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

    Neuronpedia

    INDEX
    Explanations

    names related to high-profile scandals and legal cases

    oai_token-act-pair · gpt-3.5-turbo

    references to Harvey Weinstein and his associated controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phis
    -0.92
     sovere
    -0.83
    istically
    -0.80
    asper
    -0.79
    ĪĴ
    -0.78
    nesota
    -0.78
    alist
    -0.75
    ionics
    -0.74
    usterity
    -0.73
    eanor
    -0.71
    POSITIVE LOGITS
     Weinstein
    1.37
     Bros
    0.89
    enthal
    0.83
     raped
    0.80
    wald
    0.77
     Tarant
    0.75
     allegations
    0.72
     Hoffman
    0.72
    fell
    0.67
    gren
    0.67
    Act Density 0.014%

    No Known Activations