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

    Neuronpedia

    INDEX
    Explanations

    words related to scientific research and reporting

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

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

    Punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Datuak
    -1.09
     kasarigan
    -1.01
     ―――――
    -0.98
     resourceCulture
    -0.98
    enderror
    -0.96
     Jefus
    -0.95
     myſelf
    -0.92
    rungsseite
    -0.91
     Мексичка
    -0.91
     becauſe
    -0.89
    POSITIVE LOGITS
     
    0.65
     "
    0.56
     (
    0.54
    ,
    0.54
     F
    0.52
     “
    0.50
      
    0.50
     '
    0.49
    .
    0.48
    ↵↵
    0.47
    Act Density 7.871%

    No Known Activations