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

    Neuronpedia

    INDEX
    Explanations

    patterns of punctuation and special characters indicating structure in text

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

    punctuation marks related to lists or enumerations

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

    punctuation and variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acque
    -0.56
    ً
    -0.56
    (`/
    -0.56
    (__('
    -0.56
    .’
    -0.56
     reis
    -0.55
    likat
    -0.54
     blow
    -0.53
     (‘
    -0.50
     vasca
    -0.49
    POSITIVE LOGITS
     وتسجيلات
    1.02
     Roskov
    1.01
     >=",
    1.00
    )",
    0.90
     propOrder
    0.89
     للاسماء
    0.89
    +#+
    0.88
    %",
    0.88
    }(),
    0.87
    ]",
    0.86
    Act Density 0.036%

    No Known Activations