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

    Neuronpedia

    INDEX
    Explanations

    locations in the United States

    oai_token-act-pair · gpt-3.5-turbo

    names of U.S. states and locations within them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.64
    road
    -0.63
     robber
    -0.59
    Afee
    -0.59
     predict
    -0.57
    mania
    -0.57
    merce
    -0.56
     Doodle
    -0.54
     Crimean
    -0.54
    peat
    -0.54
    POSITIVE LOGITS
    .,
    0.86
    ;;;;;;;;;;;;
    0.85
    soDeliveryDate
    0.75
    .;
    0.70
    ometown
    0.69
    quartered
    0.68
    ,,
    0.67
    ,...
    0.66
     native
    0.63
    nice
    0.61
    Act Density 0.083%

    No Known Activations