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

    Neuronpedia

    INDEX
    Explanations

    output statements in code, specifically those that print or display variable values and messages

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

    Code, namespaces, or special characters

    np_acts-logits-general · gemini-2.0-flash

    output operator <<

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mil
    -0.55
    JKLM
    -0.52
     ${
    -0.49
    χα
    -0.48
    mil
    -0.48
    ${
    -0.47
    ganos
    -0.47
    作
    -0.47
    MIL
    -0.46
    kah
    -0.46
    POSITIVE LOGITS
     <<
    1.19
    Personensuche
    0.97
    ]<<
    0.94
    )<<
    0.94
    <<
    0.93
    ()<<
    0.87
    <<(
    0.78
    ఔ
    0.72
    AccessorTable
    0.67
    帖最后由
    0.63
    Act Density 0.071%

    No Known Activations