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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accusations of racism and the dynamics of political opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovaly
    -0.18
    366
    -0.16
    vyk
    -0.15
    ëĬ¥
    -0.15
    ysi
    -0.15
     Rosenstein
    -0.14
    ÑĸÑĢ
    -0.14
    lider
    -0.14
     indeb
    -0.14
    inkel
    -0.13
    POSITIVE LOGITS
     trait
    0.24
     li
    0.20
     unp
    0.18
     dangerous
    0.18
     Tra
    0.17
    li
    0.17
    trait
    0.17
     unfit
    0.17
     closet
    0.17
     coll
    0.15
    Act Density 0.160%

    No Known Activations