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

    Neuronpedia

    INDEX
    Explanations

    number-related details like dates and locations

    oai_token-act-pair · gpt-3.5-turbo

    sequences or formats related to numerical data and lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.71
     455
    -0.70
     toast
    -0.69
    pend
    -0.69
    855
    -0.68
     Peng
    -0.67
    heed
    -0.66
     Chaser
    -0.65
    son
    -0.65
    745
    -0.65
    POSITIVE LOGITS
    18
    0.85
     18
    0.84
    ģ«
    0.80
     1889
    0.77
    illes
    0.76
    ²¾
    0.72
    wer
    0.70
    1800
    0.66
     Blackwell
    0.65
    uth
    0.65
    Act Density 0.107%

    No Known Activations