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

    Neuronpedia

    INDEX
    Explanations

    phrases that quantify or make comparisons about various subjects or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berdayakan
    -0.70
     purpoſe
    -0.62
    достатки
    -0.61
    Παραπομπές
    -0.61
    umumkan
    -0.60
    holdet
    -0.57
     tantum
    -0.56
     Équipe
    -0.56
    věř
    -0.55
    ✭✭
    -0.54
    POSITIVE LOGITS
     sẻ
    0.74
    ViewFeatures
    0.72
    \{\\
    0.65
    WindowConstants
    0.61
    ății
    0.61
     earliest
    0.60
     unei
    0.59
    ThroughAttribute
    0.58
    /**
    0.57
     nahilalakip
    0.57
    Act Density 0.235%

    No Known Activations