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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating approval or agreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Okay" or similar expressions of acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lago
    -0.76
    */(
    -0.68
    tnc
    -0.68
    aternity
    -0.67
    auri
    -0.64
    atum
    -0.62
    PT
    -0.61
    edom
    -0.61
     prost
    -0.60
    apers
    -0.60
    POSITIVE LOGITS
     bye
    0.93
     yeah
    0.82
    yeah
    0.80
    zers
    0.80
    hhhh
    0.77
    lahoma
    0.77
     huh
    0.77
    hhh
    0.77
     kidding
    0.77
     prest
    0.76
    Act Density 0.058%

    No Known Activations