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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming logic and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     roti
    -0.52
     Knud
    -0.52
     hei
    -0.52
     Alfons
    -0.51
    xmlhttp
    -0.51
     Ashby
    -0.50
     Picchu
    -0.50
     Lyra
    -0.49
    Doe
    -0.49
    馃
    -0.48
    POSITIVE LOGITS
     Gerechtigkeit
    0.62
     sereia
    0.60
     Schaefer
    0.59
     Mendoza
    0.57
     Fawcett
    0.57
     Dempsey
    0.56
     uitzicht
    0.56
     Pritchard
    0.56
     Moser
    0.56
     Spagna
    0.56
    Act Density 1.414%

    No Known Activations