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

    Neuronpedia

    INDEX
    Explanations

    locations such as cities and states

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    thia
    -0.84
    riel
    -0.81
    DonaldTrump
    -0.78
    renheit
    -0.78
    cedes
    -0.77
    uria
    -0.76
    asia
    -0.74
    oldemort
    -0.72
    duty
    -0.72
    umenthal
    -0.71
    POSITIVE LOGITS
     skyline
    0.97
     metropolitan
    0.97
     Police
    0.96
     branch
    0.93
     chapter
    0.92
     legislature
    0.89
     region
    0.89
     suburbs
    0.89
     municipality
    0.88
     Evening
    0.88
    Act Density 0.180%

    No Known Activations