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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transitions and upcoming events or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ']):
    -0.43
    zzo
    -0.42
    晚上
    -0.42
    zeb
    -0.41
    ufig
    -0.41
    éis
    -0.41
    CodeAnalysis
    -0.41
     saj
    -0.40
     romain
    -0.39
    ham
    -0.39
    POSITIVE LOGITS
    SequentialGroup
    0.96
    expandindo
    0.95
    تقاوى
    0.94
    ंदीखरीदारी
    0.91
     виправивши
    0.90
    IUrlHelper
    0.86
     propOrder
    0.84
     betweenstory
    0.82
    ValueStyle
    0.82
    NameInMap
    0.81
    Act Density 0.171%

    No Known Activations