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

    Neuronpedia

    INDEX
    Explanations

    references to sexual assault

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual assault and related crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issue
    -0.81
    clips
    -0.81
    immune
    -0.75
    issues
    -0.75
    hire
    -0.72
    etheless
    -0.72
    rek
    -0.72
    edition
    -0.70
    lore
    -0.70
    fare
    -0.69
    POSITIVE LOGITS
     him
    0.87
     them
    0.73
     unsuspecting
    0.72
     prostitutes
    0.72
     himself
    0.70
     innoc
    0.67
     raping
    0.67
     Samantha
    0.65
     innocent
    0.65
     aggressively
    0.65
    Act Density 0.083%

    No Known Activations