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

    Neuronpedia

    INDEX
    Explanations

    user profiles or social media user information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Profile."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abeth
    -0.86
    atorial
    -0.71
    chest
    -0.70
    actic
    -0.70
    RECT
    -0.70
    iah
    -0.68
    ago
    -0.67
    erc
    -0.66
    mediately
    -0.66
    meaning
    -0.65
    POSITIVE LOGITS
     Profile
    1.19
     Joined
    1.00
     profiles
    0.94
     profile
    0.85
    allery
    0.84
     Blog
    0.83
     Features
    0.81
     Occupations
    0.78
     Artist
    0.73
     Quote
    0.73
    Act Density 0.009%

    No Known Activations