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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advancing or progressing in a discussion or narrative

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate progress or continuation of an idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     donated
    -0.62
     stewards
    -0.61
     Donation
    -0.61
     unbeat
    -0.61
     upkeep
    -0.61
     sacrific
    -0.60
     Leilan
    -0.60
     scrim
    -0.59
     paycheck
    -0.59
     DJs
    -0.59
    POSITIVE LOGITS
     illustrate
    0.94
     quotes
    0.89
     illustrates
    0.88
     analogy
    0.87
     noting
    0.85
     ital
    0.84
     anecdotal
    0.80
     summarize
    0.79
     summar
    0.78
     pointed
    0.78
    Act Density 0.855%

    No Known Activations