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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political occupations

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of "occupation" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boost
    -0.71
     Boost
    -0.71
    Boost
    -0.69
     Turbo
    -0.69
    ðŁij
    -0.66
    bly
    -0.65
    dd
    -0.63
    ply
    -0.63
    tube
    -0.62
    Hub
    -0.62
    POSITIVE LOGITS
     occupation
    3.99
     occupations
    2.61
     occup
    2.56
     Occup
    2.38
    Occup
    2.13
    occup
    1.93
     Occupations
    1.85
     occupying
    1.85
     occupied
    1.65
     occupational
    1.55
    Act Density 0.019%

    No Known Activations