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

    Neuronpedia

    INDEX
    Explanations

    technical specifications related to measurements and performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.32
     half
    -0.32
     set
    -0.30
     involved
    -0.30
    vad
    -0.28
     present
    -0.27
     meter
    -0.27
     was
    -0.27
     Bag
    -0.26
     league
    -0.26
    POSITIVE LOGITS
     ModelExpression
    0.84
    RectangleBorder
    0.70
     kasarigan
    0.68
    MessageTagHelper
    0.68
    Unlimited
    0.68
     limitless
    0.66
    mögen
    0.66
    unlimited
    0.65
     ilimit
    0.65
     vermogen
    0.64
    Act Density 0.504%

    No Known Activations