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

    Neuronpedia

    INDEX
    Explanations

    boilerplate or formatting characters used in programming or technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stesso
    -0.71
     staden
    -0.65
     stessa
    -0.65
     ہی
    -0.62
     medes
    -0.56
     itself
    -0.55
     saites
    -0.54
     död
    -0.54
     courants
    -0.53
     appunto
    -0.53
    POSITIVE LOGITS
     Paglinawan
    1.26
     kaarangay
    1.15
    <bos>
    1.11
     >=",
    1.04
    contentLoaded
    1.01
     podjela
    0.90
     Савезне
    0.88
     <>",
    0.87
     Roskov
    0.79
    Diwedd
    0.76
    Act Density 0.413%

    No Known Activations