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

    Neuronpedia

    INDEX
    Explanations

    profanity and oaths

    oai_token-act-pair · gpt-3.5-turbo

    instances of swearing or cursing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Northwestern
    -0.67
     Pioneer
    -0.67
    Fab
    -0.67
     Seed
    -0.66
     seed
    -0.64
     prototype
    -0.64
     Cater
    -0.63
     Safari
    -0.63
    erella
    -0.63
     Marin
    -0.61
    POSITIVE LOGITS
     swearing
    4.00
     cursing
    2.35
     yelling
    1.43
     swore
    1.36
     swear
    1.36
     shouting
    1.27
     perjury
    1.19
    uty
    1.16
     barking
    1.14
     spitting
    1.14
    Act Density 0.038%

    No Known Activations