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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     éste
    -0.39
     discí
    -0.36
     بگ
    -0.36
     also
    -0.35
     Padilla
    -0.35
    DEPART
    -0.35
     ésta
    -0.34
     idéia
    -0.34
     beliau
    -0.34
     svå
    -0.34
    POSITIVE LOGITS
    ſelf
    0.60
    NameInMap
    0.57
    Portail
    0.57
    انيف
    0.54
    MigrationBuilder
    0.52
    يكب
    0.51
    новниш
    0.51
    raulic
    0.50
     ſta
    0.50
    astéro
    0.50
    Act Density 0.610%

    No Known Activations