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

    Neuronpedia

    INDEX
    Explanations

    references to scientific papers, including citations and links

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -0.83
     للمعارف
    -0.81
     Efq
    -0.81
    ьаж
    -0.81
    /**
    -0.80
     Jefus
    -0.80
    Filmographie
    -0.77
     BoxFit
    -0.74
     leçon
    -0.74
     Reſ
    -0.73
    POSITIVE LOGITS
     
    0.51
     inv
    0.48
    handle
    0.47
     O
    0.45
    HtmlAttribute
    0.45
     ac
    0.45
     did
    0.45
     her
    0.44
     cra
    0.44
    ahal
    0.44
    Act Density 0.039%

    No Known Activations