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

    Neuronpedia

    INDEX
    Explanations

    references to batches or groups in a data processing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ties
    -0.17
    baar
    -0.16
    ju
    -0.15
    usk
    -0.15
    abeth
    -0.14
    ibrary
    -0.14
    udd
    -0.14
     Mig
    -0.14
    rael
    -0.14
    viar
    -0.14
    POSITIVE LOGITS
    elor
    0.38
    elder
    0.23
    imid
    0.21
    Normalization
    0.20
    (batch
    0.19
    oucher
    0.18
    次
    0.18
    .Batch
    0.17
    norm
    0.16
    =batch
    0.16
    Act Density 0.010%

    No Known Activations