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

    Neuronpedia

    INDEX
    Explanations

    phrases related to repetition or recurrence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest consistency or recurrence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.80
    Publisher
    -0.65
    VPN
    -0.65
    ullivan
    -0.63
    olor
    -0.63
    abytes
    -0.62
    Documents
    -0.62
     portfolios
    -0.61
    ãĤ¨ãĥ«
    -0.61
    coon
    -0.60
    POSITIVE LOGITS
     Asc
    0.65
     Nug
    0.63
     Texans
    0.58
    riz
    0.57
    ignty
    0.57
     Astros
    0.57
    quel
    0.56
     Niger
    0.56
    è¡
    0.56
     Lamar
    0.55
    Act Density 0.222%

    No Known Activations