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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to political positions and offices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FormsModule
    -0.66
    MessageTagHelper
    -0.63
    ölkerung
    -0.59
    RenderAtEndOf
    -0.57
     فريبيس
    -0.56
     asiatique
    -0.56
    belec
    -0.54
    ⅰ
    -0.54
     Alha
    -0.53
     pédagogique
    -0.52
    POSITIVE LOGITS
     position
    1.28
     positions
    1.27
     roles
    1.05
     role
    1.03
     Positions
    1.01
     Position
    0.98
    positions
    0.92
    position
    0.91
    Positions
    0.90
    Position
    0.89
    Act Density 0.319%

    No Known Activations