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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "was" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     connected
    -0.51
     otomatig
    -0.50
    viedo
    -0.49
    といって
    -0.49
    Lähteet
    -0.49
    Viited
    -0.49
     Baillargeon
    -0.48
    upsi
    -0.47
     بن
    -0.45
    Netto
    -0.45
    POSITIVE LOGITS
     был
    1.49
     была
    1.47
     Was
    1.45
    Was
    1.44
    WAS
    1.33
     був
    1.33
     Foi
    1.30
    was
    1.30
     были
    1.29
     WAS
    1.26
    Act Density 0.082%

    No Known Activations