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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.91
    ThroughAttribute
    -0.84
     pleaſure
    -0.83
     ſche
    -0.83
     ModelExpression
    -0.83
     propOrder
    -0.82
     Monfieur
    -0.82
     ſtate
    -0.81
     myſelf
    -0.80
     ſta
    -0.80
    POSITIVE LOGITS
     ist
    1.33
     sind
    1.24
     est
    1.04
     è
    1.04
     är
    0.98
     sont
    0.89
     waren
    0.89
     is
    0.88
     suis
    0.88
     sono
    0.87
    Act Density 0.025%

    No Known Activations