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

    Neuronpedia

    INDEX
    Explanations

    references to factories and manufacturing environments

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

    factory automation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Quinn
    -0.47
     Mullen
    -0.44
     appropriateness
    -0.42
    ımda
    -0.42
     McLean
    -0.40
     Connell
    -0.40
    nę
    -0.39
     Conrad
    -0.39
     rámci
    -0.39
     penned
    -0.37
    POSITIVE LOGITS
     factory
    1.76
     factories
    1.57
     FACTORY
    1.53
     Factory
    1.50
     Factories
    1.41
    factory
    1.34
     fábrica
    1.31
    factories
    1.27
    FACTORY
    1.19
     fabbrica
    1.17
    Act Density 0.005%

    No Known Activations