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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disenfranchisement and political exclusion

    oai_token-act-pair · gpt-3.5-turbo

    references to disenfranchisement and its effects on various groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PF
    -0.79
    imb
    -0.78
    BY
    -0.73
    ENCE
    -0.73
    olf
    -0.72
     venture
    -0.71
    opher
    -0.71
    Else
    -0.71
    Benz
    -0.71
     Flavoring
    -0.69
    POSITIVE LOGITS
     disenfranch
    1.55
    enfranch
    1.11
    veyard
    0.76
     Barg
    0.72
     voic
    0.71
     Skydragon
    0.69
     subjug
    0.68
     Manip
    0.66
    struction
    0.66
    ignt
    0.65
    Act Density 0.022%

    No Known Activations