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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals and discussions related to activism and opinions, especially in the context of online harassment and cyber violence

    oai_token-act-pair · gpt-3.5-turbo

    mentions of women and discussions about their roles or opinions in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewitness
    -0.88
    externalActionCode
    -0.83
     Paso
    -0.81
    dayName
    -0.79
    iscal
    -0.79
    hiba
    -0.78
    �
    -0.77
    ciples
    -0.73
    arbon
    -0.73
    rolet
    -0.72
    POSITIVE LOGITS
     Gamergate
    1.90
     GamerGate
    1.88
     Yiannopoulos
    1.72
     Milo
    1.65
    Gamer
    1.60
     misogyn
    1.57
     Gawker
    1.48
     Feminist
    1.47
     feminists
    1.47
     Zoe
    1.43
    Act Density 0.836%

    No Known Activations