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

    Neuronpedia

    INDEX
    Explanations

    increases and decreases in numerical values over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to percentage changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leneck
    -0.80
    clear
    -0.80
    rongh
    -0.79
    ItemTracker
    -0.76
    important
    -0.74
    webkit
    -0.73
    Important
    -0.72
    hai
    -0.71
    TN
    -0.70
    Limited
    -0.70
    POSITIVE LOGITS
     afar
    1.02
     whence
    0.93
     baseline
    0.78
     scratch
    0.75
     1929
    0.71
     conception
    0.70
     thence
    0.69
     Berk
    0.66
     inception
    0.63
     Above
    0.63
    Act Density 0.073%

    No Known Activations