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

    Neuronpedia

    INDEX
    Explanations

    terms related to directionality in data or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.90
    Espèce
    -0.87
    новниш
    -0.84
    letus
    -0.83
    ]]);
    -0.83
     Leal
    -0.81
    owulf
    -0.79
    abestanden
    -0.77
    ]--;
    -0.75
    GEBURTSDATUM
    -0.75
    POSITIVE LOGITS
     direction
    1.88
     directions
    1.74
     Direction
    1.73
     DIRECTION
    1.66
    Direction
    1.62
    direction
    1.58
    DIRECTION
    1.51
    directions
    1.46
     Directions
    1.43
     DIRECTIONS
    1.27
    Act Density 0.057%

    No Known Activations