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

    Neuronpedia

    INDEX
    Explanations

    locations with historical or cultural significance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.66
    rists
    -0.65
    azeera
    -0.64
     diapers
    -0.63
     flu
    -0.62
     hairc
    -0.62
     knives
    -0.61
    otypes
    -0.61
     salesman
    -0.60
     pills
    -0.60
    POSITIVE LOGITS
     northwest
    0.94
     downtown
    0.93
     southwest
    0.93
     southwestern
    0.90
     UNESCO
    0.90
     latitude
    0.89
     footh
    0.89
     northeast
    0.88
     adjacent
    0.87
     bedrock
    0.87
    Act Density 0.306%

    No Known Activations