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

    Neuronpedia

    INDEX
    Explanations

    instances of numbers and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fran
    -0.16
    ronym
    -0.15
     ple
    -0.15
    λÎŃ
    -0.14
    lein
    -0.14
    abei
    -0.14
     jadx
    -0.14
    holm
    -0.14
     лÑİд
    -0.14
    urity
    -0.14
    POSITIVE LOGITS
    stime
    0.15
    799
    0.15
    Ã¶ÃŁe
    0.13
    apon
    0.13
     failing
    0.13
     mobility
    0.13
     Rosenberg
    0.13
    568
    0.13
     prestige
    0.13
    enville
    0.13
    Act Density 0.023%

    No Known Activations