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

    Neuronpedia

    INDEX
    Explanations

    statistics and numerical data related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    statements related to statistical data and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dishes
    -0.74
    ossom
    -0.66
    wake
    -0.65
     latch
    -0.64
     awaits
    -0.64
    olog
    -0.63
     wishes
    -0.63
     cabinets
    -0.62
     Recipes
    -0.61
     corners
    -0.60
    POSITIVE LOGITS
     proportional
    0.98
     fluct
    0.97
     proportion
    0.95
     tripled
    0.95
     averaged
    0.94
     negligible
    0.93
     estimated
    0.92
     quadru
    0.91
     inflated
    0.90
     doubled
    0.90
    Act Density 0.266%

    No Known Activations