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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and cabinet appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barack
    -0.23
     Obama
    -0.18
    Obama
    -0.15
    aurus
    -0.15
     xrange
    -0.15
     Holder
    -0.14
    orsi
    -0.14
     barg
    -0.14
     Vel
    -0.14
     Zimmerman
    -0.14
    POSITIVE LOGITS
     Trump
    0.20
     Pruitt
    0.20
    Trump
    0.20
     DeV
    0.18
     rollback
    0.17
     Gors
    0.16
     Bannon
    0.16
    leta
    0.16
     Pompeo
    0.15
     Scalia
    0.15
    Act Density 0.027%

    No Known Activations