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

    Neuronpedia

    INDEX
    Explanations

    instances of words starting with 'w' followed by a verb or noun

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "w"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.80
    pora
    -0.70
     fracturing
    -0.70
     succeeding
    -0.69
    hyde
    -0.67
     culp
    -0.66
    Ô
    -0.65
     Palestin
    -0.64
    uate
    -0.64
    ãĤŃ
    -0.63
    POSITIVE LOGITS
    ither
    1.24
    atts
    1.16
    idd
    1.09
    irts
    1.07
    atson
    1.06
    iggle
    1.06
    ithering
    1.06
    itty
    1.03
    igg
    1.02
    urst
    1.00
    Act Density 0.018%

    No Known Activations