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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash

    This neuron detects the assistant’s stock self‐disclaimer phrasing (e.g. the “As an AI language model…” and related first‐person statements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    language related to perceived political bias and comparative assessments of political parties.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     writ
    -0.07
    lobby
    -0.06
    �
    -0.06
     plugs
    -0.06
     MF
    -0.06
    Quit
    -0.06
    編
    -0.06
     embar
    -0.06
    :type
    -0.06
    getto
    -0.06
    POSITIVE LOGITS
    _CHANNEL
    0.07
     professors
    0.07
    ,state
    0.06
     Birleşik
    0.06
    baş
    0.06
    .Groups
    0.06
    Die
    0.06
     Reserved
    0.06
    $html
    0.06
     columnName
    0.06
    Act Density 0.114%

    No Known Activations