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

    Neuronpedia

    INDEX
    Explanations

    words related to traditional or old-fashioned concepts or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to traditional or classic styles and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SEA
    -0.72
    kers
    -0.67
     Nanto
    -0.66
    soon
    -0.66
    externalActionCode
    -0.66
    nea
    -0.65
    lez
    -0.63
    afa
    -0.63
    Posts
    -0.63
    Interstitial
    -0.63
    POSITIVE LOGITS
    fashioned
    1.16
     fashioned
    1.15
    ftime
    0.90
    nesday
    0.85
    reet
    0.80
    inois
    0.73
     notions
    0.72
    zsche
    0.72
    MpServer
    0.70
     showc
    0.70
    Act Density 0.009%

    No Known Activations