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

    Neuronpedia

    INDEX
    Explanations

    terms related to sexual matters or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual misconduct and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dispatch
    -0.93
    ALS
    -0.79
     Breaker
    -0.78
    iard
    -0.78
    tower
    -0.78
     Glob
    -0.72
    GV
    -0.72
    reads
    -0.71
    ills
    -0.71
    IVERS
    -0.71
    POSITIVE LOGITS
     intercourse
    1.20
    ized
    1.03
    ity
    1.02
     assault
    1.02
    ization
    0.99
    izing
    0.94
     harassment
    0.94
     ensl
    0.92
     misconduct
    0.92
    ised
    0.91
    Act Density 0.023%

    No Known Activations