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

    Neuronpedia

    INDEX
    Explanations

    numerical values mentioned or related to body parts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ingham
    -0.88
    ajo
    -0.75
    èĢħ
    -0.73
    Kings
    -0.73
    eele
    -0.72
     Integrity
    -0.70
     Highlights
    -0.69
     Quote
    -0.69
     Preservation
    -0.69
     Procedures
    -0.68
    POSITIVE LOGITS
    ishly
    1.02
    ously
    0.84
    emic
    0.83
    emonic
    0.80
    antically
    0.79
    creen
    0.78
    istine
    0.78
    ingly
    0.77
     inducing
    0.77
    VIDIA
    0.77
    Act Density 0.876%

    No Known Activations