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

    Neuronpedia

    INDEX
    Explanations

    statements or quotes made by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "said."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.85
    folios
    -0.75
    equipped
    -0.74
    ritional
    -0.74
    cv
    -0.73
    pleting
    -0.71
    osponsors
    -0.69
    aliation
    -0.68
    ernels
    -0.67
    =~=~
    -0.67
    POSITIVE LOGITS
     goodbye
    1.32
     aloud
    1.00
     hello
    0.92
     bluntly
    0.78
     farewell
    0.78
     sarcast
    0.77
     bye
    0.75
     loudly
    0.74
     Goodbye
    0.73
     YES
    0.70
    Act Density 0.172%

    No Known Activations