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

    Neuronpedia

    INDEX
    Explanations

    terms related to economic principles and mechanisms

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

    Follows adjectives like "valuable", "useful", or "costly"

    np_acts-logits-general · gemini-2.0-flash

    value and importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     épaules
    -0.94
     lèvres
    -0.94
     négociations
    -0.82
     genoux
    -0.79
     dépens
    -0.79
     églises
    -0.78
     bienfaits
    -0.77
     attentes
    -0.76
     pouvoirs
    -0.75
     vœux
    -0.74
    POSITIVE LOGITS
     examples
    1.09
     entities
    1.05
     targets
    1.03
     substitutes
    1.02
     replacements
    1.02
     ones
    1.01
     extensions
    1.00
     objects
    0.99
     staples
    0.99
     additions
    0.98
    Act Density 0.726%

    No Known Activations