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

    Neuronpedia

    INDEX
    Explanations

    phrases related to equality and rights

    oai_token-act-pair · gpt-3.5-turbo

    references to equality and equal rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hari
    -0.80
    Äĩ
    -0.75
    HI
    -0.74
     Coffin
    -0.66
    Ľ
    -0.64
    eca
    -0.62
    ski
    -0.61
    Cra
    -0.60
    bara
    -0.60
     Canaver
    -0.59
    POSITIVE LOGITS
    izer
    1.44
    izers
    1.35
    ization
    1.23
    iser
    1.21
    izing
    1.20
    ized
    1.15
    izes
    1.13
    itarian
    1.11
    ising
    1.10
    isers
    1.09
    Act Density 0.038%

    No Known Activations