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

    Neuronpedia

    INDEX
    Explanations

    elements related to geometry and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cylindrical
    -0.17
     mushroom
    -0.15
    aliz
    -0.14
     cyl
    -0.14
     ellipt
    -0.14
     Singular
    -0.14
     bump
    -0.14
     sigmoid
    -0.14
    leton
    -0.13
    ocks
    -0.13
    POSITIVE LOGITS
     triangles
    0.29
     triangle
    0.28
    triangle
    0.27
     sides
    0.26
     Triangle
    0.25
     acute
    0.23
    Triangle
    0.22
    Triangles
    0.21
     congr
    0.20
     Pentagon
    0.20
    Act Density 0.046%

    No Known Activations