INDEX
Explanations
occurrences of the word "shock" and its variations
New Auto-Interp
Negative Logits
fty
-0.19
иÑģк
-0.16
ake
-0.15
hti
-0.15
nty
-0.14
stvo
-0.14
iac
-0.14
кин
-0.14
ighth
-0.14
sao
-0.14
POSITIVE LOGITS
ingly
0.46
wave
0.34
waves
0.32
tober
0.29
absor
0.28
waves
0.26
Wave
0.23
wave
0.22
Waves
0.20
ument
0.19
Activations Density 0.010%