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

    Neuronpedia

    INDEX
    Explanations

    first-person and third-person plural pronouns indicating collective group identity

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

    "We" followed by auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    we followed by auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.52
    taken
    -0.50
    est
    -0.48
     pomo
    -0.48
     explication
    -0.46
     officiating
    -0.46
     clarification
    -0.45
     grading
    -0.45
    WithTag
    -0.45
    led
    -0.45
    POSITIVE LOGITS
     can
    1.19
     have
    1.04
     are
    1.01
     will
    0.94
     could
    0.93
     would
    0.93
     cannot
    0.92
     had
    0.92
     don
    0.91
     didn
    0.88
    Act Density 0.888%

    No Known Activations