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

    Neuronpedia

    INDEX
    Explanations

    references to Arabic names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.30
     themſelves
    -1.07
     myſelf
    -1.04
     Efq
    -1.01
     houſe
    -0.99
     poffible
    -0.99
     Eſ
    -0.96
     pleaſure
    -0.94
     ſtate
    -0.93
     raiſ
    -0.93
    POSITIVE LOGITS
     Van
    0.80
     van
    0.75
     Von
    0.74
     von
    0.74
    ؤلاء
    0.72
     De
    0.71
     Vanden
    0.69
     ibn
    0.68
     Mc
    0.68
     Le
    0.67
    Act Density 0.249%

    No Known Activations