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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation and functionality of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.59
     InputDecoration
    -0.51
    ftagPool
    -0.48
    نز
    -0.46
    FML
    -0.46
    HideFlags
    -0.46
    روابط
    -0.46
    ábbi
    -0.45
    heiz
    -0.45
    VideoCapture
    -0.45
    POSITIVE LOGITS
    0.93
     kasarigan
    0.80
    tvguidetime
    0.70
     ProtoMessage
    0.64
     therefore
    0.60
     ComVisible
    0.57
     AssemblyVersion
    0.57
    esterday
    0.57
     surla
    0.56
    therefore
    0.55
    Act Density 0.920%

    No Known Activations