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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-expression and personal beliefs

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express statements or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kicking
    -0.58
     departing
    -0.58
    kinson
    -0.57
    nen
    -0.55
     kindly
    -0.55
    ongo
    -0.53
     captcha
    -0.53
    omen
    -0.52
     kicks
    -0.52
    ema
    -0.52
    POSITIVE LOGITS
     Finally
    1.03
     And
    0.99
     Lastly
    0.97
     He
    0.89
     etc
    0.87
     They
    0.84
     Heck
    0.80
    Finally
    0.79
    And
    0.78
    etc
    0.78
    Act Density 0.375%

    No Known Activations