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

    Neuronpedia

    INDEX
    Explanations

    references to information and requests for details about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nt
    -0.25
    mente
    -0.23
    /or
    -0.22
    ร
    -0.22
    ately
    -0.19
    hip
    -0.18
    een
    -0.17
    ãģįãģŁ
    -0.17
    ÑģÑĮ
    -0.17
    istrator
    -0.16
    POSITIVE LOGITS
    ëģĶ
    0.20
    ilitating
    0.18
    elper
    0.18
    amp
    0.18
    sumer
    0.17
    ulously
    0.17
    quam
    0.17
    ãģĬãĤĬ
    0.17
    otr
    0.16
    imized
    0.16
    Act Density 0.315%

    No Known Activations