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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of "sum."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sum" or phrases related to aggregation or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.75
     grounding
    -0.63
     Ferry
    -0.63
    ttes
    -0.60
     blinking
    -0.59
     foreclosure
    -0.59
     Flame
    -0.58
     tradem
    -0.58
     Enrique
    -0.58
     Flint
    -0.58
    POSITIVE LOGITS
    ming
    1.48
    mers
    1.36
    mits
    1.29
    mar
    1.11
    atra
    1.11
    mit
    1.09
    mons
    1.09
    ption
    1.05
    ptive
    0.99
    mary
    0.98
    Act Density 0.024%

    No Known Activations