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

    Neuronpedia

    INDEX
    Explanations

    specific dates

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical values related to deadlines and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akespe
    -0.72
    hab
    -0.70
    pron
    -0.69
    dinand
    -0.65
    tumblr
    -0.64
    ourge
    -0.63
    avorite
    -0.63
    edIn
    -0.63
    wered
    -0.62
    orable
    -0.61
    POSITIVE LOGITS
     sidx
    0.79
    externalActionCode
    0.66
     Kass
    0.64
    âĸĪâĸĪ
    0.63
     mornings
    0.62
    EVA
    0.62
     onwards
    0.61
     noon
    0.60
    th
    0.60
     ambush
    0.59
    Act Density 0.058%

    No Known Activations