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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the letter "w" followed by a verb in present tense

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'w' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.81
    pora
    -0.68
     duplication
    -0.67
     succeeding
    -0.67
     fracturing
    -0.66
     headache
    -0.65
    uate
    -0.64
    idates
    -0.63
    hyde
    -0.63
     depri
    -0.62
    POSITIVE LOGITS
    ither
    1.25
    atts
    1.16
    iggle
    1.12
    atson
    1.12
    irts
    1.09
    ithering
    1.08
    igg
    1.08
    icket
    1.07
    idd
    1.07
    tf
    1.07
    Act Density 0.017%

    No Known Activations