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

    Neuronpedia

    INDEX
    Explanations

    keywords related to data processing in a batch format

    oai_token-act-pair · gpt-3.5-turbo

    references to "batches" and "batch processing"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stances
    -0.71
    PLIED
    -0.70
    ACTED
    -0.70
    pose
    -0.64
    undai
    -0.61
    inav
    -0.61
    ophers
    -0.61
     ancest
    -0.61
     neighb
    -0.61
     familiarity
    -0.60
    POSITIVE LOGITS
     batches
    0.91
    ting
    0.82
     thereof
    0.79
    meal
    0.78
     batch
    0.76
    mates
    0.75
    tery
    0.72
     of
    0.70
    romeda
    0.70
    hari
    0.67
    Act Density 0.060%

    No Known Activations