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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.84
    ########.
    -0.71
    MemoryWarning
    -0.70
     تضيفلها
    -0.70
     Empieza
    -0.65
     isComment
    -0.63
     agra
    -0.63
     erop
    -0.61
    Tikang
    -0.61
     الرياضيه
    -0.61
    POSITIVE LOGITS
    CanBe
    0.70
    也可
    0.68
    Vidite
    0.66
     be
    0.65
     бъдат
    0.64
     Sabina
    0.63
    fxml
    0.62
     dejes
    0.60
    ypal
    0.60
     can
    0.60
    Act Density 0.189%

    No Known Activations