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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to systems and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Хьажоргаш
    -0.49
     decirle
    -0.42
     abbiano
    -0.39
    IsContent
    -0.38
     murieron
    -0.38
    InteropServices
    -0.35
     acompañar
    -0.35
    Autowired
    -0.35
    <bos>
    -0.35
     فريبيس
    -0.34
    POSITIVE LOGITS
    Tikang
    0.64
    XmlAccessType
    0.54
     itſelf
    0.53
    twimg
    0.50
     tranſ
    0.50
     myſelf
    0.49
     Monfieur
    0.48
     Jefus
    0.47
     turkey
    0.46
     betweenstory
    0.46
    Act Density 0.275%

    No Known Activations