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

    Neuronpedia

    INDEX
    Explanations

    references to locations, particularly those to the south of a specified area

    oai_token-act-pair · gpt-3.5-turbo

    references to locations, particularly those described as being "south of" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.81
    Http
    -0.71
    Versions
    -0.70
    Choice
    -0.69
    Password
    -0.69
     istg
    -0.67
    iatric
    -0.66
    itiveness
    -0.64
    appropriate
    -0.64
    PDF
    -0.63
    POSITIVE LOGITS
     Baghdad
    0.95
     Brisbane
    0.84
     Lima
    0.82
     Mosul
    0.82
     Aleppo
    0.81
     Perth
    0.81
     Bethlehem
    0.80
     Florence
    0.79
     Interstate
    0.79
     Louisville
    0.78
    Act Density 0.044%

    No Known Activations