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

    Neuronpedia

    INDEX
    Explanations

    phrases related to durations of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating durations or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.85
    ktop
    -0.71
     Clever
    -0.71
    ierrez
    -0.69
    undown
    -0.65
     resemble
    -0.64
     Alps
    -0.63
     lobb
    -0.63
    querque
    -0.63
    anamo
    -0.62
    POSITIVE LOGITS
     ago
    1.09
     anniversary
    1.00
    iversary
    0.99
    long
    0.92
    llor
    0.87
    ly
    0.85
    ning
    0.78
     Anniversary
    0.72
     hiatus
    0.71
     increments
    0.71
    Act Density 0.038%

    No Known Activations