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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical instructions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    words indicating conditions or factors related to success or efficacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surname
    -0.63
    lled
    -0.62
     quarrel
    -0.62
     clos
    -0.61
     retracted
    -0.60
     mysteriously
    -0.60
    qus
    -0.59
    lock
    -0.58
     blank
    -0.58
    iatus
    -0.58
    POSITIVE LOGITS
     Specifically
    0.89
     Especially
    0.84
     Ideally
    0.84
    enegger
    0.77
     Currently
    0.75
     Ultimately
    0.73
     leveraging
    0.73
     Whereas
    0.71
     Hopefully
    0.71
     maximizing
    0.71
    Act Density 0.667%

    No Known Activations