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

    Neuronpedia

    INDEX
    Explanations

    references to curses or negative supernatural influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    curse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ppon
    -0.47
    탤
    -0.46
    ◀
    -0.46
    OPA
    -0.42
     برانيه
    -0.41
    ymce
    -0.41
    rca
    -0.40
     bof
    -0.40
    Info
    -0.39
    eseorang
    -0.39
    POSITIVE LOGITS
     curse
    1.90
    curse
    1.83
     Curse
    1.70
    Curse
    1.70
     cursed
    1.58
     curses
    1.52
    cursed
    1.47
    Cursed
    1.41
     Cursed
    1.38
     cursing
    1.27
    Act Density 0.006%

    No Known Activations