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

    Neuronpedia

    INDEX
    Explanations

    references to "ordinary" and "elite" individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chaik
    -0.79
     chagrin
    -0.67
     faulting
    -0.66
     Hait
    -0.66
     Godhead
    -0.66
    istema
    -0.65
    Estar
    -0.65
     Whales
    -0.64
    ecake
    -0.64
    DRESS
    -0.63
    POSITIVE LOGITS
    Ordinary
    1.07
     Ordinary
    1.04
     AssemblyProduct
    1.00
     resilience
    0.97
     Extraordinary
    0.96
    ordinary
    0.93
    Revenir
    0.91
     Resilience
    0.91
     resilient
    0.90
    matchCondition
    0.90
    Act Density 0.104%

    No Known Activations