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

    Neuronpedia

    INDEX
    Explanations

    locations by searching for place names and cities

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation marks, particularly periods, indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     metic
    -0.67
    ising
    -0.66
    ures
    -0.66
     companions
    -0.64
    ushi
    -0.62
    igen
    -0.62
    aved
    -0.62
    isy
    -0.61
    pecially
    -0.60
     organis
    -0.60
    POSITIVE LOGITS
     Residents
    0.82
     Rece
    0.82
     Converted
    0.81
     Dept
    0.79
     Appropriations
    0.78
     IMAGES
    0.75
     NOTE
    0.74
     Blvd
    0.74
     Photographer
    0.73
    aucuses
    0.72
    Act Density 0.045%

    No Known Activations