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

    Neuronpedia

    INDEX
    Explanations

    content related to political ideologies, particularly focusing on fascism and Marxism, coupled with references to specific historical events and figures, like Hitler and Mussolini, encompassing broader discussions on concepts like feminism, liberalism, conservatism, and socialism

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    parts
    -0.63
    abet
    -0.60
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.55
    umm
    -0.54
    76561
    -0.54
    emade
    -0.53
    drivers
    -0.51
    vol
    -0.51
    val
    -0.51
     CFR
    -0.51
    POSITIVE LOGITS
    anship
    0.77
     fuelled
    0.70
     perv
    0.67
    opathy
    0.66
     collided
    0.65
    ophobic
    0.65
    ophobia
    0.65
     engulfed
    0.64
    jriwal
    0.63
     influenced
    0.63
    Act Density 9.777%

    No Known Activations