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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     bell
    -0.68
     strings
    -0.67
    ãģ®éŃĶ
    -0.65
     shutter
    -0.63
     stocking
    -0.63
     handc
    -0.63
     largeDownload
    -0.62
     glove
    -0.62
     supervised
    -0.62
     crawl
    -0.61
    POSITIVE LOGITS
    arat
    1.18
    apo
    1.02
    raq
    0.97
    uko
    0.96
    undai
    0.91
    arah
    0.90
    agra
    0.89
    az
    0.89
    ulu
    0.89
    assi
    0.89
    Act Density 0.151%

    No Known Activations