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

    Neuronpedia

    INDEX
    Explanations

    mathematical and physical terms related to concentric shapes and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achal
    -0.54
    uscular
    -0.52
    骼
    -0.50
    lossians
    -0.48
     dés
    -0.47
    벼
    -0.47
    andte
    -0.45
     tắt
    -0.45
     пря
    -0.44
    okan
    -0.44
    POSITIVE LOGITS
     circle
    1.58
     circles
    1.50
     radius
    1.39
     Circle
    1.37
     CIRCLE
    1.29
    Circle
    1.28
    circle
    1.28
     Circles
    1.27
    radius
    1.27
    circles
    1.25
    Act Density 0.394%

    No Known Activations