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

    Neuronpedia

    INDEX
    Explanations

    words that end with the letters "ys", potentially indicating possessiveness or plurality

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "S" followed by "ys" to identify references to species or similar categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renheit
    -0.76
     vou
    -0.67
    DERR
    -0.66
     attribution
    -0.64
     Quit
    -0.63
     stren
    -0.60
     circulation
    -0.60
     Kinnikuman
    -0.59
     Islamabad
    -0.58
     sten
    -0.57
    POSITIVE LOGITS
    omething
    1.34
    pace
    1.05
    hots
    0.94
    leep
    0.88
    metics
    0.87
    ql
    0.87
    cape
    0.87
    urus
    0.85
    olutions
    0.83
    ource
    0.82
    Act Density 0.018%

    No Known Activations