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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases and schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mornings
    -0.32
     morning
    -0.28
     Morning
    -0.25
    Morning
    -0.24
    æĻ¨
    -0.21
     sunrise
    -0.18
     Morrow
    -0.16
    isible
    -0.16
     breakfast
    -0.16
     dawn
    -0.16
    POSITIVE LOGITS
     close
    0.16
    flater
    0.16
     late
    0.16
     Late
    0.16
     sund
    0.15
    yne
    0.15
    late
    0.15
    Late
    0.15
    eyn
    0.15
    kode
    0.14
    Act Density 0.019%

    No Known Activations