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

    Neuronpedia

    INDEX
    Explanations

    references to rows in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     majeur
    -1.00
    ))->
    -0.93
     &___
    -0.90
    */),
    -0.88
     Monfieur
    -0.87
     pleaſure
    -0.85
    Anhalt
    -0.85
     himſelf
    -0.85
     virtù
    -0.85
     Majefty
    -0.84
    POSITIVE LOGITS
     row
    1.98
     Row
    1.94
     rows
    1.82
    row
    1.81
    Row
    1.75
     ROW
    1.65
    rows
    1.56
    ROW
    1.56
     Rows
    1.51
    Rows
    1.47
    Act Density 0.031%

    No Known Activations