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

    Neuronpedia

    INDEX
    Explanations

    phrases related to demographic categories

    oai_token-act-pair · gpt-3.5-turbo

    terms related to demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.81
    nard
    -0.78
    ipedia
    -0.77
    leaf
    -0.73
    pit
    -0.72
    mosp
    -0.70
    ELS
    -0.70
    ouston
    -0.69
    lain
    -0.69
    amina
    -0.69
    POSITIVE LOGITS
     demographics
    0.98
     demographic
    0.97
     profile
    0.76
     profiles
    0.76
     makeup
    0.71
    ographically
    0.71
    ally
    0.70
     pressures
    0.70
     Matters
    0.70
     breakdown
    0.69
    Act Density 0.019%

    No Known Activations