221
ppo+1.211
Neg logit contributions
-1.439
enegger-1.384
igham-1.317
-1.282
 NIC-1.270
Token very
Token ID845
Feature activation-2.98e-01

Pos logit contributions
Ore+3.141
 cherry+3.092
 Isis+3.031
lining+2.933
ppo+2.880
Neg logit contributions
-4.055
enegger-3.938
igham-3.755
 Eag-3.640
 NIC-3.613
Token hard
Token ID1327
Feature activation+1.22e-01

Pos logit contributions
+2.469
enegger+2.344
igham+2.223
 NIC+2.161
 Eag+2.100
Neg logit contributions
Ore-3.171
 Isis-2.969
ppo-2.922
 cherry-2.921
lining-2.920
Token to
Token ID284
Feature activation+1.78e-01

Pos logit contributions
Ore+1.097
 cherry+1.056
 Isis+1.046
lining+1.014
ppo+0.998
Neg logit contributions
-1.211
enegger-1.169
igham-1.109
-1.088
 NIC-1.071
Token craft
Token ID5977
Feature activation-1.44e-01

Pos logit contributions
Ore+1.522
 cherry+1.470
 Isis+1.451
lining+1.401
ppo+1.385
Neg logit contributions
-1.862
enegger-1.801
igham-1.715
-1.682
 NIC-1.646
Token a
Token ID257
Feature activation-3.09e-01

Pos logit contributions
+1.437
enegger+1.377
igham+1.320
 NIC+1.278
+1.271
Neg logit contributions
Ore-1.301
 Isis-1.224
 cherry-1.222
lining-1.188
ppo-1.185
Token bill
Token ID2855
Feature activation+2.84e-03

Pos logit contributions
+2.537
enegger+2.370
igham+2.287
 NIC+2.271
 Eag+2.158
Neg logit contributions
Ore-3.291
 Isis-3.091
ppo-3.044
 cherry-3.036
lining-3.022
Token to
Token ID284
Feature activation+1.53e-01

Pos logit contributions
Ore+0.027
 Isis+0.026
 cherry+0.026
lining+0.025
ppo+0.025
Neg logit contributions
-0.027
enegger-0.026
igham-0.025
-0.024
 NIC-0.024
Token strike
Token ID5587
Feature activation-8.98e-02

Pos logit contributions
Ore+1.304
 cherry+1.246
 Isis+1.238
lining+1.193
ppo+1.183
Neg logit contributions
-1.606
enegger-1.551
igham-1.479
-1.442
 NIC-1.423
Token a
Token ID257
Feature activation-1.35e-01

Pos logit contributions
+0.899
enegger+0.861
igham+0.827
 NIC+0.804
+0.798
Neg logit contributions
Ore-0.807
 Isis-0.753
 cherry-0.751
ppo-0.737
lining-0.733
Token Monday
Token ID3321
Feature activation-3.99e-02

Pos logit contributions
Ore+1.430
 Isis+1.361
 cherry+1.359
lining+1.311
ppo+1.277
Neg logit contributions
-1.987
enegger-1.911
igham-1.830
-1.781
 NIC-1.748
Token,
Token ID11
Feature activation-7.92e-02

Pos logit contributions
+0.395
enegger+0.380
igham+0.362
+0.352
 NIC+0.350
Neg logit contributions
Ore-0.365
 cherry-0.346
 Isis-0.345
lining-0.334
ppo-0.332
Token but
Token ID475
Feature activation-4.00e-01

Pos logit contributions
+0.777
enegger+0.749
igham+0.711
 NIC+0.696
+0.693
Neg logit contributions
Ore-0.725
 cherry-0.683
 Isis-0.683
ppo-0.663
lining-0.660
Token said
Token ID531
Feature activation-1.26e-01

Pos logit contributions
+3.524
enegger+3.439
 NIC+3.255
igham+3.239
 Eag+3.227
Neg logit contributions
Ore-3.909
 Isis-3.613
 cherry-3.612
ppo-3.588
lining-3.527
Token it
Token ID340
Feature activation+9.10e-02

