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

    Neuronpedia

    INDEX
    Explanations

    phrases related to factory settings or operations

    oai_token-act-pair · gpt-3.5-turbo

    references to factory farming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.89
    laus
    -0.87
    byss
    -0.83
    vind
    -0.75
    lihood
    -0.75
    ĺħ
    -0.70
     Liberties
    -0.68
    */(
    -0.68
    meet
    -0.67
    kj
    -0.66
    POSITIVE LOGITS
     factory
    0.84
    actory
    0.84
    ounter
    0.78
     Reloaded
    0.76
     worker
    0.76
     farming
    0.75
     Worker
    0.75
    orer
    0.71
    Made
    0.70
    arded
    0.69
    Act Density 0.020%

    No Known Activations