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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to automation and automated systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    off
    -0.15
    _utilities
    -0.15
    ently
    -0.14
    tram
    -0.14
    .getElements
    -0.14
    omba
    -0.14
    amar
    -0.14
    atan
    -0.14
     Popular
    -0.14
    popular
    -0.14
    POSITIVE LOGITS
    erture
    0.15
    641
    0.15
    abei
    0.14
    eldorf
    0.14
    eza
    0.14
    ANJI
    0.14
     Archie
    0.14
    ëłµ
    0.13
    anz
    0.13
    raits
    0.13
    Act Density 0.002%

    No Known Activations