INDEX
Explanations
expressions of surprise or excitement typically involving the phrase "Oh my god."
expressions of exclamation or surprise
New Auto-Interp
Negative Logits
BILITIES
-0.81
eele
-0.76
alion
-0.73
orea
-0.72
udeb
-0.68
actionDate
-0.65
Fed
-0.65
olutions
-0.63
aign
-0.63
ertain
-0.63
POSITIVE LOGITS
Witness
0.68
asca
0.64
deaf
0.61
gasp
0.58
warts
0.58
Watt
0.57
shudder
0.56
stagger
0.55
witnesses
0.55
mute
0.55
Activations Density 0.060%