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

    Neuronpedia

    INDEX
    Explanations

    references to regulatory or governing bodies and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.93
     pleaſure
    -0.92
     houſe
    -0.92
     myſelf
    -0.90
     ſmall
    -0.88
     poffible
    -0.88
     ſte
    -0.83
     himſelf
    -0.81
     ſta
    -0.80
     ſtate
    -0.79
    POSITIVE LOGITS
     assurent
    0.43
     الحره
    0.40
    ies
    0.39
    park
    0.39
    の
    0.38
     }
    0.36
    κτηρισ
    0.36
    헌
    0.36
    rungsseite
    0.35
    ـ
    0.35
    Act Density 0.138%

    No Known Activations