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

    Neuronpedia

    INDEX
    Explanations

    mentions of corporate subsidiaries

    oai_token-act-pair · gpt-3.5-turbo

    references to companies and their subsidiaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cage
    -0.77
     Hav
    -0.76
    bat
    -0.73
    bra
    -0.72
    hma
    -0.72
    aiman
    -0.70
    hus
    -0.69
    hner
    -0.69
    ohan
    -0.69
    sticks
    -0.67
    POSITIVE LOGITS
     subsidiary
    1.11
    rador
    1.07
     subsidiaries
    0.94
     operating
    0.80
     owned
    0.79
     operated
    0.75
    unia
    0.74
    itute
    0.74
     subcontract
    0.73
     outsourcing
    0.73
    Act Density 0.028%

    No Known Activations