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

    Neuronpedia

    INDEX
    Explanations

    phrases related to workplace incidents and disputes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal issues and disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.80
    ortality
    -0.73
    iak
    -0.72
    agically
    -0.70
    yrinth
    -0.69
    DragonMagazine
    -0.68
     conclud
    -0.68
    venture
    -0.68
    depending
    -0.68
    negie
    -0.67
    POSITIVE LOGITS
     menstru
    1.11
     hijab
    1.05
     sexist
    0.94
     breastfeeding
    0.92
     incorrectly
    0.91
     improperly
    0.90
     restroom
    0.90
     breasts
    0.88
     disrespectful
    0.87
     hairst
    0.87
    Act Density 0.626%

    No Known Activations