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

    Neuronpedia

    INDEX
    Explanations

    numbers associated with various statistical measures or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ows
    -0.18
    olog
    -0.16
    agra
    -0.15
    MBER
    -0.15
    lar
    -0.15
    endoza
    -0.15
    ament
    -0.14
    olar
    -0.14
    ixa
    -0.14
    olars
    -0.14
    POSITIVE LOGITS
    ï¸ı
    0.23
    s
    0.19
    xffff
    0.16
    oo
    0.16
    lymp
    0.15
    ooo
    0.15
    xFFFF
    0.15
    /null
    0.15
    ãĥ«ãĥĪ
    0.15
    xFFFFFFFF
    0.14
    Act Density 0.167%

    No Known Activations