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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "do" and its conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eniable
    -0.16
    ÑĤиÑĢов
    -0.16
    voj
    -0.16
     Dense
    -0.15
    anden
    -0.14
    unga
    -0.14
    antan
    -0.14
    -pills
    -0.13
    okt
    -0.13
    aina
    -0.13
    POSITIVE LOGITS
     now
    0.18
     dot
    0.18
     net
    0.18
     mot
    0.17
     riot
    0.17
     not
    0.16
    jang
    0.16
    Dot
    0.15
    -dot
    0.15
    irsch
    0.14
    Act Density 0.056%

    No Known Activations