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

    Neuronpedia

    INDEX
    Explanations

    words related to geographic locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arabian
    -0.78
    ktop
    -0.77
     exception
    -0.72
     Flavoring
    -0.66
     Borders
    -0.64
     Compass
    -0.62
     retaining
    -0.62
     contrast
    -0.62
     exact
    -0.62
    DragonMagazine
    -0.61
    POSITIVE LOGITS
    zee
    1.05
    sama
    1.02
    fi
    1.02
    eyed
    1.00
    bang
    0.98
    bye
    0.97
    shaped
    0.97
    chan
    0.97
    gee
    0.96
    vous
    0.95
    Act Density 0.056%

    No Known Activations