Pos logit contributions
+1.205
enegger+1.157
igham+1.099
 NIC+1.080
 Eag+1.064
Neg logit contributions
Ore-1.181
 cherry-1.115
 Isis-1.111
ppo-1.081
lining-1.079
Token would
Token ID561
Feature activation-1.43e-01

Pos logit contributions
Ore+0.841
 cherry+0.801
 Isis+0.799
lining+0.772
ppo+0.766
Neg logit contributions
-0.893
enegger-0.858
igham-0.817
-0.795
 NIC-0.787
Token try
Token ID1949
Feature activation-5.37e-02

Pos logit contributions
+1.384
enegger+1.324
igham+1.259
 NIC+1.247
+1.213
Neg logit contributions
Ore-1.326
 Isis-1.243
 cherry-1.223
lining-1.201
ppo-1.192
Token to
Token ID284
Feature activation-1.72e-01

Pos logit contributions
+0.522
enegger+0.502
igham+0.477
+0.464
 NIC+0.460
Neg logit contributions
Ore-0.501
 cherry-0.476
 Isis-0.475
lining-0.460
ppo-0.457
Token mitigate
Token ID24237
Feature activation-1.77e-01

Pos logit contributions
+1.704
enegger+1.612
igham+1.552
 NIC+1.525
+1.485
Neg logit contributions
Ore-1.568
 Isis-1.457
 cherry-1.433
lining-1.416
ppo-1.399
Token the
Token ID262
Feature activation+7.95e-02

Pos logit contributions
+1.801
enegger+1.737
igham+1.648
 NIC+1.622
+1.603
Neg logit contributions
Ore-1.566
 cherry-1.468
 Isis-1.468
ppo-1.425
lining-1.417
Token impact
Token ID2928
Feature activation+1.31e-01

Pos logit contributions
Ore+0.774
 cherry+0.740
 Isis+0.738
lining+0.714
ppo+0.708
Neg logit contributions
-0.741
enegger-0.710
igham-0.674
-0.655
 NIC-0.647
Token the
Token ID262
Feature activation+1.59e-01

Pos logit contributions
Ore+1.548
 cherry+1.480
 Isis+1.467
lining+1.418
ppo+1.406
Neg logit contributions
-1.805
enegger-1.743
igham-1.657
-1.618
 NIC-1.591
Token cigarette
Token ID17779
Feature activation-2.15e-01

Pos logit contributions
Ore+1.488
 cherry+1.424
 Isis+1.416
lining+1.370
ppo+1.359
Neg logit contributions
-1.531
enegger-1.474
igham-1.399
-1.363
 NIC-1.343
Token lighter
Token ID14871
Feature activation+1.23e-01

Pos logit contributions
+2.138
enegger+2.021
igham+1.956
 NIC+1.908
+1.886
Neg logit contributions
Ore-1.940
 Isis-1.848
 cherry-1.806
lining-1.758
ppo-1.750
Token inside
Token ID2641
Feature activation-7.95e-02

Pos logit contributions
Ore+1.105
 cherry+1.052
 Isis+1.044
lining+1.012
ppo+1.004
Neg logit contributions
-1.228
enegger-1.186
igham-1.126
-1.099
 NIC-1.083
Token the
Token ID262
Feature activation+1.15e-01

Pos logit contributions
+0.807
enegger+0.773
igham+0.736
 NIC+0.719
+0.717
Neg logit contributions
Ore-0.707
 Isis-0.670
 cherry-0.666
lining-0.641
ppo-0.640
Token console
Token ID8624
Feature activation-4.47e-02

Pos logit contributions
Ore+1.052
 cherry+1.004
 Isis+1.000
lining+0.966
ppo+0.958
Neg logit contributions
-1.132
enegger-1.089
igham-1.036
-1.009
 NIC-0.997
Token storage
Token ID6143
Feature activation-2.33e-02

Pos logit contributions
+0.437
enegger+0.419
igham+0.399
+0.387
 NIC+0.386
Neg logit contributions
Ore-0.414
 Isis-0.394
 cherry-0.393
lining-0.380
ppo-0.377
Token area
Token ID1989
Feature activation-3.09e-01

