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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements in code snippets

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

    Code, parentheses, brackets, and semicolons

    np_acts-logits-general · gemini-2.0-flash

    '; () [] {}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -1.06
     myſelf
    -0.99
     becauſe
    -0.95
    Bronnen
    -0.94
     Wiktionnaire
    -0.92
    Geplaatst
    -0.91
     Jefus
    -0.91
     EconPapers
    -0.91
     ſeveral
    -0.90
     raiſ
    -0.89
    POSITIVE LOGITS
     po
    0.53
     Po
    0.46
     Wol
    0.44
    Wol
    0.43
     nenhuma
    0.42
    </em>
    0.41
     lo
    0.40
    po
    0.40
    Po
    0.39
     भ
    0.39
    Act Density 0.089%

    No Known Activations