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

    Neuronpedia

    INDEX
    Explanations

    discussions related to current events, politics, and social issues on Twitter

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cale
    -1.08
     cumbers
    -1.06
     predec
    -1.05
    arantine
    -1.02
    phia
    -1.01
    achus
    -0.99
     unnecess
    -0.97
    vasive
    -0.97
    reditary
    -0.95
    idious
    -0.93
    POSITIVE LOGITS
     09
    1.27
     06
    1.25
     03
    1.25
     04
    1.25
     05
    1.25
     07
    1.24
     02
    1.23
     01
    1.20
     08
    1.20
     2017
    1.16
    Act Density 0.606%

    No Known Activations