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

    Neuronpedia

    INDEX
    Explanations

    names of streets, locations, and neighborhoods

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.78
    о
    -0.65
     litres
    -0.63
     asses
    -0.63
    ãģĦ
    -0.61
    izations
    -0.61
    arian
    -0.61
     appendix
    -0.61
    eding
    -0.60
    onom
    -0.60
    POSITIVE LOGITS
     Plaza
    1.08
     Station
    1.04
     Cemetery
    1.01
     Resort
    1.01
     Rd
    1.00
     Blvd
    0.94
     Mall
    0.94
     Massacre
    0.93
     Hotel
    0.93
     Bridge
    0.92
    Act Density 0.946%

    No Known Activations