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

    Neuronpedia

    INDEX
    Explanations

    parentheses and brackets in code-related contexts

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

    ( followed by specific characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſta
    -0.46
     paſſ
    -0.46
     ſtre
    -0.45
     juſ
    -0.45
     tranſ
    -0.45
     preſent
    -0.44
    MigrationBuilder
    -0.43
     viſ
    -0.40
     Inſ
    -0.40
     ſol
    -0.39
    POSITIVE LOGITS
    +#+#
    0.57
     jScrollPane
    0.56
    sizeCache
    0.56
    awtextra
    0.54
     initComponents
    0.53
     #(
    0.52
    三四
    0.52
    ----</
    0.52
     CanadaChoose
    0.51
     }^{(
    0.49
    Act Density 0.031%

    No Known Activations