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

    Neuronpedia

    INDEX
    Explanations

    terms related to rights and benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kraj
    -0.15
    izr
    -0.15
    oley
    -0.15
     nackte
    -0.14
    _makeConstraints
    -0.14
     DOI
    -0.14
    åŁĭ
    -0.14
    eme
    -0.14
    otland
    -0.14
     ساÙĦÙĩ
    -0.14
    POSITIVE LOGITS
    iges
    0.16
    æĭ
    0.14
    858
    0.14
    Coach
    0.14
    amura
    0.14
    269
    0.14
     barg
    0.14
    forth
    0.14
    /disable
    0.14
    ton
    0.13
    Act Density 0.004%

    No Known Activations