Pos logit contributions
+0.223
enegger+0.213
igham+0.204
 NIC+0.197
+0.197
Neg logit contributions
Ore-0.220
 Isis-0.210
 cherry-0.209
lining-0.202
ppo-0.201
Token (
Token ID357
Feature activation+1.31e-01

Pos logit contributions
+2.887
enegger+2.748
igham+2.632
 NIC+2.560
+2.536
Neg logit contributions
Ore-2.907
 Isis-2.801
 cherry-2.786
lining-2.691
ppo-2.682
Tokenunder
Token ID4625
Feature activation+1.83e-01

Pos logit contributions
Ore+1.169
 cherry+1.105
 Isis+1.099
lining+1.070
ppo+1.059
Neg logit contributions
-1.334
enegger-1.292
igham-1.228
-1.199
 NIC-1.185
Token the
Token ID262
Feature activation-1.43e-01

Pos logit contributions
Ore+1.551
 cherry+1.491
 Isis+1.464
lining+1.443
ppo+1.405
Neg logit contributions
-1.919
enegger-1.849
igham-1.768
-1.731
 NIC-1.691
Token that
Token ID326
Feature activation+2.96e-01

Pos logit contributions
Ore+0.570
 cherry+0.543
 Isis+0.542
lining+0.524
ppo+0.519
Neg logit contributions
-0.620
enegger-0.596
igham-0.567
-0.553
 NIC-0.547
Token you
Token ID345
Feature activation+8.31e-02

Pos logit contributions
Ore+2.618
 cherry+2.553
 Isis+2.519
lining+2.426
ppo+2.399
Neg logit contributions
-2.953
enegger-2.879
igham-2.750
-2.679
 NIC-2.608
Token really
Token ID1107
Feature activation+3.99e-01

Pos logit contributions
Ore+0.761
 cherry+0.722
 Isis+0.721
lining+0.697
ppo+0.691
Neg logit contributions
-0.823
enegger-0.791
igham-0.752
-0.732
 NIC-0.727
Token want
Token ID765
Feature activation-2.22e-02

Pos logit contributions
Ore+3.345
 cherry+3.339
 Isis+3.249
ppo+3.106
lining+3.058
Neg logit contributions
-4.151
enegger-4.025
igham-3.861
-3.854
 Eag-3.634
Token in
Token ID287
Feature activation-7.28e-01

Pos logit contributions
+0.217
enegger+0.208
igham+0.197
+0.192
 NIC+0.191
Neg logit contributions
Ore-0.207
 cherry-0.197
 Isis-0.197
lining-0.190
ppo-0.189
Token your
Token ID534
Feature activation-2.43e-01

Pos logit contributions
+6.564
enegger+6.028
 NIC+5.965
 Eag+5.858
 Ghana+5.728
Neg logit contributions
Ore-6.657
 Isis-6.182
ppo-6.100
 cherry-6.035
lining-5.858
Token collection
Token ID4947
Feature activation-2.20e-01

Pos logit contributions
+2.358
enegger+2.205
 NIC+2.121
igham+2.106
 Eag+2.074
Neg logit contributions
Ore-2.259
 Isis-2.115
 cherry-2.072
lining-2.041
ppo-2.037
Token.
Token ID13
Feature activation+4.17e-01

Pos logit contributions
+2.076
enegger+1.980
igham+1.883
 NIC+1.841
+1.816
Neg logit contributions
Ore-2.095
 Isis-1.982
 cherry-1.972
lining-1.920
ppo-1.917
Token A
Token ID317
Feature activation+3.80e-02

Pos logit contributions
Ore+3.239
 cherry+3.123
 Isis+3.107
lining+2.923
ppo+2.904
Neg logit contributions
-4.602
enegger-4.495
igham-4.346
-4.228
 NIC-4.052
Token great
Token ID1049
Feature activation-2.52e-01

Pos logit contributions
Ore+0.381
 cherry+0.364
 Isis+0.363
lining+0.352
ppo+0.350
Neg logit contributions
-0.343
enegger-0.329
igham-0.311
-0.302
 NIC-0.299
Token example
Token ID1672
Feature activation-3.36e-01

