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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "say"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express assertions or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.70
    pes
    -0.70
    ¥ŀ
    -0.69
    xtap
    -0.68
     Firearms
    -0.68
    folios
    -0.67
    rients
    -0.65
    onut
    -0.65
     conflic
    -0.65
    Tai
    -0.64
    POSITIVE LOGITS
     goodbye
    1.51
     hello
    1.12
     aloud
    0.92
     Goodbye
    0.89
     sorry
    0.88
     hi
    0.84
     bye
    0.78
     definitively
    0.78
    biz
    0.76
     farewell
    0.75
    Act Density 0.040%

    No Known Activations