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

    Neuronpedia

    INDEX
    Explanations

    comparisons or examples in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LayoutManager
    -0.16
    èn
    -0.15
    eken
    -0.15
    //{{
    -0.15
     imaginary
    -0.14
     太
    -0.14
    LIKELY
    -0.14
    ůvod
    -0.14
    ãĥ¥ãĥ¼
    -0.14
    REA
    -0.14
    POSITIVE LOGITS
    :
    0.15
    tgt
    0.14
    echa
    0.14
     oz
    0.14
     prosec
    0.13
    amet
    0.13
    té
    0.13
    çķ
    0.13
    eless
    0.13
    ument
    0.13
    Act Density 0.055%

    No Known Activations