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

    Neuronpedia

    INDEX
    Explanations

    references to pull requests in a coding or version control context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newOwner
    -0.55
     ब्रेकडाउन
    -0.51
     kaarangay
    -0.50
    parsedMessage
    -0.49
    AddTagHelper
    -0.48
    ImageContext
    -0.48
    tonsoft
    -0.47
     CanadaChoose
    -0.45
     unknownFields
    -0.45
     ComVisible
    -0.44
    POSITIVE LOGITS
     pr
    0.92
     Pr
    0.81
    pr
    0.81
     cr
    0.78
    Pr
    0.73
     gr
    0.73
     Gr
    0.70
    Gr
    0.66
    gr
    0.63
    cr
    0.61
    Act Density 0.474%

    No Known Activations