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

    Neuronpedia

    INDEX
    Explanations

    user profile information

    oai_token-act-pair · gpt-3.5-turbo

    mentions of user profiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abeth
    -0.78
    chest
    -0.68
    ows
    -0.66
    rought
    -0.62
    vest
    -0.62
    bled
    -0.62
    isen
    -0.62
    lins
    -0.61
    phas
    -0.61
    ilk
    -0.61
    POSITIVE LOGITS
     Profile
    1.30
     profiles
    0.92
    iership
    0.87
     Joined
    0.87
    allery
    0.86
     profile
    0.86
     Seym
    0.86
    pedia
    0.82
    Profile
    0.76
     Features
    0.74
    Act Density 0.005%

    No Known Activations