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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or events that happen before a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    actions and processes involving the concept of "going" or "movement."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    among
    -0.74
    paralle
    -0.72
    rather
    -0.72
    never
    -0.69
     aver
    -0.66
    <?
    -0.66
     underestimated
    -0.64
    eret
    -0.63
    while
    -0.63
     misunderstood
    -0.61
    POSITIVE LOGITS
    pection
    0.71
     landfall
    0.70
    apses
    0.69
     anymore
    0.68
     hostilities
    0.67
    adelphia
    0.65
    aban
    0.65
     expires
    0.65
     expiration
    0.64
    zhou
    0.62
    Act Density 0.308%

    No Known Activations