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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names associated with people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frisch
    -0.75
    dsc
    -0.59
    loth
    -0.59
    aarrggbb
    -0.59
    sth
    -0.59
    arno
    -0.58
     Harlan
    -0.58
     pinulongan
    -0.58
    THANKS
    -0.57
    chra
    -0.57
    POSITIVE LOGITS
    ley
    2.26
    LEY
    2.10
    ey
    1.70
    ney
    1.62
     LEY
    1.52
    NEY
    1.45
     ley
    1.39
    Ley
    1.35
    sey
    1.32
    leys
    1.30
    Act Density 0.163%

    No Known Activations