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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the impact on people's lives or livelihoods

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the identities and well-being of individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cano
    -0.80
    iasm
    -0.77
    pmwiki
    -0.75
    clair
    -0.74
    iHUD
    -0.72
    ucc
    -0.71
    phabet
    -0.71
    avascript
    -0.69
     largeDownload
    -0.69
    etsk
    -0.69
    POSITIVE LOGITS
     individuals
    0.95
     those
    0.81
     Individuals
    0.77
     everyone
    0.75
     each
    0.75
     citizens
    0.75
     minorities
    0.74
     humankind
    0.74
     persons
    0.70
     foreigners
    0.69
    Act Density 0.206%

    No Known Activations