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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the allocation of time or effort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ceilings
    -0.68
     inacc
    -0.67
    soDeliveryDate
    -0.65
     slate
    -0.61
     Fib
    -0.61
     departures
    -0.61
    Compat
    -0.61
     Mayo
    -0.59
     axis
    -0.59
    ovi
    -0.57
    POSITIVE LOGITS
    ibal
    0.82
    oling
    0.74
     bucks
    0.73
     semester
    0.72
    arant
    0.71
    ornia
    0.68
    olation
    0.68
    secut
    0.68
    anchester
    0.68
    anmar
    0.67
    Act Density 0.129%

    No Known Activations