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

    Neuronpedia

    INDEX
    Explanations

    words related to freedom and rights

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

    rights termination or restriction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.66
    ########.
    -0.59
    AddHtmlAttribute
    -0.59
     فريبيس
    -0.57
    MemoryWarning
    -0.56
    wahati
    -0.54
     WaitForSeconds
    -0.52
    cestershire
    -0.52
    ----</
    -0.51
    SBATCH
    -0.51
    POSITIVE LOGITS
     lives
    0.46
     LIVES
    0.45
     Lives
    0.38
     NEEDS
    0.36
     auguri
    0.33
     vidas
    0.33
     relied
    0.31
     child
    0.31
    <bos>
    0.31
     names
    0.31
    Act Density 0.347%

    No Known Activations