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

    Neuronpedia

    INDEX
    Explanations

    names of political figures and concepts related to government and legislation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    perty
    -1.15
    gee
    -1.08
    pler
    -1.05
    puter
    -1.02
    asonable
    -1.01
    pper
    -0.98
    bec
    -0.97
    plete
    -0.96
    merce
    -0.96
    cer
    -0.96
    POSITIVE LOGITS
    sburgh
    1.41
    s
    1.27
    enance
    1.20
    rates
    1.12
    schild
    1.09
    sburg
    1.08
    rating
    1.07
    NESS
    1.00
    ees
    0.97
    rans
    0.97
    Act Density 2.607%

    No Known Activations