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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating size, quantity, or degree

    oai_token-act-pair · gpt-3.5-turbo

    assertions about performance relative to expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Britann
    -0.64
    leted
    -0.61
     CRC
    -0.59
     irresistible
    -0.57
     legend
    -0.56
     DRAGON
    -0.55
     gorgeous
    -0.55
     legends
    -0.55
     ROCK
    -0.55
     forged
    -0.54
    POSITIVE LOGITS
     anymore
    1.32
     nor
    1.22
    nor
    1.06
     whatsoever
    0.93
     anywhere
    0.89
    enough
    0.88
     unless
    0.82
    yet
    0.81
     anything
    0.80
     necessarily
    0.79
    Act Density 0.792%

    No Known Activations