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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    killer
    -0.66
     téléphonique
    -0.62
     smtplib
    -0.62
    brun
    -0.61
    biri
    -0.61
     pinulongan
    -0.61
    彡
    -0.59
    cryption
    -0.59
    MLLoader
    -0.58
     killer
    -0.57
    POSITIVE LOGITS
     ahogy
    0.96
     as
    0.75
     تضيفلها
    0.72
    Vidite
    0.70
     καθώς
    0.68
     patr
    0.66
    mored
    0.63
    AsUp
    0.62
     AsyncTask
    0.61
    ỏa
    0.60
    Act Density 0.141%

    No Known Activations