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

    Neuronpedia

    INDEX
    Explanations

    terminology related to configuration and operational performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ‘
    -0.67
     “
    -0.65
    Билгалдахарш
    -0.56
     eben
    -0.55
    ’
    -0.54
     wasn
    -0.52
     Indeed
    -0.52
     indeed
    -0.52
    gridx
    -0.52
     big
    -0.51
    POSITIVE LOGITS
     pleaſure
    1.08
     ſche
    0.96
     fubject
    0.93
     purpoſe
    0.93
     houſe
    0.93
     auffi
    0.89
     neceſſ
    0.88
     Monfieur
    0.88
     ſtate
    0.86
     myſelf
    0.86
    Act Density 0.411%

    No Known Activations