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

    Neuronpedia

    INDEX
    Explanations

    financial figures represented in millions and percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and financial data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Þ
    -0.95
     exting
    -0.93
     reluct
    -0.92
     corrid
    -0.90
     oun
    -0.88
     nomine
    -0.86
    ß
    -0.86
     pione
    -0.84
     practition
    -0.81
    aditional
    -0.80
    POSITIVE LOGITS
    ))))
    0.68
    }}
    0.65
    00
    0.63
    px
    0.63
    micro
    0.62
    slice
    0.62
    {{
    0.62
    3333
    0.62
    }"
    0.61
    38
    0.60
    Act Density 0.097%

    No Known Activations