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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to machine learning and computing resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    URED
    -0.16
    è
    -0.16
    repid
    -0.16
    ovah
    -0.15
    ãĥªãĥ³
    -0.14
    _ISO
    -0.14
    andi
    -0.14
    .iso
    -0.14
    Iso
    -0.14
    ucht
    -0.14
    POSITIVE LOGITS
     gall
    0.17
     padd
    0.17
    .tensor
    0.17
     paddle
    0.17
    quant
    0.16
     Gall
    0.16
    cum
    0.16
     fused
    0.15
     tensor
    0.15
    _tensor
    0.15
    Act Density 0.009%

    No Known Activations