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

    Neuronpedia

    INDEX
    Explanations

    words related to taking action or making progress

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    blance
    -0.69
    creen
    -0.67
    brates
    -0.65
    vironment
    -0.64
     Millennium
    -0.63
    brate
    -0.63
    baum
    -0.61
    uates
    -0.61
    576
    -0.60
    yip
    -0.60
    POSITIVE LOGITS
    regn
    1.46
    romptu
    1.44
    otent
    1.40
    ulsive
    1.35
    ossibly
    1.34
    urities
    1.29
    orters
    1.22
    assion
    1.22
    ressive
    1.18
    ressing
    1.17
    Act Density 0.013%

    No Known Activations