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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing awe, surprise, or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the idea of experiencing or witnessing something for the first time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     upgr
    -0.64
     portfolios
    -0.62
    markets
    -0.62
     arteries
    -0.62
     reins
    -0.61
     antioxid
    -0.57
    Accessory
    -0.57
    cms
    -0.56
    ju
    -0.56
     juices
    -0.55
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.93
     EVER
    0.92
     dime
    0.84
     anywhere
    0.80
     imaginable
    0.79
    javascript
    0.74
     anybody
    0.73
    Initialized
    0.73
     ever
    0.72
    ever
    0.71
    Act Density 0.144%

    No Known Activations