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

    Neuronpedia

    INDEX
    Explanations

    instances of specific numerical conditions or iterations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ||↵
    -0.16
    Ø°
    -0.15
    andra
    -0.15
    ]bool
    -0.15
    ãĥ¼ãĥĵ
    -0.14
    UNET
    -0.14
    ignant
    -0.14
     Raq
    -0.14
    )>>
    -0.13
    onda
    -0.13
    POSITIVE LOGITS
     <
    0.29
     <=
    0.23
    <
    0.22
     less
    0.18
     !=
    0.17
     fewer
    0.17
    <translation
    0.17
    <=
    0.17
     ï¼ľ
    0.16
    idis
    0.16
    Act Density 0.021%

    No Known Activations