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

    Neuronpedia

    INDEX
    Explanations

    references to social hierarchies and discrimination based on caste

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icho
    -0.15
    /WebAPI
    -0.14
    INCT
    -0.14
    lobal
    -0.14
    xbd
    -0.13
    @nate
    -0.13
    raq
    -0.13
    achen
    -0.13
     Summers
    -0.13
    errar
    -0.13
    POSITIVE LOGITS
     Scheduled
    0.37
     reservation
    0.37
     cast
    0.34
     SC
    0.33
     Reservation
    0.33
     Dal
    0.32
     reservations
    0.32
     caste
    0.32
    Scheduled
    0.32
     backward
    0.31
    Act Density 0.084%

    No Known Activations