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

    Neuronpedia

    INDEX
    Explanations

    angel

    np_max-act · gemini-2.0-flash

    references to angels and divine beings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on occurrences of “angel” (including its plural and derivative forms) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _winner
    -0.07
     واست
    -0.07
     Output
    -0.06
     Precision
    -0.06
     tavern
    -0.06
     marsh
    -0.06
     substr
    -0.06
    考
    -0.06
    862
    -0.06
     Wood
    -0.06
    POSITIVE LOGITS
     Angel
    0.14
     angel
    0.12
    Angel
    0.11
     angels
    0.09
     Angels
    0.08
     GAL
    0.07
     helicopters
    0.07
    aphael
    0.07
     Halo
    0.07
     symbol
    0.07
    Act Density 0.005%

    No Known Activations