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

    Neuronpedia

    INDEX
    Explanations

    instances where users can take action such as opting out or unsubscribing at any time

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of time and its flexibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ards
    -0.68
    arded
    -0.66
     tomat
    -0.63
    ging
    -0.62
    avorite
    -0.62
    uned
    -0.58
    gotten
    -0.57
    eur
    -0.57
     miner
    -0.56
     darn
    -0.54
    POSITIVE LOGITS
    zone
    0.87
    cale
    0.77
     periods
    0.75
    aneously
    0.75
    frames
    0.74
    î
    0.73
     period
    0.71
    è¦ļéĨĴ
    0.70
    .*
    0.70
    frame
    0.70
    Act Density 0.059%

    No Known Activations