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

    Neuronpedia

    INDEX
    Explanations

    articles and pronouns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    centralwidget
    -0.68
     legislation
    -0.65
    addComponent
    -0.65
     pouvoirs
    -0.62
     dítě
    -0.61
     člove
    -0.60
     gouvernements
    -0.60
     vrijwilli
    -0.59
     sentiers
    -0.59
     karta
    -0.59
    POSITIVE LOGITS
    Những
    1.16
     those
    1.09
     οι
    1.09
     những
    1.06
     these
    1.04
     few
    1.03
    those
    1.01
     mga
    1.01
    Οι
    1.00
    wsze
    0.98
    Act Density 0.262%

    No Known Activations