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

    Neuronpedia

    INDEX
    Explanations

    numbers, including city names or sports team information

    oai_token-act-pair · gpt-3.5-turbo

    numeric values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.71
    ','
    -0.67
    bryce
    -0.67
    eatures
    -0.67
     unsurprisingly
    -0.66
     horm
    -0.65
     humane
    -0.64
     antit
    -0.63
     reversible
    -0.62
     predictably
    -0.62
    POSITIVE LOGITS
     Avg
    0.75
    etta
    0.72
     avg
    0.71
    itate
    0.71
     Median
    0.66
    inus
    0.64
     respectively
    0.63
     =================================
    0.63
     Rivals
    0.63
    Len
    0.62
    Act Density 0.072%

    No Known Activations