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

    Neuronpedia

    INDEX
    Explanations

    specific references to authors or names associated with research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izard
    -0.17
    peror
    -0.16
    leared
    -0.16
    itoris
    -0.16
    oje
    -0.15
    Ñİн
    -0.15
    eph
    -0.14
    UTION
    -0.14
    hte
    -0.14
    ë¦Ń
    -0.14
    POSITIVE LOGITS
    er
    0.18
    oned
    0.18
    igan
    0.18
    t
    0.17
    stown
    0.17
    erot
    0.16
    κε
    0.16
    ÙĨج
    0.15
    igans
    0.15
    alez
    0.14
    Act Density 0.026%

    No Known Activations