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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is speaking up or expressing themselves emphatically

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.82
    folios
    -0.80
    estern
    -0.74
    pleting
    -0.73
    ritional
    -0.72
    mental
    -0.66
    folio
    -0.65
    ¥ŀ
    -0.65
    gotten
    -0.64
    onut
    -0.64
    POSITIVE LOGITS
     goodbye
    1.79
     hello
    1.33
     aloud
    1.23
     farewell
    1.11
     Goodbye
    1.09
     loudly
    1.02
     bye
    1.00
     hi
    0.91
     sorry
    0.86
     bluntly
    0.86
    Act Density 1.280%

    No Known Activations