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

    Neuronpedia

    INDEX
    Explanations

    words related to names or persons

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.72
     Vega
    -0.66
    FORMATION
    -0.66
     Malays
    -0.64
    ources
    -0.63
    ////////////////
    -0.61
     VIDEOS
    -0.61
    RFC
    -0.60
    ĸļ
    -0.57
    Former
    -0.57
    POSITIVE LOGITS
    levard
    1.06
    lehem
    0.98
    pillar
    0.96
    apest
    0.88
    hammad
    0.83
    acket
    0.80
    ĵĺ
    0.79
    illet
    0.79
    artisan
    0.78
    aneers
    0.78
    Act Density 0.345%

    No Known Activations