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

    Neuronpedia

    INDEX
    Explanations

    addresses, street names, cities, and geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FISA
    -0.69
    utsche
    -0.68
     interrog
    -0.67
     Euros
    -0.67
     notebooks
    -0.64
     pessim
    -0.64
    henko
    -0.62
     defence
    -0.62
     mistakes
    -0.62
     successes
    -0.61
    POSITIVE LOGITS
    opolis
    0.88
     Boulevard
    0.85
     Junction
    0.85
     Plaza
    0.83
     Springs
    0.80
     Harbor
    0.79
    town
    0.77
     Recreation
    0.75
    ensis
    0.72
     Streets
    0.72
    Act Density 0.443%

    No Known Activations