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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and notation, especially those involving subscripts and superscripts

    oai_token-act-pair · gemini-2.0-flash

    ordinal numbers

    np_token-act-pair-logits · gpt-4o-mini

    say "the ending -th"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.93
    expandindo
    -0.85
     resourceCulture
    -0.84
     оригіналу
    -0.79
    modelBuilder
    -0.78
    tagHelperRunner
    -0.75
     snippetHide
    -0.75
    +#+#
    -0.75
    featureID
    -0.71
    migrationBuilder
    -0.71
    POSITIVE LOGITS
    th
    1.85
     th
    1.47
    TH
    1.21
    Th
    1.20
    <sup>
    1.16
    ième
    1.06
    nd
    0.99
    thof
    0.98
    oth
    0.98
    ths
    0.93
    Act Density 1.951%

    No Known Activations