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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    is followed by a verb or noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outta
    -0.45
    everything
    -0.43
     EVERYTHING
    -0.41
     Deckel
    -0.40
     ANYTHING
    -0.40
    AndGet
    -0.39
     freakin
    -0.38
     damas
    -0.38
     everything
    -0.38
    anything
    -0.37
    POSITIVE LOGITS
     następnie
    0.60
     observed
    0.56
     described
    0.55
     ilustracja
    0.53
     ſind
    0.50
    AsUp
    0.49
     subsequently
    0.49
     systematically
    0.49
     został
    0.49
     lecz
    0.49
    Act Density 0.342%

    No Known Activations