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
    estar
    -0.15
    amac
    -0.15
     rib
    -0.15
     pari
    -0.15
     ÐĿаÑģ
    -0.14
    aty
    -0.14
    thes
    -0.14
     Rag
    -0.14
    ovable
    -0.14
    /export
    -0.14
    POSITIVE LOGITS
    -shaped
    0.36
     shaped
    0.24
     shape
    0.23
    shape
    0.21
    oidal
    0.20
    _shape
    0.20
     formation
    0.19
     Shape
    0.19
    å½¢
    0.18
     Formation
    0.18
    Act Density 0.174%

    No Known Activations