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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global awareness and community service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actually
    -0.57
     supposedly
    -0.55
     вроде
    -0.53
     hit
    -0.53
    4
    -0.52
     really
    -0.52
     sneaky
    -0.52
     tricky
    -0.51
     
    -0.51
     pretty
    -0.51
    POSITIVE LOGITS
    InjectAttribute
    0.97
     Catawiki
    0.96
    Personensuche
    0.95
     autorytatywna
    0.94
    出版年
    0.93
    AndEndTag
    0.92
     تضيفلها
    0.89
    featureID
    0.88
    ValueStyle
    0.88
     pleaſure
    0.87
    Act Density 0.214%

    No Known Activations