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

    Neuronpedia

    INDEX
    Explanations

    instances where the text prompts the reader to take a specific action, such as leaving a comment or sharing

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that invite reader engagement or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.74
    SPONSORED
    -0.71
    stood
    -0.67
    Hum
    -0.67
    advertisement
    -0.66
    andowski
    -0.63
    ynthesis
    -0.63
    Judge
    -0.62
     )]
    -0.60
    Rew
    -0.59
    POSITIVE LOGITS
     possible
    0.84
    rame
    0.69
     warranted
    0.66
    abouts
    0.66
     practicable
    0.64
     typo
    0.62
     prompted
    0.62
     interested
    0.62
     Helpful
    0.60
    erent
    0.59
    Act Density 0.182%

    No Known Activations