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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "we" and related first-person plural references

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

    now we verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     previously
    -0.41
     IIRC
    -0.40
     meticulously
    -0.38
    strerror
    -0.36
     initially
    -0.36
     originally
    -0.36
     numerous
    -0.35
     tidigare
    -0.35
     ранее
    -0.34
     liknande
    -0.34
    POSITIVE LOGITS
    Now
    0.90
    now
    0.90
     Now
    0.90
    Jetzt
    0.80
     now
    0.79
     Ahora
    0.79
     NOW
    0.79
    NOW
    0.78
    Sekarang
    0.73
    Ahora
    0.73
    Act Density 0.017%

    No Known Activations