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

    Neuronpedia

    INDEX
    Explanations

    names, especially emphasizing "Vic"

    oai_token-act-pair · gpt-3.5-turbo

    names and references to a specific individual or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.83
    xual
    -0.80
    tenance
    -0.78
    manship
    -0.76
    Ô
    -0.75
    landish
    -0.72
    SpaceEngineers
    -0.72
     EntityItem
    -0.70
    spread
    -0.69
    dress
    -0.68
    POSITIVE LOGITS
    arious
    1.13
    inity
    1.04
    isions
    1.02
    entric
    0.99
    abulary
    0.93
    ente
    0.91
    ient
    0.90
    ision
    0.89
    iple
    0.89
    imated
    0.89
    Act Density 0.014%

    No Known Activations