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

    Neuronpedia

    INDEX
    Explanations

    references to periods of time expressed in years

    oai_token-act-pair · gpt-3.5-turbo

    references to durations expressed in years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.91
     Clever
    -0.70
    hops
    -0.66
    icio
    -0.66
     lobb
    -0.66
    iqu
    -0.63
    UTF
    -0.63
     Rooms
    -0.62
    OULD
    -0.62
    undown
    -0.62
    POSITIVE LOGITS
     ago
    1.09
     anniversary
    0.98
    iversary
    0.89
    long
    0.86
    llor
    0.82
     olds
    0.78
    ly
    0.77
     increments
    0.73
    period
    0.71
    frames
    0.71
    Act Density 0.038%

    No Known Activations