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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms related to organizations and certifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umat
    -0.15
    owl
    -0.15
    _serialize
    -0.14
    iale
    -0.14
    atial
    -0.13
    ertas
    -0.13
    lsen
    -0.13
     Bowman
    -0.13
    esium
    -0.13
    amiento
    -0.13
    POSITIVE LOGITS
    igy
    0.16
    chied
    0.16
    usted
    0.15
    el
    0.15
    amet
    0.14
    amarin
    0.14
    auss
    0.14
    yb
    0.14
     gros
    0.14
     Learned
    0.14
    Act Density 0.250%

    No Known Activations