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

    Neuronpedia

    INDEX
    Explanations

    references to data rows in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     majeur
    -0.95
    ))->
    -0.86
    */),
    -0.82
     ruines
    -0.80
     virtù
    -0.79
    Anhalt
    -0.78
     &___
    -0.77
    plin
    -0.76
     apprécier
    -0.75
     dernières
    -0.74
    POSITIVE LOGITS
     row
    1.87
     Row
    1.86
     rows
    1.76
    row
    1.67
    Row
    1.66
     ROW
    1.65
     Rows
    1.51
    rows
    1.49
    ROW
    1.49
    Rows
    1.41
    Act Density 0.026%

    No Known Activations