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

    Neuronpedia

    INDEX
    Explanations

    discussions about rules and regulations surrounding practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gow
    -0.69
     Catalog
    -0.66
     Spac
    -0.66
    etti
    -0.64
     brightest
    -0.64
    incinn
    -0.61
    TeX
    -0.58
    udeau
    -0.58
    bitious
    -0.58
    vae
    -0.57
    POSITIVE LOGITS
     practiced
    0.96
     whereby
    0.90
     entails
    0.78
    horse
    0.78
    ually
    0.78
     pract
    0.77
     involves
    0.73
     originated
    0.73
    uses
    0.73
     persists
    0.69
    Act Density 0.054%

    No Known Activations