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

    Neuronpedia

    INDEX
    Explanations

    references to authoritarianism and political oppression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Agamemnon
    -0.68
     Shakspeare
    -0.68
     propOrder
    -0.66
     initComponents
    -0.65
     Custer
    -0.63
    脚注の使い方
    -0.62
    labus
    -0.62
    NewUrlParser
    -0.61
     Flanders
    -0.60
     Cleopatra
    -0.58
    POSITIVE LOGITS
     diss
    0.91
     freedom
    0.82
     Freedom
    0.81
     opposition
    0.81
    Freedom
    0.76
     freedoms
    0.76
     dissent
    0.73
     political
    0.73
     FREEDOM
    0.71
    freedom
    0.70
    Act Density 0.216%

    No Known Activations