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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الرياضيه
    -1.02
    ImageContext
    -0.87
    UserScript
    -0.81
    PerformLayout
    -0.81
     purpoſe
    -0.78
    UnusedPrivate
    -0.75
    addCriterion
    -0.72
     ſche
    -0.70
     ftate
    -0.68
     ſtate
    -0.68
    POSITIVE LOGITS
     easily
    0.88
     be
    0.87
    也可
    0.86
    CanBe
    0.77
     can
    0.77
     Audiodateien
    0.73
     puede
    0.71
     facilement
    0.70
    也可以
    0.67
     facilmente
    0.67
    Act Density 0.116%

    No Known Activations