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

    Neuronpedia

    INDEX
    Explanations

    confrontational language related to challenges or threats

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

    "challenge" or "duel"

    np_acts-logits-general · gemini-2.0-flash

    challenge or duel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.61
    AccessorTable
    -0.57
    insegna
    -0.56
    SharedCtor
    -0.54
    AddHtmlAttribute
    -0.52
    kreis
    -0.52
    erschutz
    -0.52
     klucz
    -0.49
    effetto
    -0.49
     perkembangan
    -0.48
    POSITIVE LOGITS
     challenge
    0.97
    challenge
    0.85
     challenged
    0.84
    Challenge
    0.83
     Challenge
    0.82
     duel
    0.78
     challenger
    0.78
     CHALLENGE
    0.77
     challeng
    0.74
     desafi
    0.73
    Act Density 0.212%

    No Known Activations