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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing personal opinions and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seton
    -0.60
    ftant
    -0.59
     Xamarin
    -0.58
     Weich
    -0.56
     Winding
    -0.56
    etton
    -0.56
    acherous
    -0.55
     divertimento
    -0.55
     Methuen
    -0.55
    سط
    -0.55
    POSITIVE LOGITS
     myself
    0.78
    ParallelGroup
    0.71
    دانشنامهٔ
    0.70
    IUrlHelper
    0.59
     okuyayım
    0.58
     cherchés
    0.55
    Personally
    0.55
    UnusedPrivate
    0.55
     recomiendo
    0.55
    個人的には
    0.55
    Act Density 0.346%

    No Known Activations