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

    Neuronpedia

    INDEX
    Explanations

    words related to personal experiences and situations, and expressions of emotions and sentiments

    oai_token-act-pair · gpt-3.5-turbo

    themes related to challenges and perseverance in personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    capacity
    -0.72
    orgetown
    -0.70
     torpedo
    -0.67
    arthed
    -0.66
     disqualified
    -0.64
    grave
    -0.64
    rake
    -0.63
     Dover
    -0.63
    ONSORED
    -0.62
     Rhodes
    -0.61
    POSITIVE LOGITS
    âĢ
    1.34
     tho
    1.19
     âĢ
    1.10
     alot
    1.08
     âĿ
    1.04
     thats
    1.02
    âĹ
    1.01
     ðŁĺ
    0.99
    ï¸ı
    0.98
     âĺ
    0.97
    Act Density 0.592%

    No Known Activations