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

    Neuronpedia

    INDEX
    Explanations

    mentions of personal experiences or anecdotes involving friends and acquaintances

    oai_token-act-pair · gpt-3.5-turbo

    references to personal relationships and friendships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOW
    -0.77
     understatement
    -0.77
    ardless
    -0.74
     compliant
    -0.70
    excluding
    -0.69
     defenders
    -0.69
    olute
    -0.68
    ctive
    -0.67
    azeera
    -0.67
     Pwr
    -0.66
    POSITIVE LOGITS
     overheard
    1.02
     accidentally
    0.86
     acquaintance
    0.86
     stumbled
    0.83
     Bought
    0.80
     reminis
    0.79
     overhe
    0.78
     wandered
    0.77
     asked
    0.76
     casually
    0.75
    Act Density 0.536%

    No Known Activations