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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing the passage of time or duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾į
    -0.71
    ollah
    -0.62
    arget
    -0.60
    onto
    -0.60
     elig
    -0.58
    Tes
    -0.57
    _-
    -0.57
     ingred
    -0.57
    Rank
    -0.56
    =-=-=-=-=-=-=-=-
    -0.56
    POSITIVE LOGITS
     lately
    1.09
     since
    0.92
     awhile
    0.82
     downhill
    0.78
     recently
    0.76
     unsuccessfully
    0.74
     previously
    0.72
    umatic
    0.71
     successful
    0.71
     fruitful
    0.70
    Act Density 0.335%

    No Known Activations