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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the beginning of sections or special formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.68
     quæ
    -0.67
     ejus
    -0.63
    AndEndTag
    -0.63
    unggulan
    -0.62
    GenerationType
    -0.62
    umumkan
    -0.62
     näin
    -0.60
     suivants
    -0.59
     enää
    -0.58
    POSITIVE LOGITS
    ngdoc
    0.72
     kasarigan
    0.61
    solt
    0.61
    ‬‬
    0.60
     opti
    0.59
    unmodifiable
    0.58
    unsaturated
    0.58
     phone
    0.58
    EDEFAULT
    0.57
     Kamar
    0.57
    Act Density 0.667%

    No Known Activations