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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire or intent, particularly the word "want."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.93
     itſelf
    -0.90
     pleaſure
    -0.88
     Jefus
    -0.88
     ſhould
    -0.84
     himſelf
    -0.83
     ſaid
    -0.82
     reaſon
    -0.81
     greateſt
    -0.81
     ſay
    -0.80
    POSITIVE LOGITS
     no
    0.73
     None
    0.71
     nobody
    0.69
     geen
    0.69
     No
    0.67
    None
    0.66
     Not
    0.66
    no
    0.66
     none
    0.66
     nenhuma
    0.65
    Act Density 0.422%

    No Known Activations