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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "yes" with high activation values

    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
    ojure
    -0.80
    Merit
    -0.79
    lets
    -0.76
    bage
    -0.75
    Offline
    -0.74
    RAW
    -0.72
    rarily
    -0.72
     externalToEVAOnly
    -0.71
    DragonMagazine
    -0.70
    ributed
    -0.69
    POSITIVE LOGITS
    terday
    1.37
     yes
    1.06
    etheless
    0.88
     sir
    0.87
     YES
    0.79
     matter
    0.73
     Yes
    0.73
     sure
    0.72
     parole
    0.70
     stranger
    0.69
    Act Density 0.008%

    No Known Activations