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

    Neuronpedia

    INDEX
    Explanations

    geometric shapes and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouz
    -0.17
    Sphere
    -0.16
    mant
    -0.15
    cline
    -0.15
    395
    -0.15
     ÐĿаÑģ
    -0.15
     sphere
    -0.15
    idth
    -0.15
    Cube
    -0.14
     Sphere
    -0.14
    POSITIVE LOGITS
    -shaped
    0.49
     shaped
    0.36
     shape
    0.35
    shape
    0.31
     Shape
    0.30
    å½¢
    0.27
    Shape
    0.26
     shapes
    0.26
    çĬ¶
    0.24
    _shape
    0.24
    Act Density 0.183%

    No Known Activations