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

    Neuronpedia

    INDEX
    Explanations

    references to events, locations, and metropolitan areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ="@+
    -0.57
    SANTA
    -0.56
     BERKELEY
    -0.56
     MASSACHUSETTS
    -0.56
     OHIO
    -0.56
    TEXAS
    -0.56
    wales
    -0.56
    ohio
    -0.55
    URBANA
    -0.55
    Surrey
    -0.54
    POSITIVE LOGITS
     Chicago
    0.42
     Atlanta
    0.40
     Boston
    0.40
     greater
    0.39
     Philadelphia
    0.38
     Toronto
    0.37
     Los
    0.36
    Cyfeiriadau
    0.34
     San
    0.33
     London
    0.33
    Act Density 0.332%

    No Known Activations