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

    Neuronpedia

    INDEX
    Explanations

    special characters and syntax elements in a programming context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Vander
    -0.59
     hemor
    -0.58
     Gemini
    -0.58
    achus
    -0.57
    ©¶æ¥µ
    -0.54
    ¥ŀ
    -0.52
     Elder
    -0.52
     Frey
    -0.51
     warr
    -0.51
     ende
    -0.51
    POSITIVE LOGITS
    \-
    0.57
    hello
    0.53
    root
    0.53
    =#
    0.52
    empty
    0.51
    Applications
    0.51
    -+
    0.50
    usr
    0.49
     hello
    0.49
    xff
    0.48
    Act Density 8.217%

    No Known Activations