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

    Neuronpedia

    INDEX
    Explanations

    references to news outlets or media sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wyn
    -0.15
    abar
    -0.15
    aram
    -0.14
    ÑĪе
    -0.14
    vale
    -0.14
    cente
    -0.14
    aran
    -0.13
    oses
    -0.13
    _HS
    -0.13
    Ale
    -0.13
    POSITIVE LOGITS
    grav
    0.16
    æ¥Ń
    0.16
    avi
    0.15
    attles
    0.15
    Scalars
    0.14
    ELLOW
    0.14
    /tty
    0.14
     svaz
    0.14
    nitÅĻ
    0.13
    anner
    0.13
    Act Density 0.138%

    No Known Activations