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

    Neuronpedia

    INDEX
    Explanations

    phrases related to equality

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to equality and equal rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HI
    -0.83
    UX
    -0.80
    asel
    -0.73
    ARCH
    -0.72
    stra
    -0.70
    OCK
    -0.69
     Coffin
    -0.68
     Brass
    -0.67
    stal
    -0.66
    OST
    -0.64
    POSITIVE LOGITS
    izers
    0.99
    itarian
    0.99
    itably
    0.95
    izer
    0.95
    itable
    0.92
    izational
    0.87
    itability
    0.86
     footing
    0.83
    iser
    0.81
    izes
    0.80
    Act Density 0.019%

    No Known Activations