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

    Neuronpedia

    INDEX
    Explanations

    references to superheroes or heroic figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Hero" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rup
    -0.84
    aeda
    -0.78
     Debor
    -0.72
    gdala
    -0.71
    creen
    -0.70
    nce
    -0.69
    mosp
    -0.69
    cone
    -0.67
    rea
    -0.67
    ORK
    -0.66
    POSITIVE LOGITS
    ic
    0.79
    osate
    0.76
    inic
    0.74
    Hero
    0.73
     Girls
    0.70
    ipeg
    0.69
     Acad
    0.68
    inous
    0.68
    inical
    0.68
    vernment
    0.67
    Act Density 0.030%

    No Known Activations