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

    Neuronpedia

    INDEX
    Explanations

    various tags or categories denoting specific topics or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SystemService
    -0.18
    icari
    -0.17
    achu
    -0.16
    械
    -0.16
    Ñĥп
    -0.15
    vsp
    -0.14
    -CS
    -0.14
    EDIUM
    -0.14
    tober
    -0.14
    elho
    -0.14
    POSITIVE LOGITS
    ĶåĽŀ
    0.16
     Mil
    0.15
    ç©
    0.15
    esar
    0.15
     hungry
    0.14
     Killing
    0.14
     OC
    0.14
     Hutch
    0.13
    _extensions
    0.13
    à¹īà¸Ńà¸Ļ
    0.13
    Act Density 0.000%

    No Known Activations