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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or expressions of doubt and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kesha
    -0.74
     regular
    -0.65
     Regular
    -0.61
     tra
    -0.60
     समीक्षक
    -0.59
     Leger
    -0.58
    udent
    -0.56
     Wiley
    -0.53
     mando
    -0.53
    LANTA
    -0.51
    POSITIVE LOGITS
     hiér
    0.73
     handker
    0.72
    تقاوى
    0.66
     kife
    0.65
    下载附件
    0.65
    saraba
    0.65
     تضيفلها
    0.64
    følgelig
    0.64
    tagHelperRunner
    0.62
     InputDecoration
    0.62
    Act Density 0.106%

    No Known Activations