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

    Neuronpedia

    INDEX
    Explanations

    conjugated forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     énergé
    -0.57
     elettrica
    -0.56
     popolari
    -0.56
     démocr
    -0.54
     universale
    -0.51
     thérape
    -0.51
     vertes
    -0.49
     underlie
    -0.49
     Polize
    -0.49
     giuri
    -0.49
    POSITIVE LOGITS
    queryInterface
    0.89
     looking
    0.88
    TargetException
    0.86
     doing
    0.86
    tvguidetime
    0.86
     trying
    0.85
     thinking
    0.84
     making
    0.82
    المناصب
    0.79
     taking
    0.78
    Act Density 0.328%

    No Known Activations