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

    Neuronpedia

    INDEX
    Explanations

    phrases related to devices and technology

    oai_token-act-pair · gpt-3.5-turbo

    expressions of apology or regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥı
    -0.76
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    utm
    -0.73
    elled
    -0.71
    "},"
    -0.70
    ür
    -0.67
    umerable
    -0.67
    ĸļ
    -0.66
    ãĥĩ
    -0.66
    urated
    -0.65
    POSITIVE LOGITS
     disclaimer
    1.05
     caveat
    0.95
    :]
    0.94
    Disclaimer
    0.88
     kicker
    0.85
     note
    0.85
     caveats
    0.84
     NOTE
    0.83
     icing
    0.80
    PLE
    0.78
    Act Density 0.524%

    No Known Activations