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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "wrap" and its variations or contexts related to completion or ending

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

    concluding or wrapping up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     children
    -0.36
    Applies
    -0.34
     people
    -0.33
    StringTo
    -0.33
     user
    -0.33
    Measured
    -0.33
     male
    -0.32
     users
    -0.32
     growth
    -0.31
     patin
    -0.30
    POSITIVE LOGITS
     concluding
    0.86
     concludes
    0.82
    conclusion
    0.81
     محفوظة
    0.76
     завер
    0.75
     conclude
    0.74
     concluded
    0.74
     conclusion
    0.73
     conclusão
    0.69
     concluir
    0.68
    Act Density 0.006%

    No Known Activations