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

    Neuronpedia

    INDEX
    Explanations

    references to prominent figures and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Obr
    -0.15
    ohl
    -0.15
    ãĤ¦ãĥĪ
    -0.15
     kone
    -0.14
    709
    -0.14
    PRI
    -0.14
    sep
    -0.13
    íĸ¥
    -0.13
    ÃŃch
    -0.13
     давно
    -0.13
    POSITIVE LOGITS
     remained
    0.44
     stays
    0.41
     stay
    0.41
     stayed
    0.40
     until
    0.37
     Stay
    0.36
    stay
    0.36
    Stay
    0.35
     remain
    0.35
     lasted
    0.33
    Act Density 0.210%

    No Known Activations