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

    Neuronpedia

    INDEX
    Explanations

    occurrences of single or multiple digit numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.18
    zon
    -0.17
     Elias
    -0.14
    olla
    -0.14
    .Orientation
    -0.14
    /apps
    -0.13
    tel
    -0.13
    essian
    -0.13
    ignon
    -0.13
    urchase
    -0.13
    POSITIVE LOGITS
    .WinForms
    0.16
    omat
    0.16
    ç±
    0.15
    kus
    0.14
    erb
    0.14
    ometr
    0.14
    ensem
    0.14
    vise
    0.14
    ctrine
    0.14
    ecko
    0.14
    Act Density 0.002%

    No Known Activations