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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific duration of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating durations or periods of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caption
    -0.64
     Athletics
    -0.59
     Anthropology
    -0.59
     Challenges
    -0.59
     Indust
    -0.58
     Mysteries
    -0.58
     Pione
    -0.58
     Engineers
    -0.57
     Rolling
    -0.57
     embassies
    -0.57
    POSITIVE LOGITS
    fold
    1.24
    peat
    1.15
     dimensional
    1.10
    teenth
    1.08
    -
    1.08
    âĢij
    1.02
    some
    1.00
    quel
    1.00
    dimensional
    0.98
    âĢIJ
    0.94
    Act Density 0.088%

    No Known Activations