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

    Neuronpedia

    INDEX
    Explanations

    phrases related to job promotions

    oai_token-act-pair · gpt-3.5-turbo

    references to promotions and promotional activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ð
    -0.72
     Refuge
    -0.67
     Hayward
    -0.66
    akia
    -0.65
    sson
    -0.64
    mia
    -0.62
     Hipp
    -0.62
     sequest
    -0.62
    lv
    -0.62
     PRESIDENT
    -0.62
    POSITIVE LOGITS
    xual
    1.07
     promotion
    0.92
    chwitz
    0.89
    stakes
    0.85
    olicy
    0.80
    pires
    0.79
     tremend
    0.79
     promotions
    0.77
    ISO
    0.76
    rish
    0.76
    Act Density 0.015%

    No Known Activations