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

    Neuronpedia

    INDEX
    Explanations

    references to creators or authors of various works

    oai_token-act-pair · gpt-3.5-turbo

    references to creators and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cups
    -0.74
    edu
    -0.67
    uckle
    -0.66
    uckles
    -0.66
    olor
    -0.64
    heddar
    -0.63
    zan
    -0.62
    hma
    -0.62
    earances
    -0.61
     blat
    -0.60
    POSITIVE LOGITS
     thereof
    1.16
    liest
    0.90
     of
    0.82
    iest
    0.81
    owitz
    0.71
    natureconservancy
    0.68
     portion
    0.67
     mechanism
    0.66
    stration
    0.64
    itial
    0.63
    Act Density 0.339%

    No Known Activations