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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inclusivity and diversity

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusivity and the diversity of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.69
     awa
    -0.67
     reinforcements
    -0.63
     bulldo
    -0.61
     morp
    -0.61
     divid
    -0.60
     reminders
    -0.60
     symptoms
    -0.59
    potion
    -0.59
    Quotes
    -0.59
    POSITIVE LOGITS
    abama
    0.92
    heastern
    0.84
     backgrounds
    0.84
    astern
    0.82
    bilt
    0.76
    areth
    0.75
     faiths
    0.73
    arth
    0.73
     stripe
    0.72
    estern
    0.72
    Act Density 0.243%

    No Known Activations