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

    Neuronpedia

    INDEX
    Explanations

    the word "cease" or phrases related to stopping or discontinuing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stopping or ending actions or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rium
    -0.86
    ramid
    -0.85
    aceae
    -0.78
    hetti
    -0.76
    ammy
    -0.76
    raviolet
    -0.73
    assium
    -0.72
    aries
    -0.72
    arse
    -0.72
    oos
    -0.71
    POSITIVE LOGITS
    rences
    0.82
     hostilities
    0.78
    cedes
    0.77
     seiz
    0.74
     peacefully
    0.73
    plin
    0.73
    fires
    0.73
    motion
    0.73
     belie
    0.71
    lement
    0.71
    Act Density 0.023%

    No Known Activations