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

    Neuronpedia

    INDEX
    Explanations

    uncommon characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol or character in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rag
    -0.71
     salad
    -0.69
     carts
    -0.68
     Dirt
    -0.67
     Lunch
    -0.64
     scatter
    -0.63
     Marshal
    -0.62
     gad
    -0.62
     Droid
    -0.62
     lunch
    -0.61
    POSITIVE LOGITS
    º
    1.13
    ¹
    1.13
    Ĵ
    0.93
    acca
    0.92
    ı
    0.91
    £
    0.90
    ··
    0.90
    į
    0.87
    ¼
    0.85
    »
    0.85
    Act Density 0.112%

    No Known Activations