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

    Neuronpedia

    INDEX
    Explanations

    decimal numbers with a specified number of decimal places

    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
     bang
    -0.67
     Span
    -0.65
     backlog
    -0.63
     churn
    -0.58
     dred
    -0.58
     Slav
    -0.58
     keyboards
    -0.58
     Nou
    -0.57
     clim
    -0.57
     Joy
    -0.57
    POSITIVE LOGITS
    025
    1.35
    024
    1.30
    200000
    1.26
    075
    1.24
    035
    1.20
    070
    1.20
    050
    1.19
    045
    1.18
    080
    1.17
    125
    1.17
    Act Density 0.063%

    No Known Activations