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

    Neuronpedia

    INDEX
    Explanations

    the word "Yeah"

    oai_token-act-pair · gpt-3.5-turbo

    affirmative responses or acknowledgments in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAW
    -0.81
    apers
    -0.78
    tein
    -0.77
    minist
    -0.73
    rament
    -0.69
    effic
    -0.69
    actionDate
    -0.67
     kindred
    -0.66
    pent
    -0.66
    aukee
    -0.64
    POSITIVE LOGITS
     Yeah
    1.16
    terday
    1.16
    yeah
    1.07
    hhhh
    0.99
     yeah
    0.99
    Yeah
    0.89
    hhh
    0.86
     kidding
    0.84
    hh
    0.83
     gotta
    0.72
    Act Density 0.019%

    No Known Activations