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

    Neuronpedia

    INDEX
    Explanations

    @ symbols often used in programming or social media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inar
    -0.16
    ÑĩÑĥк
    -0.16
    hazi
    -0.15
    .obtain
    -0.15
    s
    -0.15
    INDEX
    -0.14
    ariant
    -0.14
    _uniform
    -0.14
    resse
    -0.14
    _IMPL
    -0.13
    POSITIVE LOGITS
    neau
    0.15
    iets
    0.15
    etten
    0.15
    (#)
    0.15
    esson
    0.15
    ehler
    0.15
    Dash
    0.14
    vÄĽ
    0.14
    hone
    0.13
    QP
    0.13
    Act Density 0.024%

    No Known Activations