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

    Neuronpedia

    INDEX
    Explanations

    mentions of biographies

    oai_token-act-pair · gpt-3.5-turbo

    references to biographies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     emit
    -0.75
     resorts
    -0.73
    tern
    -0.69
     resort
    -0.64
    escal
    -0.64
     tant
    -0.64
     oven
    -0.63
    rend
    -0.63
     Revel
    -0.63
    ters
    -0.61
    POSITIVE LOGITS
     biography
    3.51
     autobiography
    1.32
     profile
    1.19
     encyclopedia
    1.18
    ographies
    1.13
     portrait
    1.12
    Profile
    1.06
     bio
    1.04
     Profile
    1.02
    profile
    0.99
    Act Density 0.015%

    No Known Activations