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

    Neuronpedia

    INDEX
    Explanations

    nouns and their various forms related to literature and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     koji
    -0.23
     italiano
    -0.22
    “He
    -0.20
    "He
    -0.20
     Ñıкий
    -0.17
     коÑĤоÑĢÑĭй
    -0.17
     který
    -0.17
     ÙĥبÙĬر
    -0.17
    æ´ŀ
    -0.17
    isé
    -0.17
    POSITIVE LOGITS
     herself
    0.34
     αÏħÏĦή
    0.27
     italiana
    0.24
     latina
    0.23
     коÑĤоÑĢаÑı
    0.23
    “She
    0.22
     która
    0.22
    "She
    0.22
     pública
    0.21
     коÑĤоÑĢÑĥÑİ
    0.21
    Act Density 0.133%

    No Known Activations