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

    Neuronpedia

    INDEX
    Explanations

    references to attribute manipulation in programming contexts

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

    attr() and ATTR_ constants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.62
    pog
    -0.62
    CLC
    -0.59
     Pineda
    -0.57
     Seif
    -0.57
    ℤ
    -0.56
     Bergmann
    -0.56
     Pog
    -0.56
     Reichen
    -0.54
    SOUNDBITE
    -0.54
    POSITIVE LOGITS
    Attr
    1.70
     attr
    1.67
    attr
    1.65
     Attr
    1.60
    ATTR
    1.21
     ATTR
    1.08
    Attrs
    1.03
     attrs
    0.91
    attrs
    0.83
     attribute
    0.80
    Act Density 0.011%

    No Known Activations