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

    Neuronpedia

    INDEX
    Explanations

    references to privilege and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalTable
    -1.02
    +#+#
    -0.91
     contextLoads
    -0.88
    IUrlHelper
    -0.87
    日閲覧
    -0.84
    ViewFeatures
    -0.81
     linkovi
    -0.80
     Roskov
    -0.75
     odkazy
    -0.73
    Diweddarwch
    -0.72
    POSITIVE LOGITS
     bo
    0.45
    kla
    0.41
     Bo
    0.41
    ija
    0.40
    fontein
    0.38
    edded
    0.38
    awtextra
    0.38
     giro
    0.38
    gester
    0.37
     BO
    0.36
    Act Density 1.070%

    No Known Activations