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

    Neuronpedia

    INDEX
    Explanations

    numeric values and identifiers in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.71
     in
    -0.60
     and
    -0.54
     a
    -0.53
     to
    -0.52
     on
    -0.52
     of
    -0.51
     as
    -0.51
     (
    -0.49
    .
    -0.49
    POSITIVE LOGITS
     вÑĸ
    0.28
     меÑĪ
    0.27
     наÑģеленнÑı
    0.25
     пÑĢип
    0.25
     оÑģÑĸб
    0.25
     доÑĢ
    0.25
     вÑĸд
    0.24
     ÑĢозп
    0.23
     оÑģоби
    0.23
     понад
    0.23
    Act Density 0.002%

    No Known Activations