Pos logit contributions
+2.638
enegger+2.525
igham+2.413
 NIC+2.393
 Eag+2.366
Neg logit contributions
Ore-2.135
 Isis-1.969
 cherry-1.928
ppo-1.906
lining-1.893
Token Friends
Token ID14213
Feature activation+2.98e-02

Pos logit contributions
+3.495
enegger+3.327
 Eag+3.176
 NIC+3.159
+3.075
Neg logit contributions
Ore-3.082
 cherry-2.914
lining-2.870
 Isis-2.842
ppo-2.805
Token and
Token ID290
Feature activation+6.44e-01

Pos logit contributions
Ore+0.265
 cherry+0.252
 Isis+0.251
lining+0.242
ppo+0.240
Neg logit contributions
-0.303
enegger-0.292
igham-0.278
-0.271
 NIC-0.269
Token foes
Token ID20822
Feature activation-2.00e-03

Pos logit contributions
Ore+4.956
 Isis+4.901
 cherry+4.898
lining+4.555
ppo+4.490
Neg logit contributions
-6.868
enegger-6.677
igham-6.417
-6.148
 NIC-5.941
Token alike
Token ID12936
Feature activation-1.61e-01

Pos logit contributions
+0.020
enegger+0.019
igham+0.018
+0.017
 NIC+0.017
Neg logit contributions
Ore-0.019
 Isis-0.018
 cherry-0.018
lining-0.017
ppo-0.017
Token hardly
Token ID8941
Feature activation+3.52e-02

Pos logit contributions
+1.529
enegger+1.481
igham+1.394
 NIC+1.358
 Eag+1.339
Neg logit contributions
Ore-1.535
 Isis-1.430
 cherry-1.399
lining-1.378
ppo-1.373
Token mention
Token ID3068
Feature activation-7.52e-01

Pos logit contributions
Ore+0.313
 cherry+0.297
 Isis+0.296
lining+0.286
ppo+0.284
Neg logit contributions
-0.357
enegger-0.344
igham-0.328
-0.319
 NIC-0.316
Token Land
Token ID6379
Feature activation-2.41e-01

Pos logit contributions
+5.747
enegger+5.519
 Eag+5.404
 NIC+5.230
igham+5.197
Neg logit contributions
Ore-7.626
 Isis-7.168
ppo-7.097
 cherry-7.066
lining-6.957
Tokenrie
Token ID5034
Feature activation+4.13e-01

Pos logit contributions
+1.365
enegger+1.279
igham+1.192
 NIC+1.063
+1.032
Neg logit contributions
Ore-3.153
 Isis-3.098
 cherry-3.074
lining-2.975
ppo-2.956
Tokenu
Token ID84
Feature activation-4.21e-01

Pos logit contributions
Ore+1.732
 cherry+1.512
 Isis+1.484
ppo+1.409
lining+1.382
Neg logit contributions
-6.111
enegger-6.049
-5.774
igham-5.763
 NIC-5.702
Token
Token ID447
Feature activation+2.43e-02

Pos logit contributions
+3.715
enegger+3.651
igham+3.413
 Eag+3.303
 NIC+3.271
Neg logit contributions
Ore-4.140
 Isis-3.916
 cherry-3.843
ppo-3.823
lining-3.746
Token
Token ID247
Feature activation+1.55e-01

Pos logit contributions
Ore+0.164
 cherry+0.153
 Isis+0.152
lining+0.145
ppo+0.144
Neg logit contributions
-0.299
enegger-0.290
igham-0.279
-0.273
 NIC-0.271
Token pause
Token ID14985
Feature activation-4.83e-01

Pos logit contributions
+4.463
enegger+4.121
igham+3.995
 NIC+3.932
+3.884
Neg logit contributions
Ore-5.136
 Isis-4.771
ppo-4.759
 cherry-4.705
lining-4.551
Token.
Token ID13
Feature activation+7.19e-02

Pos logit contributions
+4.194
enegger+3.934
igham+3.761
 NIC+3.673
 Eag+3.607
Neg logit contributions
Ore-4.846
 Isis-4.585
 cherry-4.532
ppo-4.446
lining-4.340
Token A
Token ID317
Feature activation-3.07e-01

