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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reflecting or reminiscing on past events or experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve reflection on past discussions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erto
    -0.87
    trump
    -0.80
    weather
    -0.76
    aldo
    -0.76
    weed
    -0.73
    iola
    -0.72
    esm
    -0.72
    worm
    -0.71
    mpeg
    -0.70
    ãĤ«
    -0.69
    POSITIVE LOGITS
     memories
    1.20
     retrospect
    1.04
     nostalg
    1.01
     events
    1.00
     hindsight
    0.97
     history
    0.95
     reminis
    0.93
     vividly
    0.88
     moments
    0.87
     experiences
    0.86
    Act Density 0.148%

    No Known Activations