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

    Neuronpedia

    INDEX
    Explanations

    economic and numerical terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to large-scale societal and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mates
    -0.90
    ĪĴ
    -0.78
    pered
    -0.78
     Jinn
    -0.78
    mate
    -0.71
    speak
    -0.70
    gently
    -0.68
    Kind
    -0.67
    ciating
    -0.65
    ©¶æ
    -0.64
    POSITIVE LOGITS
     footprint
    0.99
     (>
    0.95
     artery
    0.85
     swath
    0.85
     conglomer
    0.84
     deficit
    0.84
     deficits
    0.83
     disparity
    0.82
     chunk
    0.81
     difference
    0.81
    Act Density 0.312%

    No Known Activations