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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "harrier."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    بالإ
    -0.49
     вдох
    -0.48
    сне
    -0.46
    簡單
    -0.45
     together
    -0.45
     brain
    -0.45
    </thead>
    -0.44
     popular
    -0.44
    เต
    -0.44
     called
    -0.44
    POSITIVE LOGITS
    fjspx
    0.92
     المعيارى
    0.88
     <=",
    0.87
    帖最后由
    0.84
    contentLoaded
    0.78
    styleable
    0.75
     EconPapers
    0.74
     ویکی‌پدیای
    0.73
     nahilalakip
    0.71
     ExecuteAsync
    0.71
    Act Density 0.096%

    No Known Activations