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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to race and identity classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.84
     AssemblyProduct
    -0.79
     للمعارف
    -0.64
    SourceChecksum
    -0.63
    (!__
    -0.59
    LookAnd
    -0.59
     Horatio
    -0.57
    RefNanny
    -0.57
    AndEndTag
    -0.55
     propOrder
    -0.55
    POSITIVE LOGITS
     mukana
    0.55
     quelcon
    0.54
     sauvages
    0.54
     locaux
    0.52
     autorités
    0.50
     lenker
    0.49
    xFFFFFF
    0.49
     varandra
    0.49
     giudizio
    0.48
     muualla
    0.48
    Act Density 0.662%

    No Known Activations