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

    Neuronpedia

    INDEX
    Explanations

    words related to financial and business concepts, such as 'sales growth', 'debt', and 'incentives'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific measurements, quantities, or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ³
    -0.67
    Pur
    -0.59
    Īè
    -0.57
     Summon
    -0.56
     festive
    -0.55
    MAP
    -0.55
    Joy
    -0.54
    Su
    -0.54
    arch
    -0.54
    å§
    -0.53
    POSITIVE LOGITS
     alike
    0.90
     respectively
    0.90
    depending
    0.80
    ,,,,
    0.72
    essions
    0.69
    src
    0.66
    ingen
    0.66
    ovi
    0.66
    oti
    0.66
    raised
    0.62
    Act Density 0.353%

    No Known Activations