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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly parentheses, commas, and the use of parentheses in function calls

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

    Code snippets with specific punctuation

    np_acts-logits-general · gemini-2.0-flash

    separators followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    -0.47
    ↵↵
    -0.46
     can
    -0.46
     D
    -0.45
     h
    -0.43
    kom
    -0.42
     too
    -0.42
     for
    -0.42
     célèbres
    -0.42
    de
    -0.41
    POSITIVE LOGITS
     myſelf
    1.19
     purpoſe
    1.16
     Италијани
    1.13
     Monfieur
    1.11
     متعلقه
    1.10
    Хьажоргаш
    1.09
     reaſon
    1.08
     Houſe
    1.06
    GEBURTSDATUM
    1.06
     poffible
    1.05
    Act Density 0.261%

    No Known Activations