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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geopolitical conflicts and territorial changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     коÑĢол
    -0.15
     Roose
    -0.15
    pill
    -0.14
     Babylon
    -0.14
     jadx
    -0.14
    afia
    -0.14
    .scalablytyped
    -0.14
    ëĭĪìķĦ
    -0.13
    çļĩ
    -0.13
     Foley
    -0.13
    POSITIVE LOGITS
     Che
    0.28
     Ing
    0.27
     Kar
    0.26
    Ing
    0.25
     Georgia
    0.25
     Mountain
    0.25
     break
    0.23
     Caucasian
    0.23
     Ab
    0.23
     separat
    0.23
    Act Density 0.019%

    No Known Activations