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

    Neuronpedia

    INDEX
    Explanations

    phrases containing quoted speech

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or direct speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.85
    ritional
    -0.75
    mania
    -0.71
    cv
    -0.71
    orneys
    -0.71
    equipped
    -0.70
    folios
    -0.70
    icably
    -0.69
    inguished
    -0.69
    ernels
    -0.68
    POSITIVE LOGITS
     goodbye
    1.07
     aloud
    0.90
     sarcast
    0.80
     bluntly
    0.79
     hello
    0.78
     bye
    0.76
     Goodbye
    0.72
     YES
    0.71
     loudly
    0.68
     Cortana
    0.66
    Act Density 0.200%

    No Known Activations