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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roosevelt
    -0.18
     Amerikan
    -0.15
     Roose
    -0.15
    scribed
    -0.14
    ุล
    -0.14
    otas
    -0.14
    753
    -0.14
    mund
    -0.14
     Kapoor
    -0.14
     Gotham
    -0.14
    POSITIVE LOGITS
     Representative
    0.25
     Cond
    0.23
     Rah
    0.23
     Ann
    0.20
     Pat
    0.20
     Rand
    0.20
     Rep
    0.20
     Strom
    0.20
     Ari
    0.20
     Rush
    0.19
    Act Density 0.272%

    No Known Activations