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

    Neuronpedia

    INDEX
    Explanations

    numerical values and associated formatting in mathematical or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [toxicity=0]
    -0.41
    <eos>
    -0.34
    <i>
    -0.29
    1
    -0.28
     Gerechtigkeit
    -0.28
    <b>
    -0.27
    2
    -0.26
     kaybet
    -0.26
     Weiterbildung
    -0.25
     Versammlung
    -0.24
    POSITIVE LOGITS
    SequentialGroup
    1.26
     مشين
    1.13
     ब्रेकडाउन
    1.10
     فريبيس
    1.09
     propOrder
    1.07
    Personendaten
    1.07
    ValueStyle
    1.05
    LookAnd
    1.03
     كومونز
    1.01
     autorytatywna
    0.99
    Act Density 0.841%

    No Known Activations