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

    Neuronpedia

    INDEX
    Explanations

    semicolons and related punctuation marks

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

    semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.54
    cvt
    -0.51
    vetica
    -0.48
     McMahon
    -0.46
     Schrader
    -0.46
     Bana
    -0.45
     Shelton
    -0.45
     Вин
    -0.44
     Chriſt
    -0.44
    RemoteException
    -0.44
    POSITIVE LOGITS
    +;
    0.86
    ;
    0.81
    $;
    0.74
     ;
    0.71
    !;
    0.71
    %;
    0.69
     {;
    0.68
    /;
    0.68
    ?;
    0.66
    .;
    0.65
    Act Density 0.174%

    No Known Activations