INDEX
Explanations
The neuron activates on mentions of odor and related descriptive adjectives (i.e. references to a chemical’s smell).
New Auto-Interp
Negative Logits
CD
-0.07
Bottom
-0.07
inv
-0.06
K
-0.06
actions
-0.06
urons
-0.06
CD
-0.06
Resume
-0.06
Ded
-0.06
Ea
-0.06
POSITIVE LOGITS
_timeline
0.07
niên
0.07
đường
0.07
tgl
0.06
-me
0.06
wield
0.06
Neon
0.06
Swansea
0.06
ANGO
0.06
Class
0.06
Activations Density 0.006%