Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to hands or hand-related actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    BIL
    -1.20
    hya
    -1.11
    è¦ļéĨĴ
    -1.08
     Flavoring
    -1.07
    anut
    -1.06
    natureconservancy
    -1.05
     Cosponsors
    -1.03
    ashtra
    -1.02
    oult
    -1.01
    BAT
    -1.00
    POSITIVE LOGITS
     strokes
    0.95
     circles
    0.94
     flank
    0.91
     counsel
    0.89
    hander
    0.88
     Cullen
    0.86
     populism
    0.86
     Lug
    0.86
     slic
    0.86
     eject
    0.85
    Act Density 0.446%

    No Known Activations