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

    Neuronpedia

    INDEX
    Explanations

    locations such as streets, cities, and countries

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and their placements in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ł
    -0.60
    omorph
    -0.59
    ¦
    -0.59
    ¯
    -0.57
    ãĥ¼
    -0.56
    ĸ
    -0.55
    ãĥ¥
    -0.55
    entimes
    -0.55
    ¡
    -0.54
    Reason
    -0.54
    POSITIVE LOGITS
     died
    1.00
     arrives
    0.91
     survives
    0.90
     publishes
    0.90
     has
    0.90
     belongs
    0.90
     announces
    0.89
     joins
    0.88
     resides
    0.87
     discusses
    0.86
    Act Density 0.414%

    No Known Activations