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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of "the" as well as a focus on significant nouns and their importance in the context

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

    Followed by "of" and a positive word

    np_acts-logits-general · gemini-2.0-flash

    the importance or fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     publiques
    -0.71
     houſe
    -0.65
     européennes
    -0.65
     avoient
    -0.64
     officielles
    -0.64
     commerciales
    -0.63
     directos
    -0.62
     humaines
    -0.61
     ſtate
    -0.60
     électroniques
    -0.60
    POSITIVE LOGITS
     fact
    0.95
     need
    0.78
     importance
    0.75
     impact
    0.65
     difficulty
    0.62
     lack
    0.59
    fact
    0.58
     tremendous
    0.56
     enorm
    0.54
     benefit
    0.54
    Act Density 0.423%

    No Known Activations