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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jeografia
    -0.81
    themselves
    -0.71
    kusen
    -0.70
    parsedMessage
    -0.67
     beginnetje
    -0.67
     CURLOPT
    -0.65
    ']))
    -0.65
    NameInMap
    -0.64
    IUrlHelper
    -0.63
    alike
    -0.63
    POSITIVE LOGITS
     Jr
    0.51
    SPATH
    0.50
     perſon
    0.49
    さんが
    0.47
     Justus
    0.46
     людини
    0.46
    Життєпис
    0.44
     ſaid
    0.44
     valueForKey
    0.43
     abbraccio
    0.43
    Act Density 0.509%

    No Known Activations