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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "kind" in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to different types or kinds of situations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Balls
    -0.69
    BuyableInstoreAndOnline
    -0.68
     Crush
    -0.67
     sher
    -0.65
    biz
    -0.64
    nut
    -0.63
     Doors
    -0.63
     Bars
    -0.63
    WOR
    -0.62
    INA
    -0.62
    POSITIVE LOGITS
    ilege
    0.89
    ileged
    0.87
    lihood
    0.84
    ebin
    0.76
    folio
    0.75
    rait
    0.72
    etting
    0.68
    isphere
    0.68
    ativity
    0.66
    ifier
    0.65
    Act Density 0.030%

    No Known Activations