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

    Neuronpedia

    INDEX
    Explanations

    phrases that express strong opinions or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ousal
    -0.36
    amaño
    -0.35
    MigrationBuilder
    -0.33
     пом
    -0.32
     kon
    -0.32
    arakat
    -0.32
    bil
    -0.32
     inst
    -0.32
     закры
    -0.30
     गर्
    -0.30
    POSITIVE LOGITS
     truly
    0.98
    truly
    0.94
     realmente
    0.86
     gerçekten
    0.85
     genuinely
    0.85
     verdaderamente
    0.84
     really
    0.84
    really
    0.82
     veramente
    0.82
     réellement
    0.79
    Act Density 0.313%

    No Known Activations