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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases that indicate subtlety or nuance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    subtle differences and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     useAppContext
    -0.59
     élect
    -0.48
     electrophoresis
    -0.47
    actéristi
    -0.47
     rencontr
    -0.46
    endphp
    -0.45
     Kild
    -0.45
     getItemCount
    -0.45
     chargeur
    -0.44
     houſe
    -0.44
    POSITIVE LOGITS
     subtle
    1.96
    subtle
    1.95
     Subtle
    1.75
     subtly
    1.67
     subtlety
    1.40
     sutil
    1.37
     subtleties
    1.27
     subtil
    1.11
    微妙
    0.98
     sottile
    0.95
    Act Density 0.006%

    No Known Activations