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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing occasional or periodic actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate time or temporal transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udeb
    -0.75
    iov
    -0.73
    dor
    -0.72
     TOUR
    -0.70
    comings
    -0.69
    drawn
    -0.67
    sett
    -0.66
    war
    -0.65
    MSN
    -0.65
    tein
    -0.64
    POSITIVE LOGITS
    ciating
    0.70
    */(
    0.68
    uce
    0.64
     Nieto
    0.64
     Flores
    0.63
     hairc
    0.61
     imaginable
    0.59
     proport
    0.58
    rouse
    0.57
     glance
    0.56
    Act Density 0.057%

    No Known Activations