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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and their association with emotions or actions

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

    X が

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     []).
    -0.59
    jspb
    -0.58
     onOptions
    -0.52
    ImageContext
    -0.51
    featureID
    -0.46
     оригіналу
    -0.45
     betweenstory
    -0.45
    HtmlAttribute
    -0.45
    ']}
    -0.44
    "]}
    -0.44
    POSITIVE LOGITS
     linho
    0.46
    Duración
    0.42
    WebElementEntity
    0.35
     Tamaño
    0.35
    tilhar
    0.34
     crochê
    0.34
     verdaderamente
    0.33
    したのが
    0.33
     températures
    0.33
     metales
    0.33
    Act Density 0.049%

    No Known Activations