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

    Neuronpedia

    INDEX
    Explanations

    financial and numerical data

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations and measures of various types of data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doodle
    -0.76
     Rhodes
    -0.74
     Canaan
    -0.72
     secrets
    -0.70
     Jihad
    -0.70
     Sanctuary
    -0.68
     Gaal
    -0.68
     Forge
    -0.67
     activist
    -0.66
     sham
    -0.66
    POSITIVE LOGITS
    average
    1.40
    total
    1.32
    percent
    1.29
    £
    1.24
    Average
    1.23
    adjusted
    1.20
    $
    1.19
    mean
    1.17
    Avg
    1.14
    gross
    1.13
    Act Density 0.216%

    No Known Activations