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

    Neuronpedia

    INDEX
    Explanations

    references to women and their roles or representation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (crate
    -0.15
    ennes
    -0.15
    ัà¸ģษ
    -0.14
    vertise
    -0.14
    leton
    -0.14
    lesia
    -0.14
    cházet
    -0.14
     mimo
    -0.14
    _least
    -0.13
    ÏĦαι
    -0.13
    POSITIVE LOGITS
    Ticker
    0.16
    ulet
    0.16
    eca
    0.14
    panion
    0.14
    arden
    0.14
    zell
    0.14
    uada
    0.14
    oir
    0.14
     vox
    0.14
    terrain
    0.13
    Act Density 0.067%

    No Known Activations