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

    Neuronpedia

    INDEX
    Explanations

    blockquotes and quoted text

    oai_token-act-pair · gemini-2.0-flash

    words with specific formatting or styles

    np_token-act-pair-logits · gpt-4o-mini

    HTML and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -1.03
     d
    -1.01
     R
    -0.94
     Le
    -0.94
     B
    -0.93
     t
    -0.92
     di
    -0.91
     b
    -0.91
     to
    -0.90
     s
    -0.90
    POSITIVE LOGITS
     itſelf
    1.84
     myſelf
    1.52
     Houſe
    1.52
     Shakspeare
    1.50
     Jefus
    1.46
     Monfieur
    1.46
     Anſ
    1.45
     houſe
    1.43
     pleaſure
    1.41
    ſelf
    1.40
    Act Density 2.986%

    No Known Activations