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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and cultural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     коÑĢол
    -0.18
    à¥Į
    -0.16
     apartheid
    -0.15
    -Saharan
    -0.14
     ÐĶжон
    -0.14
     ÐĿÑĸ
    -0.14
     Salvador
    -0.14
     Garc
    -0.14
     Bucc
    -0.13
     Beans
    -0.13
    POSITIVE LOGITS
     Russia
    0.61
     Russian
    0.60
     Moscow
    0.57
     Russians
    0.54
    Russian
    0.52
    Russia
    0.51
     russian
    0.50
     Putin
    0.47
     Kremlin
    0.45
    ä¿Ħ
    0.45
    Act Density 0.711%

    No Known Activations