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

    Neuronpedia

    INDEX
    Explanations

    technical terms and data points scattered within sentences

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and associated analytical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chuk
    -0.56
    farious
    -0.47
    abus
    -0.43
     Pixie
    -0.42
     Throne
    -0.42
    ovan
    -0.41
    士
    -0.40
    sylv
    -0.39
    bernatorial
    -0.39
     Ivory
    -0.38
    POSITIVE LOGITS
    pmwiki
    0.60
    etheless
    0.57
     WARN
    0.51
    NetMessage
    0.51
    bably
    0.48
     largeDownload
    0.47
    !--
    0.44
     android
    0.44
    conservancy
    0.41
    )!
    0.40
    Act Density 4.013%

    No Known Activations