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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.57
     hina
    -0.53
     juſ
    -0.51
     Chriſt
    -0.50
     Вин
    -0.49
    cvt
    -0.49
     Bana
    -0.47
    chevron
    -0.46
    vetica
    -0.46
     McMahon
    -0.46
    POSITIVE LOGITS
    +;
    0.98
    %;
    0.82
    $;
    0.82
     {;
    0.82
    °;
    0.79
    !;
    0.79
    *;
    0.79
    ;
    0.78
    -;
    0.77
    .;
    0.76
    Act Density 0.304%

    No Known Activations