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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the passage of time and events happening in sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to periods of absence or return

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OULD
    -0.66
    acea
    -0.63
    \":
    -0.61
    minimum
    -0.57
     Crate
    -0.56
    bleacher
    -0.56
     Explos
    -0.56
    PLIED
    -0.55
     ..............
    -0.55
    positive
    -0.55
    POSITIVE LOGITS
     thereafter
    1.43
     afterward
    1.26
     afterwards
    1.24
     later
    1.15
     again
    1.12
     shortly
    1.06
     midway
    1.05
     subsequently
    1.00
     altogether
    0.96
     subsequent
    0.95
    Act Density 0.388%

    No Known Activations