INDEX
Explanations
references to ongoing activities or events
New Auto-Interp
Negative Logits
oods
-0.15
ĨĴ
-0.14
alph
-0.14
-*-č↵
-0.13
ä½ĵ
-0.13
Scaling
-0.13
locale
-0.13
etter
-0.13
iac
-0.12
orton
-0.12
POSITIVE LOGITS
happening
0.51
going
0.45
ongoing
0.42
going
0.38
-going
0.38
Going
0.37
occurring
0.35
Going
0.35
happen
0.33
happens
0.32
Activations Density 0.221%