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

    Neuronpedia

    INDEX
    Explanations

    words related to sexual misconduct and criminal behavior

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual offenses against children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    frames
    -0.74
    Condition
    -0.69
    pring
    -0.68
     antioxid
    -0.67
    NPR
    -0.64
     Solitaire
    -0.64
     Runner
    -0.63
    IFE
    -0.62
    soType
    -0.62
    PN
    -0.62
    POSITIVE LOGITS
     pedoph
    1.04
     mol
    1.01
    ophile
    0.97
    estation
    0.91
    osexual
    0.90
    riages
    0.89
    olester
    0.86
    eties
    0.84
    ocide
    0.83
    Sexual
    0.81
    Act Density 0.024%

    No Known Activations