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

    Neuronpedia

    INDEX
    Explanations

    mentions of geographical locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.75
    antz
    -0.75
    ivas
    -0.71
    verbal
    -0.70
    ixtape
    -0.68
    agascar
    -0.67
    BIP
    -0.66
    irus
    -0.65
    wolves
    -0.65
    argument
    -0.65
    POSITIVE LOGITS
     confines
    1.16
     vicinity
    1.02
     absence
    0.97
     stead
    0.94
     manner
    0.91
     basement
    0.89
     courtyard
    0.89
     guise
    0.88
     sandbox
    0.86
     evenings
    0.86
    Act Density 0.299%

    No Known Activations