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

    Neuronpedia

    INDEX
    Explanations

    references to controversial films and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hairst
    -0.15
     frags
    -0.15
    isor
    -0.14
    etooth
    -0.14
    afen
    -0.14
    yntax
    -0.14
    argon
    -0.14
    ocide
    -0.14
    LookAndFeel
    -0.14
     bullshit
    -0.13
    POSITIVE LOGITS
     explicit
    0.34
     naked
    0.33
     sexual
    0.33
     Explicit
    0.32
     lasc
    0.32
     sex
    0.32
     sexually
    0.30
     nude
    0.29
     nudity
    0.29
    Explicit
    0.29
    Act Density 0.498%

    No Known Activations