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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their impact on the emotional tone of statements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.87
    DoubleQuotes
    -0.83
     مشين
    -0.77
    CloseOperation
    -0.71
     Chwiliwch
    -0.66
    posedge
    -0.66
    UnsafeEnabled
    -0.64
    IntoConstraints
    -0.64
    ioutil
    -0.59
    ьаж
    -0.59
    POSITIVE LOGITS
    :✨
    0.55
    PreferredItem
    0.54
     KONG
    0.54
    IENTE
    0.53
     Pitman
    0.51
    emias
    0.50
     kong
    0.49
    ulante
    0.48
     marketing
    0.48
    caz
    0.47
    Act Density 0.027%

    No Known Activations