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

    Neuronpedia

    INDEX
    Explanations

    instances of the first-person plural pronoun "we" and related phrases indicating collaboration or collective action

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

    Sections like "Summary" or "Conclusion"

    np_acts-logits-general · gemini-2.0-flash

    we have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.88
     Roskov
    -0.79
    WithIOException
    -0.79
     CreateTagHelper
    -0.78
     &___
    -0.78
     snippetHide
    -0.77
     ujednoznacz
    -0.73
     Administrativna
    -0.72
    WireFormatLite
    -0.70
     resourceCulture
    -0.70
    POSITIVE LOGITS
    Finally
    0.49
     zakon
    0.46
    <eos>
    0.46
     finally
    0.45
    Overall
    0.42
    最後に
    0.42
     Finally
    0.41
     concluding
    0.40
    <strong>
    0.39
    Lastly
    0.39
    Act Density 0.172%

    No Known Activations