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

    Neuronpedia

    INDEX
    Explanations

    references to batches or groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexContent
    -0.90
     leetcode
    -0.83
    EDEFAULT
    -0.82
     ModelRenderer
    -0.82
    gameserver
    -0.79
     LEYENDO
    -0.77
     mena
    -0.76
    aarrggbb
    -0.75
    mergeFrom
    -0.75
     रु
    -0.74
    POSITIVE LOGITS
     batch
    2.16
     Batch
    2.04
     BATCH
    1.99
    Batch
    1.99
    batch
    1.96
    BATCH
    1.89
     batches
    1.88
    batches
    1.61
     lotes
    1.31
     lote
    1.28
    Act Density 0.069%

    No Known Activations