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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating temporal context or reference to past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exitRule
    -0.48
     wasteful
    -0.42
    PreferredItem
    -0.41
    rusted
    -0.41
     orgull
    -0.39
     Waste
    -0.39
    Autoritní
    -0.39
     Să
    -0.39
     stupid
    -0.39
    Kesimpulan
    -0.38
    POSITIVE LOGITS
     kasarigan
    0.47
     >=",
    0.46
    TestingModule
    0.46
     year
    0.45
    ⓧ
    0.45
    TagMode
    0.44
     "..\..\..\
    0.42
    новниш
    0.42
    TokenNameEQUAL
    0.42
    Dispatchers
    0.41
    Act Density 0.209%

    No Known Activations