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

    Neuronpedia

    INDEX
    Explanations

    elements related to authority and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WillAppear
    -0.93
     kasarigan
    -0.90
    évaluateur
    -0.86
     CreateTagHelper
    -0.85
     فريبيس
    -0.80
     >=",
    -0.80
    StoryboardSegue
    -0.80
    RectangleBorder
    -0.78
    béco
    -0.78
    PerformLayout
    -0.78
    POSITIVE LOGITS
     young
    0.48
     and
    0.47
    trans
    0.46
     W
    0.45
     (-
    0.43
    ,
    0.43
    Trans
    0.41
     in
    0.41
     trans
    0.41
    j
    0.41
    Act Density 0.130%

    No Known Activations