Pos logit contributions
Ore+0.593
 cherry+0.561
 Isis+0.560
lining+0.538
ppo+0.533
Neg logit contributions
-0.777
enegger-0.750
igham-0.717
-0.699
 NIC-0.693
Token very
Token ID845
Feature activation-2.75e-01

Pos logit contributions
+2.703
enegger+2.514
igham+2.451
+2.374
 NIC+2.360
Neg logit contributions
Ore-3.105
 Isis-2.980
 cherry-2.914
ppo-2.890
lining-2.860
Token long
Token ID890
Feature activation-6.18e-01

Pos logit contributions
+2.541
enegger+2.384
igham+2.310
 NIC+2.254
+2.235
Neg logit contributions
Ore-2.674
 Isis-2.504
ppo-2.489
 cherry-2.474
lining-2.455
Token pause
Token ID14985
Feature activation-8.87e-01

Pos logit contributions
+4.720
enegger+4.376
igham+4.127
 NIC+4.067
+4.057
Neg logit contributions
Ore-6.658
 Isis-6.305
ppo-6.208
 cherry-6.145
lining-6.060
Token.
Token ID13
Feature activation-2.75e-02

Pos logit contributions
+6.922
enegger+6.357
igham+6.019
 NIC+5.853
+5.763
Neg logit contributions
Ore-9.039
 Isis-8.636
 cherry-8.378
ppo-8.251
Bee-8.143
Token During
Token ID5856
Feature activation-1.63e-01

Pos logit contributions
+0.293
enegger+0.282
igham+0.269
+0.263
 NIC+0.263
Neg logit contributions
Ore-0.230
 cherry-0.218
 Isis-0.216
lining-0.210
ppo-0.208
Token that
Token ID326
Feature activation-7.91e-03

Pos logit contributions
+1.594
enegger+1.513
igham+1.459
+1.415
 NIC+1.408
Neg logit contributions
Ore-1.510
 cherry-1.425
 Isis-1.425
ppo-1.376
lining-1.369
Token time
Token ID640
Feature activation-3.30e-01

Pos logit contributions
+0.071
enegger+0.068
igham+0.064
+0.062
 NIC+0.062
Neg logit contributions
Ore-0.080
 cherry-0.076
 Isis-0.076
lining-0.074
ppo-0.073
Token I
Token ID314
Feature activation+6.26e-02

Pos logit contributions
+3.105
enegger+2.946
igham+2.863
+2.768
 NIC+2.763
Neg logit contributions
Ore-3.122
 Isis-2.920
 cherry-2.917
lining-2.839
ppo-2.825
Token.
Token ID13
Feature activation-1.39e-02

Pos logit contributions
+0.528
enegger+0.499
igham+0.473
 NIC+0.462
+0.461
Neg logit contributions
Ore-0.503
 cherry-0.481
 Isis-0.480
lining-0.465
ppo-0.462
Tokenx
Token ID87
Feature activation-9.26e-03

Pos logit contributions
+0.157
enegger+0.150
igham+0.144
+0.141
 NIC+0.140
Neg logit contributions
Ore-0.107
 cherry-0.101
 Isis-0.101
lining-0.097
ppo-0.096
Token.
Token ID13
Feature activation-1.80e-01

Pos logit contributions
+0.091
enegger+0.087
igham+0.082
+0.080
 NIC+0.080
Neg logit contributions
Ore-0.085
 cherry-0.082
 Isis-0.081
lining-0.079
ppo-0.078
Tokenx
Token ID87
Feature activation-1.77e-01

Pos logit contributions
+1.984
enegger+1.844
igham+1.805
+1.724
 Eag+1.723
Neg logit contributions
Ore-1.439
 Isis-1.386
 cherry-1.378
lining-1.313
ppo-1.294
Token.
Token ID13
Feature activation-5.04e-01

Pos logit contributions
+1.704
enegger+1.589
igham+1.517
 NIC+1.465
+1.461
Neg logit contributions
Ore-1.658
 cherry-1.604
 Isis-1.601
lining-1.552
ppo-1.533
Token105
Token ID13348
Feature activation-6.97e-01

