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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns followed by contractions and mentions of high personal involvement

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns indicating personal statements or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADVERTISEMENT
    -0.98
    colored
    -0.86
     Organizations
    -0.82
    izational
    -0.81
     totaling
    -0.81
     behaviors
    -0.81
     honors
    -0.80
    imize
    -0.78
     nonexistent
    -0.75
     unfavorable
    -0.75
    POSITIVE LOGITS
     apologise
    1.79
     realise
    1.75
     recognise
    1.75
     apologised
    1.69
     realised
    1.64
     recognised
    1.50
     learnt
    1.49
     analyse
    1.38
     criticised
    1.34
     emphas
    1.33
    Act Density 0.264%

    No Known Activations