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

    Neuronpedia

    INDEX
    Explanations

    numerical data, symbols, and figures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The number "6" or "sixth"

    np_acts-logits-general · gemini-2.0-flash

    six

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Atoi
    -0.68
    Itoa
    -0.51
     kasarigan
    -0.50
     György
    -0.50
    ργ
    -0.46
     Kina
    -0.46
    ichtet
    -0.45
     terecht
    -0.44
    리
    -0.43
    ǎ
    -0.43
    POSITIVE LOGITS
    6
    1.57
     sixth
    1.37
     Sixth
    1.36
     Six
    1.35
     six
    1.30
     SIX
    1.30
    six
    1.26
    Sixth
    1.20
    Six
    1.18
    SIX
    1.16
    Act Density 0.622%

    No Known Activations