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

    Neuronpedia

    INDEX
    Explanations

    common punctuation marks and their frequency in the text

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

    sentence breaks follow punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     color
    -0.35
     zero
    -0.33
    ございません
    -0.33
    orcid
    -0.33
    zel
    -0.33
     volunteer
    -0.32
    bri
    -0.32
    組
    -0.32
     recognized
    -0.32
    volunteer
    -0.32
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.72
    MessageTagHelper
    0.63
    RegressionTest
    0.62
     GenerationType
    0.62
    帖最后由
    0.60
    jmniej
    0.59
    RTLI
    0.56
    aarrggbb
    0.55
     otomatig
    0.54
    andExpect
    0.52
    Act Density 0.136%

    No Known Activations