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

    Neuronpedia

    INDEX
    Explanations

    words related to perceptions and beliefs

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to perceptions of social and racial disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akura
    -0.72
    raid
    -0.70
    kers
    -0.69
    etts
    -0.64
    packed
    -0.64
    hands
    -0.63
    cise
    -0.63
    ature
    -0.63
    ercise
    -0.62
    err
    -0.62
    POSITIVE LOGITS
     perceptions
    0.84
     recoil
    0.78
    wcsstore
    0.76
     attractiveness
    0.73
    ually
    0.70
    ibly
    0.70
     cumbers
    0.69
     conflic
    0.69
    ById
    0.67
     perceive
    0.66
    Act Density 0.024%

    No Known Activations