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

    Neuronpedia

    INDEX
    Explanations

    references to modeling or mode-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.52
    Annotation
    -0.49
     برانيه
    -0.42
    annotation
    -0.42
    Servlet
    -0.42
    脚注の使い方
    -0.41
     annotation
    -0.40
    Footnotes
    -0.40
    ölkerung
    -0.40
     formule
    -0.40
    POSITIVE LOGITS
    Mode
    1.93
    MODE
    1.77
    mode
    1.57
     Mode
    1.37
     MODE
    1.28
    setMode
    1.05
     Modelling
    0.96
    Modelling
    0.93
     modelling
    0.90
     Modeling
    0.85
    Act Density 0.093%

    No Known Activations