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

    Neuronpedia

    INDEX
    Explanations

    semicolons and other punctuation marks within code

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

    statement terminator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chriſt
    -0.70
     juſ
    -0.69
     ſur
    -0.64
     hina
    -0.60
     viſ
    -0.60
     ſche
    -0.59
     EconPapers
    -0.59
    EndContext
    -0.57
     ſol
    -0.57
    Avon
    -0.57
    POSITIVE LOGITS
    ;
    0.82
     ;
    0.81
    .;
    0.79
    ;;;
    0.78
    ;;;;
    0.76
     {;
    0.72
    ;;
    0.72
    !;
    0.70
    $;
    0.70
    (';
    0.68
    Act Density 0.141%

    No Known Activations