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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "detail."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    got
    -0.17
    .uk
    -0.16
    aign
    -0.15
     Lump
    -0.15
    aging
    -0.15
    adian
    -0.15
    خاÙĨÙĩ
    -0.15
    cribe
    -0.15
    uments
    -0.15
    eyse
    -0.15
    POSITIVE LOGITS
    led
    0.24
    ียà¸Ķ
    0.19
    /detail
    0.19
    itarian
    0.18
    -rich
    0.17
    mente
    0.17
    .Detail
    0.17
    istic
    0.17
    -oriented
    0.17
    dehyde
    0.17
    Act Density 0.030%

    No Known Activations