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 expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.81
    RAW
    -0.72
    rehens
    -0.69
    apers
    -0.68
    effic
    -0.67
    tein
    -0.65
    pent
    -0.64
     kindred
    -0.64
    aukee
    -0.63
    govtrack
    -0.63
    POSITIVE LOGITS
     Yeah
    1.20
    yeah
    1.14
     yeah
    0.99
    Yeah
    0.92
    hhhh
    0.91
    terday
    0.91
    hhh
    0.85
     bye
    0.81
     kidding
    0.80
     dunno
    0.80
    Act Density 0.011%

    No Known Activations