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

    Neuronpedia

    INDEX
    Explanations

    phrases related to speech or quotes

    oai_token-act-pair · gpt-3.5-turbo

    references to speech and statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shoot
    -0.73
    onut
    -0.69
    equipped
    -0.67
    xtap
    -0.67
    amate
    -0.64
     Claw
    -0.64
    ticket
    -0.62
    pend
    -0.61
     fullest
    -0.61
    ãĥ¯ãĥ³
    -0.60
    POSITIVE LOGITS
     goodbye
    1.36
     aloud
    1.33
     about
    1.19
     ABOUT
    0.95
     loudly
    0.91
    about
    0.88
     publicly
    0.87
     Goodbye
    0.85
     hello
    0.84
     afterwards
    0.83
    Act Density 0.048%

    No Known Activations