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

    Neuronpedia

    INDEX
    Explanations

    pieces of code denoting programming concepts or instructions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    borough
    -0.87
    ulhu
    -0.86
    76561
    -0.80
     Hanson
    -0.77
    edin
    -0.77
    akura
    -0.77
    gam
    -0.76
    OPLE
    -0.74
    swick
    -0.74
    Phones
    -0.74
    POSITIVE LOGITS
     keyword
    1.04
     inline
    1.04
     syntax
    1.00
     boolean
    0.98
     invocation
    0.97
     pointer
    0.95
    attribute
    0.91
     modifier
    0.91
     namespace
    0.89
     polymorph
    0.89
    Act Density 7.800%

    No Known Activations