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

    Neuronpedia

    INDEX
    Explanations

    references to democracy and democratic values

    oai_token-act-pair · gpt-3.5-turbo

    mentions of democratic principles or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ting
    -0.80
    thy
    -0.77
    cial
    -0.76
    thur
    -0.75
    other
    -0.75
     Painter
    -0.75
    senal
    -0.72
    ciating
    -0.69
    uality
    -0.69
    balls
    -0.69
    POSITIVE LOGITS
     socialist
    1.09
     minded
    0.97
     republic
    0.96
     democratic
    0.95
     freedoms
    0.91
     rights
    0.89
     democracy
    0.88
     ideals
    0.88
     republican
    0.87
     societies
    0.85
    Act Density 0.016%

    No Known Activations