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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing emphasis or strong opinions

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

    à la Alaska

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     därför
    -0.34
     Inscrivez
    -0.34
     personer
    -0.33
     considère
    -0.33
    lihatkan
    -0.32
     Yesus
    -0.31
     mères
    -0.30
     étrangers
    -0.30
    ntä
    -0.30
     istnie
    -0.28
    POSITIVE LOGITS
    хьтан
    1.02
     kaarangay
    0.99
    Portale
    0.96
     ویکی‌پدی
    0.90
    EndProject
    0.82
     AssemblyTitle
    0.79
    تقاوى
    0.79
    <unused41>
    0.79
     erſt
    0.79
    [@BOS@]
    0.79
    Act Density 0.043%

    No Known Activations