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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating differences or similarities

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

    making comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.64
    ագրություններ
    -0.62
    parsedMessage
    -0.56
    httphttps
    -0.54
    complexContent
    -0.52
    Erreferentziak
    -0.51
    +#+#
    -0.50
     Infór
    -0.49
    GraphicsUnit
    -0.49
    ">*</
    -0.49
    POSITIVE LOGITS
     than
    0.51
    than
    0.39
     beyond
    0.38
    Than
    0.36
     ніж
    0.35
    下载附件
    0.35
     Than
    0.34
     THAN
    0.32
    voer
    0.32
    THAN
    0.31
    Act Density 0.133%

    No Known Activations