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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "say" in statements or conversations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of speaking or expressing opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folios
    -0.72
    folio
    -0.70
    xtap
    -0.70
    ockets
    -0.70
    mental
    -0.69
    ritional
    -0.69
    pleting
    -0.66
    estern
    -0.65
    ãĤ´ãĥ³
    -0.64
    videos
    -0.63
    POSITIVE LOGITS
     goodbye
    1.74
     hello
    1.32
     aloud
    1.18
     farewell
    1.09
     Goodbye
    1.04
     bye
    1.00
     hi
    0.99
     sorry
    0.95
     loudly
    0.94
     something
    0.85
    Act Density 0.129%

    No Known Activations