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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating preference or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.46
     island
    -0.46
     propOrder
    -0.46
    BeginInit
    -0.45
    TintMode
    -0.42
    expandindo
    -0.41
    island
    -0.41
    🔕
    -0.40
    MessageTagHelper
    -0.40
    Island
    -0.39
    POSITIVE LOGITS
     zamiast
    0.61
    而非
    0.60
    而不是
    0.56
    IsContent
    0.54
     anstatt
    0.54
    principalColumn
    0.47
     právě
    0.47
    awtextra
    0.47
     eikä
    0.46
     gynhyrchwyd
    0.46
    Act Density 0.296%

    No Known Activations