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

    Neuronpedia

    INDEX
    Explanations

    references to various types of bread

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iske
    -0.15
    ocht
    -0.15
    brew
    -0.14
    ilit
    -0.14
    tte
    -0.14
    abcdefghijklmnop
    -0.14
    ot
    -0.14
    ajas
    -0.14
    asca
    -0.14
    ItemSelectedListener
    -0.13
    POSITIVE LOGITS
    sticks
    0.19
     Bread
    0.19
    winner
    0.19
     bread
    0.18
    tember
    0.17
    width
    0.17
     loaf
    0.16
    illon
    0.16
    itoris
    0.16
    iful
    0.16
    Act Density 0.013%

    No Known Activations