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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uality
    -0.73
    lihood
    -0.71
     Alonso
    -0.71
     Norn
    -0.70
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.67
    LY
    -0.65
    âĹ¼
    -0.64
     Guerrero
    -0.64
     oppos
    -0.63
     Bucc
    -0.62
    POSITIVE LOGITS
    iard
    1.45
    top
    1.18
    tops
    1.14
    side
    1.11
    yer
    1.02
    bill
    1.02
    castle
    0.99
    hog
    0.97
    marks
    0.92
    fort
    0.91
    Act Density 0.024%

    No Known Activations