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

    Neuronpedia

    INDEX
    Explanations

    terms related to racial issues and injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.81
     ſche
    -0.71
     ſeveral
    -0.69
     Majefty
    -0.68
     Jefus
    -0.68
     Nimbus
    -0.68
    цездатний
    -0.67
    MessageOf
    -0.67
     ―――――
    -0.67
     itſelf
    -0.65
    POSITIVE LOGITS
    부터
    0.63
     racial
    0.60
    RegressionTest
    0.59
     pol
    0.59
     Inn
    0.55
     CURIAM
    0.52
     Ku
    0.51
     Racial
    0.51
     Pol
    0.51
    racial
    0.50
    Act Density 2.113%

    No Known Activations