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

    Neuronpedia

    INDEX
    Explanations

    different descriptions and characteristics of shapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Munro
    -0.89
     acorns
    -0.84
    wój
    -0.83
    CodedInputStream
    -0.81
     MenuView
    -0.80
     myſelf
    -0.78
     thirds
    -0.78
    crollView
    -0.77
     trouvera
    -0.77
    例句
    -0.77
    POSITIVE LOGITS
     shape
    2.21
     shapes
    2.07
     SHAPE
    2.06
     Shape
    2.02
    shape
    1.99
     Shapes
    1.92
    SHAPE
    1.91
    Shape
    1.89
    shapes
    1.81
     shaped
    1.69
    Act Density 0.048%

    No Known Activations