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

    Neuronpedia

    INDEX
    Explanations

    architectural descriptors and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     test
    -0.41
     ser
    -0.40
     
    -0.40
    ks
    -0.40
     (
    -0.40
     مص
    -0.40
     Y
    -0.39
     med
    -0.39
    []
    -0.39
     ה
    -0.38
    POSITIVE LOGITS
    AnchorStyles
    1.20
     itſelf
    1.06
     myſelf
    0.99
     '\\;'
    0.99
    CloseOperation
    0.95
     doubtnut
    0.93
     Efq
    0.90
     himſelf
    0.89
     iſt
    0.89
     ſeveral
    0.89
    Act Density 0.970%

    No Known Activations