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

    Neuronpedia

    INDEX
    Explanations

    references to dates and figures in the context of reports or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ++++++++++++++++
    -0.91
    ^^^^^^^^
    -0.90
     isComment
    -0.77
     Tartar
    -0.76
    enem
    -0.75
    \}\\
    -0.75
    '])){
    -0.74
    ционной
    -0.73
    Information
    -0.72
    equation
    -0.72
    POSITIVE LOGITS
    httphttps
    1.06
     Champs
    1.03
     Atty
    0.96
     Pollut
    0.92
     تانيه
    0.87
     Assn
    0.87
    ltä
    0.86
     gotta
    0.86
     pitié
    0.86
    QUADS
    0.84
    Act Density 0.314%

    No Known Activations