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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating generation or authorship

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

    generated by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.85
    InitStruct
    -0.69
    RenderAtEndOf
    -0.68
     вікі
    -0.67
    copg
    -0.66
    下载附件
    -0.65
     betweenstory
    -0.64
     للاسماء
    -0.64
    AsUp
    -0.63
    UnitTesting
    -0.61
    POSITIVE LOGITS
    CodeAttribute
    0.56
    generator
    0.53
     generator
    0.53
     generated
    0.51
     generators
    0.50
     Generator
    0.49
     génér
    0.47
     Generated
    0.47
    generators
    0.47
     Generators
    0.46
    Act Density 0.005%

    No Known Activations