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

    Neuronpedia

    INDEX
    Explanations

    shapes and dimensions, particularly those that are geometric or associated with specific design representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pson
    -0.18
    taire
    -0.16
    braco
    -0.16
    Ñıж
    -0.15
    ber
    -0.14
    ecess
    -0.14
    det
    -0.14
    ham
    -0.14
     success
    -0.14
    -lite
    -0.14
    POSITIVE LOGITS
     shape
    0.20
     Shape
    0.18
    -shaped
    0.18
    shape
    0.18
    Shape
    0.17
    .shape
    0.17
    иÑĤом
    0.16
     Shapes
    0.16
     shapes
    0.16
    cko
    0.15
    Act Density 0.116%

    No Known Activations