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

    Neuronpedia

    INDEX
    Explanations

    the word "once."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "at once."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bett
    -0.74
    uay
    -0.73
    Stew
    -0.72
    enh
    -0.66
    ovi
    -0.66
    band
    -0.66
    aren
    -0.65
    eva
    -0.64
    rollers
    -0.64
    andi
    -0.63
    POSITIVE LOGITS
     glance
    1.02
     horizont
    0.73
     disembark
    0.67
    xus
    0.64
    Spoiler
    0.64
    aneously
    0.62
     glances
    0.61
     blush
    0.60
    FTWARE
    0.59
    ocus
    0.58
    Act Density 0.014%

    No Known Activations