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

    Neuronpedia

    INDEX
    Explanations

    numerical values in a specific format, often appearing as percentages or decimal numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urat
    -0.74
     overt
    -0.61
     divest
    -0.61
    hetti
    -0.59
     realistically
    -0.59
    pocket
    -0.58
     severed
    -0.58
     youth
    -0.57
     consecut
    -0.57
    ively
    -0.57
    POSITIVE LOGITS
    GHz
    1.08
     GHz
    0.94
    BSD
    0.91
    ©¶æ¥µ
    0.90
     oz
    0.87
    %:
    0.86
    MB
    0.86
     Ranked
    0.85
    %"
    0.85
    %
    0.84
    Act Density 0.037%

    No Known Activations