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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reflecting on personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    first-person references and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Finch
    -0.85
     Chavez
    -0.80
     Rhodes
    -0.71
     Powell
    -0.68
     Delta
    -0.68
     Wilkinson
    -0.68
     Gates
    -0.68
     Wilmington
    -0.67
     Buckley
    -0.66
     Osc
    -0.66
    POSITIVE LOGITS
    âĢ
    1.56
     myself
    1.30
    Í
    1.16
    à¼
    1.15
    âĢł
    1.13
    âī
    1.11
    ãĢ
    1.11
     âĢ
    1.10
    .ãĢį
    1.10
    âĹ
    1.09
    Act Density 0.596%

    No Known Activations