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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ãĥķãĤ©
    -0.68
    Specific
    -0.68
    uckles
    -0.66
    Panel
    -0.66
     Advertisement
    -0.65
    pread
    -0.64
    ======
    -0.64
    âķIJ
    -0.60
    Present
    -0.60
    overe
    -0.60
    POSITIVE LOGITS
    forts
    0.90
     overlooking
    0.84
    yards
    0.83
     USS
    0.78
     whence
    0.77
     overseen
    0.74
     where
    0.74
     of
    0.74
     Cheong
    0.73
     nearest
    0.73
    Act Density 0.344%

    No Known Activations