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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "be."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     tr
    -0.59
    illan
    -0.59
     Mog
    -0.58
     the
    -0.55
     been
    -0.54
     very
    -0.54
    церт
    -0.54
     an
    -0.51
    TimeTo
    -0.50
     enough
    -0.50
    POSITIVE LOGITS
     архивлан
    1.07
     تضيفلها
    1.04
     متعلقه
    1.03
    帖最后由
    1.01
    :✨
    0.99
    0.98
    Gambas
    0.97
     للاسماء
    0.97
     kaarangay
    0.96
    LookAnd
    0.93
    Act Density 0.045%

    No Known Activations