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

    Neuronpedia

    INDEX
    Explanations

    references to items that are incomplete or unfinished

    oai_token-act-pair · gpt-3.5-turbo

    terms related to unreleased content or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.82
    uyomi
    -0.79
    ospace
    -0.66
    hetti
    -0.65
     Gab
    -0.64
     Bernstein
    -0.63
    ortium
    -0.62
    anwhile
    -0.62
    =-=-=-=-=-=-=-=-
    -0.62
     Rams
    -0.62
    POSITIVE LOGITS
    leased
    1.20
    achable
    1.16
    ason
    0.96
    ached
    0.94
    itled
    0.93
    ported
    0.93
    agan
    0.88
    peat
    0.86
    vered
    0.85
    ired
    0.83
    Act Density 0.005%

    No Known Activations