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

    Neuronpedia

    INDEX
    Explanations

    references to bodily functions, specifically related to urination

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to urination and similar bodily functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aido
    -0.83
    ellen
    -0.83
     Flavoring
    -0.82
    ICA
    -0.70
    nikov
    -0.69
    ahn
    -0.68
    HCR
    -0.67
    cffffcc
    -0.67
    nov
    -0.67
    akespe
    -0.67
    POSITIVE LOGITS
    pee
    1.08
     bladder
    1.04
     pee
    1.04
    ysis
    0.92
     ur
    0.85
    pants
    0.81
     flush
    0.79
     ejac
    0.79
    pees
    0.78
     piss
    0.77
    Act Density 0.028%

    No Known Activations