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

    Neuronpedia

    INDEX
    Explanations

    words related to job sectors and industries

    oai_token-act-pair · gpt-3.5-turbo

    references to various job sectors and industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inconsistency
    -0.67
     shame
    -0.65
     legend
    -0.65
    perfect
    -0.64
    weet
    -0.64
    Recipe
    -0.64
     mist
    -0.63
     boo
    -0.63
     brazen
    -0.63
     fool
    -0.63
    POSITIVE LOGITS
     agriculture
    1.13
     automotive
    1.10
     telecommunications
    1.07
     aerospace
    1.07
     vocational
    1.02
     occupational
    1.00
     industrial
    0.99
     industries
    0.99
     healthcare
    0.98
     agricultural
    0.98
    Act Density 0.826%

    No Known Activations