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

    Neuronpedia

    INDEX
    Explanations

    references to learning from past experiences and making improvements for the future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     كم
    -0.44
    jface
    -0.44
    ero
    -0.41
    AddTagHelper
    -0.41
    eral
    -0.40
    vær
    -0.40
     sehari
    -0.39
     talks
    -0.39
    linspace
    -0.39
    onUpdate
    -0.38
    POSITIVE LOGITS
     فريبيس
    0.78
    存于互联网档案馆
    0.77
     aprende
    0.73
     Lessons
    0.73
    lessons
    0.70
    DebuggerNonUser
    0.68
     lessons
    0.67
    HideFlags
    0.66
    ItemBackground
    0.65
     kasarigan
    0.65
    Act Density 0.204%

    No Known Activations