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

    Neuronpedia

    INDEX
    Explanations

    numbers and their contextual usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McCabe
    -0.17
    enet
    -0.15
    PU
    -0.15
    fir
    -0.15
    este
    -0.15
    amina
    -0.14
    ÑĦоÑĢми
    -0.14
     ÑĦаÑĢ
    -0.14
    _DESTROY
    -0.14
    ullo
    -0.14
    POSITIVE LOGITS
    lez
    0.15
     Mal
    0.15
    oth
    0.15
     exp
    0.15
    mesinin
    0.14
     overall
    0.14
    åı°
    0.14
    га
    0.14
    mal
    0.14
    947
    0.14
    Act Density 0.000%

    No Known Activations