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

    Neuronpedia

    INDEX
    Explanations

    references to geometric shapes and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gabe
    -0.15
     station
    -0.15
    lue
    -0.15
    \Container
    -0.14
    ÑĨÑİ
    -0.14
    ghi
    -0.14
     oper
    -0.14
    aign
    -0.14
    station
    -0.14
    ooke
    -0.14
    POSITIVE LOGITS
    armac
    0.18
    errat
    0.16
    navigator
    0.15
    ãĥ¼ãĤ¹
    0.14
     symbolic
    0.14
    _cpp
    0.14
     Franz
    0.14
    òi
    0.14
    ulia
    0.14
    heed
    0.13
    Act Density 0.098%

    No Known Activations