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

    Neuronpedia

    INDEX
    Explanations

    time durations

    oai_token-act-pair · gpt-3.5-turbo

    the word "until" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pour
    -0.71
    certain
    -0.69
    hazard
    -0.69
    LAB
    -0.67
    venture
    -0.66
    aque
    -0.65
    puff
    -0.65
    cript
    -0.65
    founded
    -0.64
    cigarette
    -0.64
    POSITIVE LOGITS
    itures
    0.76
    ithub
    0.70
    atcher
    0.69
     adulthood
    0.69
     proven
    0.69
    llular
    0.66
    opa
    0.65
    aments
    0.65
    terday
    0.64
    ishers
    0.64
    Act Density 0.030%

    No Known Activations