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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſmall
    -0.50
     greateſt
    -0.45
     pleaſure
    -0.44
    intios
    -0.44
     houſe
    -0.43
     intermédiaire
    -0.43
     termica
    -0.43
     myſelf
    -0.42
     čierna
    -0.42
     muſt
    -0.42
    POSITIVE LOGITS
     immigrants
    0.54
     immigrant
    0.54
     refugee
    0.50
     refugees
    0.49
     emigrated
    0.49
     immig
    0.48
    InteropServices
    0.47
    0.47
    immig
    0.45
     Immigrants
    0.45
    Act Density 0.325%

    No Known Activations