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

    Neuronpedia

    INDEX
    Explanations

    Foreign

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the word “foreign” (especially at the start of title‐style phrases like “Foreign Exchange,” “Foreign Aid,” “Foreign Minister,” etc.).

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

    references to foreign entities or aspects related to international affairs.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    CHEDULE
    -0.07
    Spl
    -0.07
     STA
    -0.07
     JL
    -0.07
    inkle
    -0.07
    Lit
    -0.07
    33
    -0.07
    Thu
    -0.07
     call
    -0.07
     SYSTEM
    -0.07
    POSITIVE LOGITS
     foreign
    0.14
     Foreign
    0.13
    foreign
    0.12
    Foreign
    0.11
     FOREIGN
    0.09
     foreigners
    0.08
     abroad
    0.07
     QDom
    0.07
    _foreign
    0.07
     overseas
    0.07
    Act Density 0.008%

    No Known Activations