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

    Neuronpedia

    INDEX
    Explanations

    coding-related terminology and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phys
    -0.14
    -pill
    -0.14
    -overlay
    -0.14
    /cpp
    -0.13
    uko
    -0.13
    ç«
    -0.13
    PHY
    -0.13
    _Pin
    -0.13
     pent
    -0.13
    çĦ
    -0.13
    POSITIVE LOGITS
     SGD
    0.36
     gradient
    0.34
     updates
    0.32
     update
    0.32
     Gradient
    0.30
     gradients
    0.30
     Adam
    0.29
     minib
    0.28
    gradient
    0.28
     optimizer
    0.28
    Act Density 0.024%

    No Known Activations