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

    Neuronpedia

    INDEX
    Explanations

    numeric values and references to measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Opr
    -0.18
    isan
    -0.16
    .dtd
    -0.15
    247
    -0.15
    antz
    -0.15
    uel
    -0.15
    agr
    -0.15
    âĢĮداÙĨ
    -0.14
    ~~
    -0.14
    aghan
    -0.14
    POSITIVE LOGITS
    _unset
    0.16
    uchen
    0.15
    allet
    0.14
    UTE
    0.14
    _proto
    0.13
    LAY
    0.13
     Bilg
    0.13
    lez
    0.13
    ché
    0.13
    gré
    0.13
    Act Density 0.004%

    No Known Activations