Pos logit contributions
+3.693
enegger+3.304
igham+3.225
 Eag+3.025
 NIC+2.930
Neg logit contributions
Ore-5.758
 Isis-5.681
 cherry-5.662
lining-5.441
ppo-5.434
Token 12
Token ID1105
Feature activation-1.61e-01

Pos logit contributions
+6.504
enegger+5.992
 NIC+5.928
 Eag+5.704
 Ghana+5.665
Neg logit contributions
Ore-6.046
 cherry-5.821
lining-5.715
ppo-5.643
 Isis-5.621
Token06
Token ID3312
Feature activation+4.28e-01

Pos logit contributions
+1.708
enegger+1.628
igham+1.549
+1.517
 NIC+1.514
Neg logit contributions
Ore-1.341
 cherry-1.284
 Isis-1.271
lining-1.237
ppo-1.212
Token107
Token ID15982
Feature activation-2.92e-02

Pos logit contributions
Ore+3.953
 Isis+3.732
 cherry+3.705
ppo+3.572
lining+3.546
Neg logit contributions
-4.060
enegger-3.967
igham-3.755
-3.679
 Eag-3.587
Token x
Token ID2124
Feature activation-2.99e-02

Pos logit contributions
+0.271
enegger+0.258
igham+0.244
 NIC+0.238
+0.237
Neg logit contributions
Ore-0.285
 Isis-0.271
 cherry-0.270
lining-0.263
ppo-0.261
Token.
Token ID13
Feature activation+4.75e-02

Pos logit contributions
+0.293
enegger+0.278
igham+0.264
 NIC+0.257
+0.257
Neg logit contributions
Ore-0.276
 cherry-0.263
 Isis-0.262
lining-0.254
ppo-0.252
Token of
Token ID286
Feature activation-4.66e-01

Pos logit contributions
+1.313
enegger+1.257
igham+1.203
 NIC+1.168
+1.161
Neg logit contributions
Ore-1.173
 Isis-1.107
 cherry-1.106
ppo-1.073
lining-1.071
Token multi
Token ID5021
Feature activation-5.36e-02

Pos logit contributions
+4.009
enegger+3.820
igham+3.656
 NIC+3.597
 Eag+3.564
Neg logit contributions
Ore-4.645
ppo-4.353
 Isis-4.346
 cherry-4.299
lining-4.290
Token-
Token ID12
Feature activation-1.81e-01

Pos logit contributions
+0.531
enegger+0.509
igham+0.485
+0.472
 NIC+0.468
Neg logit contributions
Ore-0.491
 cherry-0.467
 Isis-0.466
lining-0.450
ppo-0.448
Tokenstore
Token ID8095
Feature activation-3.08e-01

Pos logit contributions
+1.891
enegger+1.796
igham+1.733
 NIC+1.671
+1.666
Neg logit contributions
Ore-1.533
 Isis-1.473
 cherry-1.467
ppo-1.412
lining-1.386
Tokeny
Token ID88
Feature activation-6.23e-01

Pos logit contributions
+3.074
enegger+2.906
igham+2.839
 NIC+2.721
+2.681
Neg logit contributions
Ore-2.728
 Isis-2.596
 cherry-2.581
lining-2.493
ppo-2.474
Token residential
Token ID12420
Feature activation-9.28e-01

Pos logit contributions
+5.155
enegger+4.953
igham+4.638
 NIC+4.577
 Eag+4.501
Neg logit contributions
Ore-6.261
 Isis-5.907
ppo-5.813
 cherry-5.808
lining-5.787
Token and
Token ID290
Feature activation-1.73e-01

Pos logit contributions
+7.319
 NIC+6.875
enegger+6.853
igham+6.464
 Eag+6.460
Neg logit contributions
Ore-8.841
ppo-8.261
Cola-8.164
lining-8.101
 Isis-8.098
Token commercial
Token ID5068
Feature activation-1.12e+00

Pos logit contributions
+1.661
enegger+1.600
igham+1.523
 NIC+1.510
+1.469
Neg logit contributions
Ore-1.603
 Isis-1.509
 cherry-1.495
lining-1.471
ppo-1.467
Token buildings
Token ID6832
Feature activation-1.30e-01

