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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing efficiency and degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tantum
    -0.68
     marquées
    -0.62
     ligiloj
    -0.60
     betere
    -0.59
     största
    -0.57
    menor
    -0.57
     quelcon
    -0.57
     keinerlei
    -0.57
     destinées
    -0.55
    nější
    -0.55
    POSITIVE LOGITS
     smoothly
    0.89
     efficiently
    0.89
     aggressively
    0.87
     successfully
    0.85
     profitably
    0.82
     peacefully
    0.82
     comfortably
    0.81
     loudly
    0.81
     prominently
    0.81
     comprehensively
    0.81
    Act Density 0.271%

    No Known Activations