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

    Neuronpedia

    INDEX
    Explanations

    terms related to fascism and its derivatives

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ので
    -0.82
    lanation
    -0.82
     Nabi
    -0.81
     Cyprus
    -0.80
    y
    -0.78
    RenderAtEndOf
    -0.77
    Cyprus
    -0.75
    frame
    -0.75
    testcase
    -0.74
    baran
    -0.74
    POSITIVE LOGITS
     Fas
    1.83
    Fas
    1.66
     fas
    1.59
    fas
    1.45
     FAS
    1.45
    FAS
    1.15
     Fascism
    1.05
     fascia
    1.00
     fasci
    0.94
     fascism
    0.92
    Act Density 0.002%

    No Known Activations