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

    Neuronpedia

    INDEX
    Explanations

    mentions of past events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time references, specifically the words "earlier in the week," "earlier in the day," and variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.65
    avorite
    -0.63
    rw
    -0.62
    VPN
    -0.61
     Simulator
    -0.60
     someday
    -0.58
    çļ
    -0.58
    apego
    -0.57
    olor
    -0.57
    osate
    -0.57
    POSITIVE LOGITS
    imester
    0.89
    notice
    0.75
    than
    0.75
     sidx
    0.73
    ounter
    0.71
    noon
    0.70
    morning
    0.69
    heast
    0.69
    ask
    0.68
     evening
    0.68
    Act Density 0.090%

    No Known Activations