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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations and landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNT
    -0.14
     Gü
    -0.14
    alus
    -0.14
     neighborhood
    -0.14
    ÏĦια
    -0.14
     Dog
    -0.14
    anel
    -0.13
    ÎķÎ¥
    -0.13
    _IMPL
    -0.13
    BEGIN
    -0.13
    POSITIVE LOGITS
     Canada
    0.32
    Canada
    0.29
     Canadian
    0.28
     Canadians
    0.28
     canada
    0.27
     Toronto
    0.26
     canadian
    0.26
    Toronto
    0.25
     Ontario
    0.24
     Ottawa
    0.24
    Act Density 0.837%

    No Known Activations