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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting markers in the text

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

    Punctuation followed by conjunctions or relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    sentence continuation after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parseFrom
    -0.63
     Архиви
    -0.62
    bedingt
    -0.60
     myſelf
    -0.60
    raud
    -0.60
     AUSSI
    -0.58
    ionario
    -0.58
    ifeng
    -0.58
    RenderAtEndOf
    -0.57
    endgroup
    -0.56
    POSITIVE LOGITS
     aquela
    0.70
     aquele
    0.66
    رشف
    0.54
     or
    0.53
     ведь
    0.53
    whether
    0.52
     مشين
    0.50
     whether
    0.49
    verwijspagina
    0.48
     zelfs
    0.48
    Act Density 0.340%

    No Known Activations