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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates, times, and events in a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (=)
    -0.15
    ãĤ¤ãĤ¯
    -0.13
    LARI
    -0.13
     vůÄįi
    -0.13
     yesterday
    -0.13
    ë£
    -0.13
    laÅŁ
    -0.13
    ê·ł
    -0.12
    æĺ¨
    -0.12
    raya
    -0.12
    POSITIVE LOGITS
     starting
    0.38
     beginning
    0.35
     @
    0.31
    starting
    0.30
     at
    0.29
     doors
    0.28
     Doors
    0.28
     between
    0.27
     from
    0.27
     Noon
    0.27
    Act Density 0.087%

    No Known Activations