INDEX
Explanations
the word "mock"
references to "mock" and related terms used in a comedic or satirical context
New Auto-Interp
Negative Logits
conserv
-0.81
cles
-0.78
aria
-0.76
arians
-0.69
conservation
-0.69
Conservation
-0.69
division
-0.68
travel
-0.67
20439
-0.67
responsible
-0.66
POSITIVE LOGITS
mock
3.92
Mock
3.64
mocked
2.08
mocking
2.05
mockery
1.43
ridicule
1.21
faux
1.20
simulated
1.17
parody
1.11
spoof
1.09
Activations Density 0.018%