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

    Neuronpedia

    INDEX
    Explanations

    language related to equality and balance

    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
    -0.81
    UX
    -0.80
    stal
    -0.78
    stra
    -0.74
    asel
    -0.71
    ARCH
    -0.71
    OLOG
    -0.70
    berries
    -0.67
     Brass
    -0.67
    hari
    -0.66
    POSITIVE LOGITS
    izers
    0.96
    itably
    0.92
    itarian
    0.89
    izer
    0.89
    itable
    0.87
    izational
    0.86
    itability
    0.83
    ization
    0.78
    iser
    0.77
     footing
    0.77
    Act Density 0.015%

    No Known Activations