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

    Neuronpedia

    INDEX
    Explanations

    references to "direction" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abestanden
    -0.92
     
    -0.90
    Espèce
    -0.86
    GEBURTSDATUM
    -0.86
    asantry
    -0.82
    letus
    -0.82
    QMessageBox
    -0.79
    flakes
    -0.79
     NSCoder
    -0.78
     Leal
    -0.78
    POSITIVE LOGITS
     direction
    1.46
     directions
    1.44
     Direction
    1.35
     DIRECTION
    1.34
    Direction
    1.26
    direction
    1.22
    DIRECTION
    1.21
     Directions
    1.21
    directions
    1.19
     DIRECTIONS
    1.11
    Act Density 0.102%

    No Known Activations