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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or periods in instructional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (
    -0.18
    umat
    -0.17
    ifest
    -0.16
    [
    -0.15
    Âł
    -0.14
    ::
    -0.14
     unh
    -0.14
     .
    -0.14
     basis
    -0.14
    adesh
    -0.14
    POSITIVE LOGITS
    еÑĤÑĮÑģÑı
    0.15
    undler
    0.15
     воÑĢ
    0.15
    íļį
    0.15
    MLElement
    0.15
     Ñĥмов
    0.15
    .Invariant
    0.15
     Posted
    0.14
    EDIA
    0.14
    leftright
    0.14
    Act Density 0.002%

    No Known Activations