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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "to be" in different forms and tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     being
    -0.77
     étant
    -0.73
     fiind
    -0.69
    Being
    -0.69
    being
    -0.68
     Being
    -0.67
     BEING
    -0.57
     fortfarande
    -0.55
     masih
    -0.51
    still
    -0.51
    POSITIVE LOGITS
     able
    0.97
     taken
    0.84
     considered
    0.81
     seen
    0.79
     regarded
    0.77
     construed
    0.76
     interpreted
    0.75
     viewed
    0.71
     replaced
    0.70
     held
    0.70
    Act Density 0.426%

    No Known Activations