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

    Neuronpedia

    INDEX
    Explanations

    commands or directives involving the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    told to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beyond
    -0.46
     насељу
    -0.46
     tiguan
    -0.43
    couvrir
    -0.41
     corrid
    -0.40
     Beyond
    -0.40
    maktadır
    -0.40
     artifact
    -0.40
    出版年
    -0.39
     various
    -0.39
    POSITIVE LOGITS
     propOrder
    0.56
    OGND
    0.54
    Recomendaciones
    0.48
     apropiado
    0.48
    Consejos
    0.48
    RenderAtEndOf
    0.47
     conseillé
    0.47
    should
    0.45
     Advice
    0.44
     zijne
    0.44
    Act Density 0.015%

    No Known Activations