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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms related to addition or accumulation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sum" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.82
     Kers
    -0.66
     Ferry
    -0.66
     Defenders
    -0.62
     blinking
    -0.61
     embr
    -0.61
     ignition
    -0.60
     surn
    -0.58
     fires
    -0.58
     Flame
    -0.56
    POSITIVE LOGITS
    ming
    1.44
    mers
    1.22
    mits
    1.17
    otaur
    0.96
    atra
    0.95
    sum
    0.93
    mes
    0.90
    ptive
    0.87
    plings
    0.86
    ulative
    0.86
    Act Density 0.024%

    No Known Activations