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

    Neuronpedia

    INDEX
    Explanations

    words related to identity and classification of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.69
    phia
    -0.68
    ppa
    -0.62
    sonian
    -0.61
    andowski
    -0.60
     properties
    -0.59
     cottage
    -0.58
     ancest
    -0.58
    ebus
    -0.58
     slic
    -0.56
    POSITIVE LOGITS
    jee
    1.04
    uese
    0.88
    aroo
    0.82
    ão
    0.70
    zee
    0.70
    ãĤ±
    0.67
    Cola
    0.67
    azing
    0.65
     Genocide
    0.65
    BuyableInstoreAndOnline
    0.65
    Act Density 0.018%

    No Known Activations