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

    Neuronpedia

    INDEX
    Explanations

    references to hands and sides of the body

    oai_token-act-pair · gpt-3.5-turbo

    references to hands and their associated actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hya
    -0.94
    usky
    -0.80
    sav
    -0.79
    hran
    -0.78
    ynt
    -0.77
    Weather
    -0.76
    DragonMagazine
    -0.75
    Bir
    -0.75
    Sav
    -0.73
    earable
    -0.72
    POSITIVE LOGITS
     circles
    0.66
     flank
    0.66
     centimeters
    0.64
     dime
    0.63
     volume
    0.63
    ACTED
    0.62
     latitude
    0.62
     gou
    0.62
     Makoto
    0.61
     slic
    0.61
    Act Density 0.078%

    No Known Activations