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

    Neuronpedia

    INDEX
    Explanations

    discourse markers and phrases indicating uncertainty or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.92
    writeFieldEnd
    -0.81
     GenerationType
    -0.78
    ніципалі
    -0.72
     BoxDecoration
    -0.70
    aarrggbb
    -0.70
     चीज़ों
    -0.68
    
    -0.67
    IsPostBack
    -0.65
    PerformLayout
    -0.64
    POSITIVE LOGITS
     about
    1.00
     nisso
    0.99
     thereof
    0.89
     dafür
    0.78
     therefor
    0.77
    about
    0.76
     siitä
    0.72
    对此
    0.71
    About
    0.71
     therewith
    0.69
    Act Density 0.326%

    No Known Activations