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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and phrases indicating titles or named entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nez
    -0.18
    ilmington
    -0.15
    ackbar
    -0.15
    _TLS
    -0.15
     TRACE
    -0.14
    CRET
    -0.14
     Chow
    -0.14
    VERBOSE
    -0.14
     Barry
    -0.14
    ion
    -0.13
    POSITIVE LOGITS
    ruc
    0.17
    usage
    0.17
    -buffer
    0.15
    endum
    0.15
     burn
    0.15
    Others
    0.15
    Ru
    0.15
    ÄŁan
    0.15
    ĭ
    0.15
    øy
    0.14
    Act Density 0.002%

    No Known Activations