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

    Neuronpedia

    INDEX
    Explanations

    phrases with a specific pattern of characters interspersed with special characters

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to entertainment or gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ranged
    -0.85
     range
    -0.85
     bending
    -0.83
     revers
    -0.80
     habit
    -0.79
     arising
    -0.79
     settings
    -0.79
     pitched
    -0.79
     currency
    -0.79
     scaling
    -0.78
    POSITIVE LOGITS
    Advertisements
    1.77
    Mar
    1.56
    Conclusion
    1.52
    Pan
    1.50
    Others
    1.50
    Nor
    1.50
    Las
    1.49
    Mal
    1.48
    Nap
    1.47
    Gal
    1.45
    Act Density 0.139%

    No Known Activations