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

    Neuronpedia

    INDEX
    Explanations

    postal abbreviations associated with geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations, particularly U.S. states and cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.85
    lihood
    -0.78
    henko
    -0.71
    andowski
    -0.69
    pour
    -0.68
    heet
    -0.67
    peat
    -0.66
    loads
    -0.66
    ror
    -0.65
    months
    -0.64
    POSITIVE LOGITS
    ARA
    0.74
     Dept
    0.72
    ./
    0.71
    JR
    0.70
    UL
    0.68
    LV
    0.68
    OTUS
    0.66
    GOP
    0.66
     Pavilion
    0.64
    ADA
    0.64
    Act Density 0.039%

    No Known Activations