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

    Neuronpedia

    INDEX
    Explanations

    terms related to gradients in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    attice
    -0.16
    ulsion
    -0.15
    STRU
    -0.14
    sgiving
    -0.14
    SCRI
    -0.14
    .dispatcher
    -0.14
    IMIT
    -0.14
     jehož
    -0.14
    .radioButton
    -0.14
    âĻª
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĥģ
    0.16
    .Gradient
    0.16
    ugar
    0.15
     shr
    0.15
    uga
    0.14
    iece
    0.14
    оÑī
    0.14
    ospital
    0.14
    en
    0.13
    ŃIJ
    0.13
    Act Density 0.002%

    No Known Activations