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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we" in various forms

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

    Immediately follows "we" or "We"

    np_acts-logits-general · gemini-2.0-flash

    we followed by specific continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addLast
    -0.61
     Lohan
    -0.55
     insectes
    -0.55
    aarrggbb
    -0.52
     noastre
    -0.51
     glatt
    -0.51
     Lessing
    -0.50
    toad
    -0.49
    توضیحات
    -0.48
     nakalista
    -0.48
    POSITIVE LOGITS
    Rohy
    0.61
    IVEREF
    0.53
    )$}
    0.51
    0.51
    writeField
    0.50
    gener
    0.49
     Energies
    0.48
    GENER
    0.47
    FARE
    0.47
    ритори
    0.47
    Act Density 0.124%

    No Known Activations