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

    Neuronpedia

    INDEX
    Explanations

    references to individual people and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ont
    -0.21
     Portsmouth
    -0.20
     Ont
    -0.19
     Suffolk
    -0.19
     Ontario
    -0.19
     Rutgers
    -0.18
    Ohio
    -0.18
     Ocean
    -0.18
    Toronto
    -0.18
     Rhode
    -0.17
    POSITIVE LOGITS
     Alberta
    0.47
    Albert
    0.44
     Calgary
    0.42
     Edmonton
    0.39
     Albert
    0.39
     AB
    0.31
     Alta
    0.29
     Oilers
    0.28
     Alberto
    0.27
    [idx
    0.26
    Act Density 0.115%

    No Known Activations