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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases indicating repetition or continuity

    oai_token-act-pair · gpt-3.5-turbo

    repeated temporal references related to time increments and ongoing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sth
    -0.78
     Polk
    -0.73
    anth
    -0.73
    iov
    -0.73
    ãĥ´ãĤ¡
    -0.71
    obal
    -0.70
     Stub
    -0.70
    jon
    -0.69
    iom
    -0.68
    rav
    -0.67
    POSITIVE LOGITS
     comparisons
    0.67
     approximation
    0.65
     proportions
    0.64
     blush
    0.62
     alike
    0.62
    è¦ļéĨĴ
    0.62
     budgets
    0.62
    ciating
    0.61
     basis
    0.60
     avalanche
    0.60
    Act Density 0.078%

    No Known Activations