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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric patterns in the form of numbers and characters, such as codes or identifiers

    oai_token-act-pair · gpt-3.5-turbo

    numeric identifiers and references related to documents or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abstinence
    -0.76
     inev
    -0.67
    lihood
    -0.66
     numbering
    -0.66
     invol
    -0.64
     noticing
    -0.64
     acquaintance
    -0.64
     abstraction
    -0.63
     rall
    -0.62
     electing
    -0.61
    POSITIVE LOGITS
    channelAvailability
    1.11
    sbm
    0.96
    quickShipAvailable
    0.95
    Fax
    0.90
    MSN
    0.88
    English
    0.82
    pal
    0.80
    sol
    0.80
    Rated
    0.79
    zan
    0.78
    Act Density 0.088%

    No Known Activations