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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "do"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    voj
    -0.17
    worm
    -0.16
    ovie
    -0.16
    lain
    -0.15
    unga
    -0.15
    ieux
    -0.15
    ÑĤиÑĢов
    -0.15
    aina
    -0.14
    lund
    -0.14
    wen
    -0.14
    POSITIVE LOGITS
     now
    0.22
     dot
    0.21
     not
    0.20
     nor
    0.19
     net
    0.19
     mot
    0.19
     hot
    0.18
     notre
    0.18
     little
    0.18
     Dot
    0.17
    Act Density 0.054%

    No Known Activations