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

    Neuronpedia

    INDEX
    Explanations

    terms related to sexual misconduct and criminal behavior, especially involving minors

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual abuse and misconduct involving minors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥķãĤ©
    -0.82
    fen
    -0.72
    addons
    -0.71
    querque
    -0.69
    cation
    -0.68
    £ı
    -0.68
    ãĤ´ãĥ³
    -0.67
    mort
    -0.67
    alg
    -0.66
    ovation
    -0.64
    POSITIVE LOGITS
     underage
    1.60
     minors
    1.40
     girls
    1.19
     females
    1.17
     prostitutes
    1.15
     teenage
    1.12
     prostitute
    1.12
     female
    1.11
    girlfriend
    1.10
     women
    1.05
    Act Density 0.235%

    No Known Activations