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

    Neuronpedia

    INDEX
    Explanations

    sequences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withd
    -0.86
     poisoning
    -0.74
     padd
    -0.74
     exha
    -0.73
     chained
    -0.73
     hunted
    -0.72
     overflowing
    -0.71
     tides
    -0.70
     recall
    -0.70
     exploited
    -0.70
    POSITIVE LOGITS
     [+
    1.39
     Introduction
    1.00
    jpg
    1.00
    0
    0.99
    09
    0.98
    5
    0.97
    05
    0.94
    06
    0.92
    08
    0.91
    07
    0.88
    Act Density 0.089%

    No Known Activations