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

    Neuronpedia

    INDEX
    Explanations

    words related to bodily functions or physical disputes

    oai_token-act-pair · gpt-3.5-turbo

    humorous or negative references to bodily functions and glitches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.86
    achment
    -0.84
     Zur
    -0.78
    amara
    -0.75
    asonry
    -0.74
    unin
    -0.74
    agar
    -0.74
     largeDownload
    -0.73
    aina
    -0.73
    acher
    -0.73
    POSITIVE LOGITS
     fart
    2.44
     spat
    2.29
     spit
    1.69
     poop
    1.59
     blink
    1.49
     spitting
    1.47
     glitch
    1.41
     yawn
    1.32
     vomit
    1.32
     malfunction
    1.32
    Act Density 0.050%

    No Known Activations