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

    Neuronpedia

    INDEX
    Explanations

    time-related durations and periods

    oai_token-act-pair · gpt-3.5-turbo

    time-related expressions indicating future durations and intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edIn
    -0.81
    ¬¼
    -0.76
     lately
    -0.75
    actionDate
    -0.74
    inventoryQuantity
    -0.68
     knack
    -0.66
     recent
    -0.64
    nered
    -0.64
    lua
    -0.63
    emia
    -0.62
    POSITIVE LOGITS
     onwards
    0.85
    .<
    0.76
    .</
    0.73
    ":"/
    0.71
    rica
    0.70
     Aviv
    0.70
    ãĥ¯
    0.70
    çļ
    0.69
     unless
    0.69
     onward
    0.69
    Act Density 0.106%

    No Known Activations