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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "wer" in various forms and capitalizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names containing "wer"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.68
     doInBackground
    -0.64
    .*")]
    -0.59
     jspb
    -0.59
     propOrder
    -0.56
    icago
    -0.55
     /*#__
    -0.55
     JAXBElement
    -0.53
    addContainerGap
    -0.52
    RegistryLite
    -0.52
    POSITIVE LOGITS
    wer
    2.67
    WER
    1.98
    wers
    1.58
    ower
    1.45
    wered
    1.34
     wer
    1.32
    Wer
    1.27
     WER
    1.27
    WERS
    1.19
     Wer
    1.17
    Act Density 0.005%

    No Known Activations