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

    Neuronpedia

    INDEX
    Explanations

    geometric shapes and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undry
    -0.17
    cid
    -0.15
    474
    -0.15
    cela
    -0.14
    ovable
    -0.14
     Boy
    -0.14
    mant
    -0.14
    estar
    -0.13
    efon
    -0.13
    pcf
    -0.13
    POSITIVE LOGITS
    -shaped
    0.33
     shape
    0.23
    shape
    0.22
     shaped
    0.21
     Shape
    0.20
    çĬ¶
    0.18
    _shape
    0.18
    å½¢
    0.18
    Shape
    0.17
    oidal
    0.17
    Act Density 0.119%

    No Known Activations