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

    Neuronpedia

    INDEX
    Explanations

    mentions of notable names and figures

    oai_token-act-pair · gpt-3.5-turbo

    lists of items or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oire
    -0.88
    okane
    -0.81
    orce
    -0.81
    olve
    -0.78
    idate
    -0.76
    erb
    -0.75
    tg
    -0.73
    ould
    -0.72
    orean
    -0.72
    orem
    -0.72
    POSITIVE LOGITS
     Jeremiah
    0.67
    :-
    0.66
     Martha
    0.64
    *:
    0.64
     Tay
    0.64
     Nos
    0.63
     Archangel
    0.63
     Nex
    0.62
     weddings
    0.62
    :
    0.62
    Act Density 0.128%

    No Known Activations