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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes or evolutions over time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "over" followed by a time duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ista
    -0.60
     breeze
    -0.59
    Ur
    -0.58
    esm
    -0.57
    UE
    -0.57
     darling
    -0.56
    ensical
    -0.55
     Oops
    -0.54
    oe
    -0.54
    itaire
    -0.54
    POSITIVE LOGITS
    comes
    1.02
    haul
    0.97
    whelming
    0.95
    arching
    0.93
    tones
    0.90
    stay
    0.86
     periods
    0.86
     decades
    0.86
    drive
    0.85
    hang
    0.84
    Act Density 0.058%

    No Known Activations