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

    Neuronpedia

    INDEX
    Explanations

    statements expressing personal opinions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.80
     snippetHide
    -0.73
    Vidite
    -0.73
     noDo
    -0.72
    PreferredItem
    -0.71
     Insee
    -0.68
    脚注の使い方
    -0.67
    ReusableCell
    -0.67
     gdyby
    -0.66
    :✨
    -0.65
    POSITIVE LOGITS
     surely
    0.81
     certainly
    0.76
     probably
    0.71
     then
    0.70
     automatically
    0.70
    าก็
    0.65
     will
    0.64
     automatiquement
    0.64
     sẽ
    0.62
    就会
    0.62
    Act Density 0.348%

    No Known Activations