INDEX
Explanations
The neuron fires on words (adjectives or adverbs) conveying urgency or a pressing need.
New Auto-Interp
Negative Logits
682
-0.07
Matthews
-0.07
foo
-0.06
feather
-0.06
scissors
-0.06
Beau
-0.06
glitch
-0.06
bachelor
-0.06
stell
-0.06
sheep
-0.06
POSITIVE LOGITS
urging
0.13
urgent
0.12
urged
0.10
urges
0.10
urgency
0.10
Urg
0.10
urge
0.09
utmost
0.08
употреб
0.08
urgently
0.08
Activations Density 0.005%