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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals, possibly relevant in a political context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names associated with immigration or humanitarian issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORED
    -0.87
    ãģ¦
    -0.77
    stood
    -0.75
    Interstitial
    -0.74
    flies
    -0.72
    earable
    -0.71
    20439
    -0.71
    ships
    -0.70
    payer
    -0.68
    oral
    -0.68
    POSITIVE LOGITS
     Kru
    1.10
     Klux
    0.98
    ijn
    0.97
    gment
    0.84
    Äį
    0.83
    ven
    0.81
    ppel
    0.80
    sts
    0.79
    ques
    0.78
    uth
    0.77
    Act Density 0.010%

    No Known Activations