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

    Neuronpedia

    INDEX
    Explanations

    words related to fire or physical locations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quality and authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rush
    -0.65
     Seym
    -0.64
     Spy
    -0.62
     Prescott
    -0.62
    Snake
    -0.62
     Nanto
    -0.61
    pta
    -0.61
    KT
    -0.60
    kson
    -0.60
    enza
    -0.59
    POSITIVE LOGITS
     bon
    1.04
     fide
    1.00
    uit
    0.94
    iously
    0.93
    bon
    0.89
    eless
    0.87
    nets
    0.85
    bat
    0.81
    ificial
    0.81
    uin
    0.81
    Act Density 0.015%

    No Known Activations