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

    Neuronpedia

    INDEX
    Explanations

    memory addressing terms and size specifications

    oai_token-act-pair · gpt-3.5-turbo

    programming and coding terminologies related to settings, dimensions, and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.87
    aeda
    -0.85
    uj
    -0.85
    agall
    -0.82
    ergy
    -0.82
    arak
    -0.81
    ullivan
    -0.81
    aer
    -0.80
    okers
    -0.79
    arnaev
    -0.76
    POSITIVE LOGITS
    Changed
    0.80
     multiplier
    0.76
     discrepancy
    0.73
     mismatch
    0.73
     constraints
    0.73
     Limits
    0.72
    Sync
    0.72
    Bytes
    0.71
     value
    0.71
    Limit
    0.70
    Act Density 0.170%

    No Known Activations