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

    Neuronpedia

    INDEX
    Explanations

    commands and code structures in programming or scripting contexts

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

    This neuron activates for whitespace, particularly line breaks and indentation at the beginning of lines.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    code repository and command line interface (CLI) related terms.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -1.24
    InputBorder
    -1.03
     BoxDecoration
    -0.98
    WebVitals
    -0.85
    ConstraintMaker
    -0.84
    GraphicsUnit
    -0.79
    AndEndTag
    -0.79
    LLocation
    -0.79
    SequentialGroup
    -0.75
    AddTagHelper
    -0.75
    POSITIVE LOGITS
    <bos>
    1.04
    ってみて
    0.69
    ってみました
    0.64
    ってみる
    0.61
     ")");
    0.60
    }],
    0.59
    expandindo
    0.58
    }),
    0.57
    ("}");
    0.56
     >=",
    0.54
    Act Density 61.495%

    No Known Activations