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

    Neuronpedia

    INDEX
    Explanations

    sections of text that contain specific numerical or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -1.20
     betweenstory
    -1.20
    rungsseite
    -1.09
    oredCriteria
    -1.00
     autorytatywna
    -0.93
    ThroughAttribute
    -0.89
    -0.87
    IsPostBack
    -0.85
    GEBURTSDATUM
    -0.82
    sidemargin
    -0.81
    POSITIVE LOGITS
      
    0.61
    DoubleQuotes
    0.56
    <em>
    0.48
    闻言
    0.44
     ​
    0.43
    <strong>
    0.42
    ↵↵
    0.40
     (
    0.40
     &
    0.39
    ↵
    0.39
    Act Density 0.078%

    No Known Activations