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

    Neuronpedia

    INDEX
    Explanations

    references to various types of identification numbers related to personal information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    виж
    -0.17
    cla
    -0.16
     div
    -0.15
     Pets
    -0.15
    à¥ĩय
    -0.15
    oucher
    -0.14
    _tC
    -0.14
    _mE
    -0.14
    ige
    -0.14
    agnar
    -0.14
    POSITIVE LOGITS
    dni
    0.16
    es
    0.15
    opher
    0.15
    (es
    0.15
    Ìĥ
    0.15
     Shine
    0.15
    linger
    0.14
    esh
    0.14
    754
    0.14
    AE
    0.14
    Act Density 0.010%

    No Known Activations