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

    Neuronpedia

    INDEX
    Explanations

    instances of proper nouns and numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acer
    -0.18
    ests
    -0.15
    sez
    -0.15
     fitte
    -0.15
    linger
    -0.15
    ¹
    -0.14
    canf
    -0.14
    ález
    -0.14
    pts
    -0.14
    fits
    -0.14
    POSITIVE LOGITS
    ivery
    0.16
     Cabin
    0.15
    _Parms
    0.14
    {})
    0.14
    ĶåĽŀ
    0.14
    160
    0.14
     Mans
    0.14
    irtual
    0.14
     Engl
    0.14
    uitka
    0.14
    Act Density 0.006%

    No Known Activations