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

    Neuronpedia

    INDEX
    Explanations

    numbers or numerical references

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Conditions
    -0.78
    Interstitial
    -0.78
    OPLE
    -0.72
    Els
    -0.72
    lich
    -0.70
    ModLoader
    -0.67
    Accessory
    -0.66
    emis
    -0.64
    raught
    -0.63
    agall
    -0.63
    POSITIVE LOGITS
    metry
    0.92
     tallied
    0.88
    enance
    0.87
     discrepancy
    0.85
    paces
    0.81
     fluct
    0.80
    ynthesis
    0.79
     underestimate
    0.79
     quoted
    0.78
     numbers
    0.77
    Act Density 0.059%

    No Known Activations