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

    Neuronpedia

    INDEX
    Explanations

    mentions of record highs or lows in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to extreme values or fluctuations in stock market or economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oute
    -0.80
    OTS
    -0.75
    Reply
    -0.69
     Caucas
    -0.63
    Translation
    -0.63
     subtitles
    -0.60
    Guide
    -0.60
    Stud
    -0.59
    Shell
    -0.59
    leted
    -0.59
    POSITIVE LOGITS
     highs
    1.03
    mith
    1.00
     lows
    0.96
     heights
    0.88
    creen
    0.87
    cape
    0.85
    terday
    0.84
    terness
    0.83
    leep
    0.78
    peed
    0.77
    Act Density 0.042%

    No Known Activations