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

    Neuronpedia

    INDEX
    Explanations

    mentions of controversial or sensitive political and social issues related to freedom, justice, and human rights

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     WD
    -0.77
    æ©
    -0.73
    anke
    -0.70
    cold
    -0.68
    drops
    -0.67
    buck
    -0.65
     Rockefeller
    -0.65
     Rober
    -0.65
    adobe
    -0.64
     Vaugh
    -0.64
    POSITIVE LOGITS
    ophobic
    1.19
    ophobia
    1.10
    abad
    1.05
     Brotherhood
    0.99
     supremacist
    0.97
     cleric
    0.94
    istani
    0.94
     fundamentalist
    0.93
     supremacists
    0.92
    ophob
    0.92
    Act Density 0.590%

    No Known Activations