Pos logit contributions
+8.234
 NIC+7.822
enegger+7.809
igham+7.379
 Eag+7.360
Neg logit contributions
Ore-10.348
ppo-9.903
 Isis-9.799
Cola-9.721
lining-9.705
Token.
Token ID13
Feature activation-4.95e-01

Pos logit contributions
+1.253
enegger+1.201
igham+1.140
+1.107
 NIC+1.106
Neg logit contributions
Ore-1.221
 cherry-1.159
 Isis-1.155
ppo-1.118
lining-1.115
Token
Token ID198
Feature activation-1.62e-01

Pos logit contributions
+4.793
enegger+4.524
 NIC+4.387
 Eag+4.305
+4.282
Neg logit contributions
Ore-4.317
 cherry-4.183
 Isis-4.145
lining-4.109
ppo-4.055
Token.
Token ID13
Feature activation-9.55e-02

Pos logit contributions
+3.920
enegger+3.753
igham+3.588
 NIC+3.440
 Eag+3.426
Neg logit contributions
Ore-4.258
 Isis-4.048
 cherry-4.008
ppo-3.894
lining-3.884
Token He
Token ID679
Feature activation+8.91e-02

Pos logit contributions
+0.981
enegger+0.938
igham+0.893
+0.872
 NIC+0.871
Neg logit contributions
Ore-0.837
 cherry-0.794
 Isis-0.791
lining-0.769
ppo-0.762
Token is
Token ID318
Feature activation+1.91e-01

Pos logit contributions
Ore+0.868
 cherry+0.830
 Isis+0.827
lining+0.801
ppo+0.795
Neg logit contributions
-0.829
enegger-0.795
igham-0.754
-0.733
 NIC-0.726
Token one
Token ID530
Feature activation+1.85e-01

Pos logit contributions
Ore+1.603
 cherry+1.544
 Isis+1.526
lining+1.471
ppo+1.446
Neg logit contributions
-2.033
enegger-1.965
igham-1.882
-1.841
 NIC-1.808
Token of
Token ID286
Feature activation-3.83e-01

Pos logit contributions
Ore+1.520
 cherry+1.461
 Isis+1.442
lining+1.395
ppo+1.363
Neg logit contributions
-1.994
enegger-1.926
igham-1.832
-1.797
 NIC-1.767
Token the
Token ID262
Feature activation-6.85e-01

Pos logit contributions
+3.506
enegger+3.294
igham+3.119
 NIC+3.081
 Eag+3.068
Neg logit contributions
Ore-3.733
 Isis-3.472
 cherry-3.421
ppo-3.421
lining-3.353
Token few
Token ID1178
Feature activation-1.26e-01

Pos logit contributions
+5.793
enegger+5.255
 NIC+5.210
 Eag+5.124
igham+5.034
Neg logit contributions
Ore-6.868
ppo-6.348
 Isis-6.283
lining-6.048
Bee-6.034
Token,
Token ID11
Feature activation+2.11e-01

Pos logit contributions
+1.175
enegger+1.116
igham+1.062
 NIC+1.034
 Eag+1.023
Neg logit contributions
Ore-1.224
 Isis-1.160
 cherry-1.146
ppo-1.124
lining-1.118
Token unfortunately
Token ID12716
Feature activation+2.20e-01

Pos logit contributions
Ore+1.970
 cherry+1.911
 Isis+1.888
lining+1.822
ppo+1.792
Neg logit contributions
-2.034
enegger-1.965
igham-1.856
-1.822
 NIC-1.784
Token forgotten
Token ID11564
Feature activation-6.90e-02

Pos logit contributions
Ore+1.876
 cherry+1.817
 Isis+1.791
lining+1.735
ppo+1.700
Neg logit contributions
-2.286
enegger-2.225
igham-2.106
-2.068
 NIC-2.030
Token today
Token ID1909
Feature activation-2.77e-01

Pos logit contributions
+0.662
enegger+0.633
igham+0.602
 NIC+0.586
+0.583
Neg logit contributions
Ore-0.651
 Isis-0.616
 cherry-0.615
ppo-0.597
lining-0.596