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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating examples or instances of something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    antage
    -0.70
    ribution
    -0.68
    ombat
    -0.67
    emi
    -0.66
    ushima
    -0.65
    dollar
    -0.63
    rition
    -0.61
    ogun
    -0.61
    olitical
    -0.61
    emale
    -0.60
    POSITIVE LOGITS
    ties
    0.71
    cond
    0.66
    worldly
    0.63
    minded
    0.60
     Osw
    0.60
     embodiments
    0.59
    things
    0.57
     namely
    0.56
     EntityItem
    0.55
    odon
    0.54
    Act Density 4.344%

    No Known Activations