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

    Neuronpedia

    INDEX
    Explanations

    mentions of sexual harassment and abuse

    oai_token-act-pair · gpt-3.5-turbo

    instances of sexual misconduct and harassment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.87
    helm
    -0.72
     mir
    -0.69
    tle
    -0.69
    sonian
    -0.68
    omsday
    -0.66
    MSN
    -0.66
    #$
    -0.65
    JV
    -0.65
    aceae
    -0.64
    POSITIVE LOGITS
     underage
    0.94
     workplace
    0.87
     minors
    0.87
     interpersonal
    0.81
     classmates
    0.78
     perpetrated
    0.75
     intern
    0.74
     Palest
    0.71
     classmate
    0.71
     adolescence
    0.70
    Act Density 0.456%

    No Known Activations