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

    Neuronpedia

    INDEX
    Explanations

    instances of text marked with a specific symbol "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    indicators of official reports or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boro
    -0.83
     Shelby
    -0.73
     Rutherford
    -0.72
    kees
    -0.70
     Floyd
    -0.70
     dime
    -0.69
     wardrobe
    -0.69
    phia
    -0.68
     amps
    -0.68
     treasure
    -0.66
    POSITIVE LOGITS
    ccording
    1.21
    However
    1.10
    Meanwhile
    1.06
    According
    1.05
    Official
    1.04
    Translation
    1.04
    Sources
    1.01
    Pakistan
    1.00
    Moreover
    1.00
    Around
    0.97
    Act Density 0.609%

    No Known Activations