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

    Neuronpedia

    INDEX
    Explanations

    quantifiers and descriptions indicating size or significance

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

    specific references to quantity and size

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

    introducing states with "there is a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.66
     Hän
    -0.60
     indisponible
    -0.57
     respectivamente
    -0.56
     jamás
    -0.55
    posób
    -0.52
     respectively
    -0.51
    respectively
    -0.51
     respectivement
    -0.48
     contextLoads
    -0.48
    POSITIVE LOGITS
     possibility
    1.04
     reason
    1.03
     CreateTagHelper
    1.02
     tendency
    0.95
     chance
    0.88
    possibility
    0.88
     difference
    0.84
     need
    0.82
     dearth
    0.81
     shortage
    0.79
    Act Density 0.069%

    No Known Activations