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

    Neuronpedia

    INDEX
    Explanations

    significant nouns or phrases that denote concepts or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rsa
    -0.15
    _stream
    -0.15
    arching
    -0.14
    Worksheet
    -0.14
    inds
    -0.14
    flu
    -0.14
    uz
    -0.13
    STREAM
    -0.13
    indo
    -0.13
    endo
    -0.13
    POSITIVE LOGITS
     deb
    0.22
    ibus
    0.16
    auer
    0.15
    ä½
    0.15
    Ïģαν
    0.15
    Universal
    0.15
     Sund
    0.15
     Fry
    0.15
    abella
    0.14
    ubb
    0.14
    Act Density 0.001%

    No Known Activations