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

    Neuronpedia

    INDEX
    Explanations

    references to political investigations and the associated figures involved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reso
    -0.16
    ühr
    -0.15
    (STD
    -0.15
     ranger
    -0.15
    alc
    -0.15
    /ref
    -0.15
     Keller
    -0.14
    vie
    -0.14
    dess
    -0.14
     Lyon
    -0.14
    POSITIVE LOGITS
     Russians
    0.22
     Russian
    0.21
     campaign
    0.21
     Manafort
    0.20
     Campaign
    0.20
     foreign
    0.19
     Russia
    0.19
     Steele
    0.19
     Trump
    0.19
     Foreign
    0.19
    Act Density 0.022%

    No Known Activations