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

    Neuronpedia

    INDEX
    Explanations

    words with character encoding anomalies

    oai_token-act-pair · gpt-3.5-turbo

    product promotions or special offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.75
     margins
    -0.72
     amput
    -0.67
     posit
    -0.66
     acknow
    -0.66
     habits
    -0.66
     inward
    -0.65
     outwe
    -0.65
    iating
    -0.64
    aved
    -0.64
    POSITIVE LOGITS
    Premium
    1.09
    Legendary
    0.92
    ================================================================
    0.92
    Offline
    0.90
    Adapt
    0.89
     Cosponsors
    0.79
     Suite
    0.79
    ¯¯¯¯¯¯¯¯
    0.78
     Reloaded
    0.77
    Adapter
    0.77
    Act Density 0.210%

    No Known Activations