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

    Neuronpedia

    INDEX
    Explanations

    names of geographical locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    erity
    -0.94
    minded
    -0.85
     verbal
    -0.84
    hetically
    -0.83
     acron
    -0.83
    matically
    -0.83
     carbohyd
    -0.82
    ccording
    -0.81
     hiring
    -0.81
     courage
    -0.81
    POSITIVE LOGITS
     Peninsula
    1.54
     Basin
    1.46
     peninsula
    1.35
     Fields
    1.31
     Heights
    1.25
     River
    1.24
     Passage
    1.23
     Gardens
    1.22
     Islands
    1.20
     Waters
    1.18
    Act Density 1.580%

    No Known Activations