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

    Neuronpedia

    INDEX
    Explanations

    expressions of political dissatisfaction and calls for change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GC
    -0.16
    ingu
    -0.15
    ³
    -0.15
    iff
    -0.14
    holm
    -0.14
     partisan
    -0.14
    rlen
    -0.13
     Carp
    -0.13
     curated
    -0.13
    .ds
    -0.13
    POSITIVE LOGITS
     bourgeois
    0.24
    bour
    0.21
     capitalists
    0.21
    capital
    0.20
     capitalist
    0.20
     contradictions
    0.19
    Capital
    0.19
     Capital
    0.19
     imperial
    0.19
     workers
    0.19
    Act Density 0.090%

    No Known Activations