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

    Neuronpedia

    INDEX
    Explanations

    references to circles and circular shapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.63
     publick
    -0.56
     تانيه
    -0.56
    onViewCreated
    -0.56
    Nationalité
    -0.55
    rogens
    -0.54
     ProtoMessage
    -0.54
    poppy
    -0.52
     Poppy
    -0.52
    Bahnhof
    -0.52
    POSITIVE LOGITS
     circle
    2.21
     circles
    2.06
     circular
    2.05
     Circle
    2.00
    Circle
    1.92
    circle
    1.91
     Circles
    1.78
     Circular
    1.76
    Circular
    1.76
     CIRCLE
    1.72
    Act Density 2.650%

    No Known Activations