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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace or empty content indicative of formatting or layout in textual data

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

    special typographic spacing and formatting characters, especially nonstandard whitespace used in tables, lists, and metadata.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    Πηγές
    -0.50
    ieważ
    -0.47
     the
    -0.46
     disponibilités
    -0.46
     beginnetje
    -0.46
    borderSide
    -0.42
    Související
    -0.40
     universel
    -0.40
     sacré
    -0.39
     Preußen
    -0.38
    POSITIVE LOGITS
    transQ
    0.71
    出版年
    0.68
    modelBuilder
    0.55
    0.53
    MigrationBuilder
    0.52
     gyhoeddwyd
    0.52
    GEBURTS
    0.51
    unicip
    0.50
    ipro
    0.50
    principalColumn
    0.50
    Act Density 0.539%

    No Known Activations