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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a rejection or denial of responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -1.04
     مرئيه
    -0.84
    دانشنامهٔ
    -0.83
    脚注の使い方
    -0.82
     getItemId
    -0.80
     للمعارف
    -0.79
    tvguidetime
    -0.75
    fjspx
    -0.72
     NSCoder
    -0.70
     дописавши
    -0.70
    POSITIVE LOGITS
    <bos>
    0.61
     võib
    0.47
    akyti
    0.46
     geçti
    0.43
     am
    0.43
    rija
    0.42
     hvert
    0.41
     sillä
    0.41
     daarvoor
    0.41
     zult
    0.40
    Act Density 0.358%

    No Known Activations