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

    Neuronpedia

    INDEX
    Explanations

    references to publications and citations within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ë¹ĦìĬ¤
    -0.17
    Úĺ
    -0.17
     Rockefeller
    -0.14
    ì¤Ģ
    -0.14
     Contents
    -0.13
     Gaga
    -0.13
     NotImplemented
    -0.13
    ussia
    -0.13
     Melania
    -0.13
     @{
    -0.13
    POSITIVE LOGITS
     http
    0.24
    ib
    0.23
    http
    0.22
     wikipedia
    0.21
     ib
    0.20
    (http
    0.20
     Wikipedia
    0.20
    .wikipedia
    0.20
    _http
    0.20
    .http
    0.19
    Act Density 0.165%

    No Known Activations