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

    Neuronpedia

    INDEX
    Explanations

    words related to addition or totals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sum" in relation to calculations or aggregations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Defenders
    -0.70
     Kers
    -0.69
     livest
    -0.69
     Ferry
    -0.68
     surn
    -0.68
     Flame
    -0.62
    eele
    -0.59
     foreclosure
    -0.59
     Blitz
    -0.58
     Battles
    -0.57
    POSITIVE LOGITS
    ming
    1.44
    mers
    1.11
    mits
    1.09
    ulative
    0.92
    otaur
    0.91
    sum
    0.89
     sum
    0.86
    total
    0.81
    mes
    0.81
    iture
    0.80
    Act Density 0.014%

    No Known Activations