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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating equivalence or similarity

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

    known as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ResumeLayout
    -0.61
    clientY
    -0.47
     purpoſe
    -0.45
     monasterio
    -0.44
    Kanpo
    -0.44
     fubject
    -0.43
     déli
    -0.43
     juſ
    -0.42
    EndInit
    -0.42
     psiqui
    -0.42
    POSITIVE LOGITS
    ConstraintMaker
    0.74
    称为
    0.66
     CALLED
    0.65
     AssemblyCompany
    0.63
     called
    0.62
    被称为
    0.62
    稱為
    0.61
    called
    0.61
    视为
    0.59
     as
    0.58
    Act Density 0.009%

    No Known Activations