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

    Neuronpedia

    INDEX
    Explanations

    references to specific units and types in structured data models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     argint
    -0.50
    存于互联网档案馆
    -0.47
    AndEndTag
    -0.45
    țiune
    -0.41
    anță
    -0.41
     للاسماء
    -0.39
    PRACT
    -0.39
     Chwiliwch
    -0.39
    țiuni
    -0.39
    szön
    -0.39
    POSITIVE LOGITS
     Unit
    0.75
     UNIT
    0.70
    Unit
    0.66
     Units
    0.65
     unit
    0.65
     kasarigan
    0.62
    OfWork
    0.59
    UNIT
    0.59
    unit
    0.57
     censiti
    0.57
    Act Density 0.082%

    No Known Activations