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

    Neuronpedia

    INDEX
    Explanations

    parts of text containing references to historical events or political ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to historical and ideological frameworks, particularly related to socialism and Marxism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rollout
    -0.76
    glers
    -0.70
     pickups
    -0.69
     upgr
    -0.69
    daq
    -0.68
     glim
    -0.68
     rookies
    -0.67
     headsets
    -0.66
     customers
    -0.66
     sprint
    -0.65
    POSITIVE LOGITS
     Chomsky
    1.50
     Trotsky
    1.26
     Nietzsche
    1.25
     Zionism
    1.22
     Engels
    1.19
     Hegel
    1.17
     Lenin
    1.17
     Marxism
    1.17
    Lenin
    1.16
    Marx
    1.14
    Act Density 0.662%

    No Known Activations