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

    Neuronpedia

    INDEX
    Explanations

    technical terms and references in scientific or technical writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McN
    -0.95
     WN
    -0.92
     PN
    -0.92
     FN
    -0.92
     GN
    -0.86
     Gn
    -0.85
     SNR
    -0.85
     RN
    -0.85
     CNA
    -0.84
     HN
    -0.83
    POSITIVE LOGITS
     Bamberg
    0.55
     Linde
    0.54
    Tanger
    0.52
     Tanger
    0.49
     Brandenburg
    0.48
     Longfellow
    0.48
     Humboldt
    0.48
     Stanton
    0.48
     Lindberg
    0.48
     Django
    0.47
    Act Density 1.581%

    No Known Activations