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

    Neuronpedia

    INDEX
    Explanations

    terms related to political discourse and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.72
    Espèce
    -0.72
     يتيمه
    -0.68
     GenerationType
    -0.66
     éprou
    -0.63
     tasche
    -0.62
    وردار
    -0.62
    DockStyle
    -0.61
     edelstahl
    -0.61
     enfans
    -0.60
    POSITIVE LOGITS
     politics
    1.18
     political
    1.17
     Politics
    1.09
    Politics
    1.05
     Political
    1.02
     politician
    1.02
    political
    1.01
     politicians
    1.00
     politik
    0.99
    politics
    0.98
    Act Density 1.040%

    No Known Activations