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

    Neuronpedia

    INDEX
    Explanations

    concepts and language related to ideologies that emphasize collective equality and critiques of capitalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conservatism
    -0.16
    /slick
    -0.15
    orate
    -0.15
    åŁŁ
    -0.15
    bÃŃ
    -0.14
    é§IJ
    -0.14
    HH
    -0.14
    ÑĢей
    -0.14
    759
    -0.13
     tvb
    -0.13
    POSITIVE LOGITS
     worker
    0.31
     Worker
    0.30
     workers
    0.30
     ut
    0.29
     Workers
    0.27
     socialism
    0.27
    -worker
    0.27
    worker
    0.26
     Social
    0.24
    workers
    0.24
    Act Density 0.142%

    No Known Activations