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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and the word "You" used in a message or conversation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     monaster
    -1.13
     poliester
    -1.06
     sacerd
    -0.95
     persil
    -0.92
     cristi
    -0.91
    bewerken
    -0.90
     susun
    -0.90
     torba
    -0.88
     quoc
    -0.88
     ananas
    -0.88
    POSITIVE LOGITS
     endeavouring
    0.80
     unspeak
    0.76
     resear
    0.73
     sophistic
    0.73
     impelled
    0.71
     don
    0.71
     practition
    0.71
     cannot
    0.69
     shouldn
    0.68
     didn
    0.68
    Act Density 0.375%

    No Known Activations