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

    Neuronpedia

    INDEX
    Explanations

    references to supplementary materials in a scientific context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Reſ
    -1.08
    Билгалдахарш
    -1.05
     iſt
    -0.98
     Efq
    -0.97
     CreateTagHelper
    -0.97
     Monfieur
    -0.97
    ſelf
    -0.96
     transfieras
    -0.96
     Houſe
    -0.96
     Anſ
    -0.95
    POSITIVE LOGITS
     (
    0.57
    .
    0.56
     
    0.56
    -
    0.50
    ’
    0.47
      
    0.47
     so
    0.46
       
    0.45
    ↵↵
    0.44
     per
    0.43
    Act Density 0.002%

    No Known Activations