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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "had."

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

    had

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtate
    -0.52
     preſent
    -0.52
    AnimationsModule
    -0.52
     houſe
    -0.50
     ſche
    -0.50
     ſte
    -0.49
     ſtre
    -0.49
     purpoſe
    -0.49
     itſelf
    -0.47
     perſon
    -0.47
    POSITIVE LOGITS
     had
    1.47
    had
    1.27
    Had
    1.23
     Had
    1.13
     HAD
    1.05
    HAD
    1.02
     miał
    0.88
     Hadley
    0.87
     tivesse
    0.87
     είχε
    0.87
    Act Density 0.069%

    No Known Activations