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

    Neuronpedia

    INDEX
    Explanations

    specific geometric shapes and their descriptions in the context of engineering or design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Stride
    -0.23
    pson
    -0.15
    @update
    -0.15
     dÆ°Æ¡ng
    -0.15
    emax
    -0.15
    _stride
    -0.14
    stride
    -0.14
    _mC
    -0.14
    SIDE
    -0.14
    TextWriter
    -0.14
    POSITIVE LOGITS
    -shaped
    0.30
     shaped
    0.22
     shape
    0.21
     formation
    0.18
    shape
    0.17
     formed
    0.17
    å½¢
    0.16
    Shape
    0.16
     shapes
    0.16
    _shape
    0.15
    Act Density 0.129%

    No Known Activations