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

    Neuronpedia

    INDEX
    Explanations

    incidents involving violent actions or crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    remen
    -0.18
    indi
    -0.16
    orden
    -0.15
    atat
    -0.15
    ServletResponse
    -0.15
    ÑĸнÑĮ
    -0.15
    аном
    -0.14
    ertiary
    -0.14
     ngh
    -0.14
    ãĥ¬ãĥ¼
    -0.14
    POSITIVE LOGITS
    Narr
    0.19
     narr
    0.16
     Narr
    0.16
    ÛĮÙĨÙĩ
    0.16
     Intelligence
    0.15
    BILE
    0.15
     Highlander
    0.15
     Civ
    0.15
     Stark
    0.15
    åı¦
    0.14
    Act Density 0.034%

    No Known Activations