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

    Neuronpedia

    INDEX
    Explanations

    terms related to processing data in batches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.93
    complexContent
    -0.91
     leetcode
    -0.88
    lessness
    -0.79
     Esquire
    -0.79
    yntaxException
    -0.77
     LEYENDO
    -0.76
    aarrggbb
    -0.76
    ophon
    -0.75
     Zor
    -0.75
    POSITIVE LOGITS
     batch
    1.67
     Batch
    1.66
     BATCH
    1.64
    Batch
    1.60
    BATCH
    1.54
    batch
    1.52
     batches
    1.48
    batches
    1.36
     lotes
    1.28
     lote
    1.16
    Act Density 0.125%

    No Known Activations