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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss comparisons and differences between subjects

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

    preceding "difference"

    np_acts-logits-general · gemini-2.0-flash

    difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    liesslich
    -0.62
    migrationBuilder
    -0.62
    ließlich
    -0.53
    processable
    -0.48
    uchungen
    -0.46
    ormány
    -0.46
     Caw
    -0.45
     Zorn
    -0.44
     يتيمه
    -0.44
     Junto
    -0.44
    POSITIVE LOGITS
     difference
    3.71
     differences
    3.47
    difference
    3.23
     Difference
    3.14
     Differences
    3.13
    Difference
    3.06
    Differences
    3.02
    differences
    2.94
     DIFFERENCE
    2.82
     différence
    2.82
    Act Density 1.209%

    No Known Activations