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

    Neuronpedia

    INDEX
    Explanations

    references to shape in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.92
     referenties
    -0.91
     $_"
    -0.90
    例句
    -0.90
     myſelf
    -0.89
    CodedInputStream
    -0.86
    wój
    -0.86
     Munro
    -0.85
     raiſ
    -0.85
    Referencie
    -0.85
    POSITIVE LOGITS
     SHAPE
    1.68
     shape
    1.66
     shapes
    1.62
     Shape
    1.55
    SHAPE
    1.50
     Shapes
    1.50
    shape
    1.48
    shapes
    1.47
    Shape
    1.42
     shaped
    1.32
    Act Density 0.059%

    No Known Activations