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

    Neuronpedia

    INDEX
    Explanations

    personal statements or expressions of identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Brains
    -0.15
    eck
    -0.14
    LEM
    -0.14
    MMdd
    -0.14
    /std
    -0.13
    impl
    -0.13
    illy
    -0.13
    arat
    -0.13
     Leather
    -0.13
    260
    -0.13
    POSITIVE LOGITS
    urat
    0.16
    _FOR
    0.16
     Gust
    0.16
     experienced
    0.15
    ocaly
    0.15
    ukan
    0.15
    ipers
    0.14
    ghost
    0.14
    Äįet
    0.14
    رØŃ
    0.14
    Act Density 0.273%

    No Known Activations