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

    Neuronpedia

    INDEX
    Explanations

    named entities and locations, specifically those with Eastern European origin

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates or chronological markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oats
    -0.72
     casc
    -0.69
     redund
    -0.68
     Sturgeon
    -0.65
     Replay
    -0.63
    onse
    -0.62
    aching
    -0.62
    erest
    -0.62
     Scotia
    -0.60
    htaking
    -0.60
    POSITIVE LOGITS
    ovic
    1.01
    ovi
    0.96
    jan
    0.87
    uary
    0.86
    ority
    0.86
    ners
    0.84
    estamp
    0.82
    owski
    0.81
    ovsky
    0.81
    ifier
    0.79
    Act Density 0.028%

    No Known Activations