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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to various fields and disciplines

    oai_token-act-pair · gpt-3.5-turbo

    specific names, terms, and categories related to scientific or technological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.76
     confir
    -0.70
     tempted
    -0.63
     destro
    -0.63
     inclined
    -0.62
    olulu
    -0.61
    undai
    -0.59
    ebus
    -0.59
    anwhile
    -0.58
    itially
    -0.57
    POSITIVE LOGITS
    "—
    0.76
    MAP
    0.60
    ",
    0.59
    LOCK
    0.59
    ")
    0.58
    "
    0.58
    Dad
    0.57
     Bastard
    0.56
     Objects
    0.56
    Dog
    0.55
    Act Density 0.453%

    No Known Activations