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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "was" or "were" indicating past occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -1.07
     Monfieur
    -1.05
     houſe
    -1.04
     pleaſure
    -1.02
     cauſe
    -1.01
     ſy
    -0.98
     reaſon
    -0.96
     becauſe
    -0.95
     ejus
    -0.95
     whoſe
    -0.94
    POSITIVE LOGITS
     was
    2.29
     Was
    1.81
    Was
    1.74
     WAS
    1.70
    was
    1.69
     were
    1.68
     WERE
    1.41
     wasn
    1.39
     Were
    1.34
    Twas
    1.34
    Act Density 0.457%

    No Known Activations