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

    Neuronpedia

    INDEX
    Explanations

    imports and code related keywords in a programming context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Redd
    -0.68
    ippers
    -0.67
    hra
    -0.67
    holes
    -0.66
    enary
    -0.64
    .–
    -0.63
    served
    -0.63
    sonian
    -0.62
    clerosis
    -0.62
    GM
    -0.61
    POSITIVE LOGITS
     std
    0.98
     java
    0.77
     sys
    0.74
     Prelude
    0.74
     ak
    0.72
     Ada
    0.71
     {
    0.71
    std
    0.70
     io
    0.69
     Sens
    0.69
    Act Density 0.040%

    No Known Activations