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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific regions or areas

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ertodd
    -1.02
    vous
    -0.97
    selage
    -0.87
    --+
    -0.83
    bats
    -0.81
    uden
    -0.80
    enment
    -0.77
    pload
    -0.76
    gerald
    -0.74
    cellent
    -0.74
    POSITIVE LOGITS
    ities
    0.95
    ized
    0.95
     offices
    0.89
    ization
    0.86
     parks
    0.86
     capitals
    0.85
    ised
    0.84
     governments
    0.84
     regions
    0.83
    izing
    0.82
    Act Density 0.016%

    No Known Activations