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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.64
     D
    -0.50
     a
    -0.49
     an
    -0.49
     the
    -0.49
     H
    -0.47
    es
    -0.45
    GroupBox
    -0.44
     at
    -0.44
    of
    -0.44
    POSITIVE LOGITS
     Roskov
    1.04
     purpoſe
    1.00
     myſelf
    0.97
     itſelf
    0.96
    出版年
    0.90
     архивлан
    0.89
     lenker
    0.88
     ſeveral
    0.88
    findpost
    0.87
     ſy
    0.86
    Act Density 0.007%

    No Known Activations