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

    Neuronpedia

    INDEX
    Explanations

    mentions of sexual offenses or misconduct

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual offenses and misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bley
    -0.76
    IVERS
    -0.73
     Glob
    -0.70
    quickShipAvailable
    -0.69
     Converted
    -0.68
    oday
    -0.65
    Dispatch
    -0.64
    jon
    -0.63
     Blizz
    -0.62
    ernels
    -0.61
    POSITIVE LOGITS
     assault
    1.32
     harassment
    1.26
     assaults
    1.17
     misconduct
    1.17
     abuse
    1.10
     intercourse
    1.09
     predator
    1.02
     exploitation
    1.02
     predators
    1.01
     Assault
    1.01
    Act Density 0.037%

    No Known Activations