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

    Neuronpedia

    INDEX
    Explanations

    words related to sexual misconduct and assault

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual misconduct and abuse allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AY
    -0.79
    IR
    -0.75
    IVERS
    -0.74
    REC
    -0.71
    REL
    -0.70
    Ability
    -0.70
     tune
    -0.68
     Advent
    -0.67
    Hyper
    -0.66
    Basic
    -0.66
    POSITIVE LOGITS
     allegations
    1.06
     grop
    1.03
     rape
    1.00
     accuser
    0.97
    Sexual
    0.95
     raping
    0.95
     sexually
    0.92
     grooming
    0.92
     mol
    0.91
     lewd
    0.88
    Act Density 0.122%

    No Known Activations