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

    Neuronpedia

    INDEX
    Explanations

    segments of text related to last or most recent entries

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.88
     nahilalakip
    -0.81
    berdayakan
    -0.78
    parsedMessage
    -0.78
     للمعارف
    -0.75
     otomatig
    -0.72
     viewDidLoad
    -0.72
    Composable
    -0.71
    awtextra
    -0.71
    DockStyle
    -0.70
    POSITIVE LOGITS
    last
    1.91
    LAST
    1.05
    lasts
    0.94
    las
    0.67
    lasty
    0.58
    ラスト
    0.56
    ask
    0.55
    lad
    0.53
     Last
    0.53
    atur
    0.52
    Act Density 0.004%

    No Known Activations