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

    Neuronpedia

    INDEX
    Explanations

    words related to construction and creation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to construction and creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stretched
    -0.65
    advert
    -0.63
     heaviest
    -0.63
     muted
    -0.60
     bum
    -0.60
    treated
    -0.59
    eger
    -0.57
    quickShipAvailable
    -0.57
     hars
    -0.56
    aminer
    -0.55
    POSITIVE LOGITS
    enstein
    0.65
     anew
    0.64
    ias
    0.64
    -+-+
    0.63
     someday
    0.61
     ASAP
    0.61
    safe
    0.60
     yourself
    0.60
    iola
    0.60
     Guant
    0.59
    Act Density 0.669%

    No Known Activations