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

    Neuronpedia

    INDEX
    Explanations

    descriptions of geometric shapes and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dur
    -0.15
    elix
    -0.14
    ostel
    -0.14
    apult
    -0.14
    ollar
    -0.14
    allas
    -0.14
    ONE
    -0.14
    æģµ
    -0.13
    edn
    -0.13
     jd
    -0.13
    POSITIVE LOGITS
    /vector
    0.17
     bore
    0.16
     purs
    0.15
     \(
    0.15
     arbitr
    0.15
     \
    0.15
    éĢĢ
    0.15
     Vect
    0.15
     enter
    0.14
     interpol
    0.14
    Act Density 0.009%

    No Known Activations