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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions and confirmations in user interactions

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

    try again or remove

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.73
     méri
    -0.71
     ſeveral
    -0.67
     plufieurs
    -0.56
     vœ
    -0.54
    protetor
    -0.54
     feveral
    -0.52
     AssemblyCompany
    -0.52
     disponibilités
    -0.52
    expandindo
    -0.52
    POSITIVE LOGITS
     selectively
    0.57
     forcibly
    0.56
     aggressively
    0.55
     take
    0.55
     forcefully
    0.53
     pull
    0.52
     bravely
    0.52
     actively
    0.52
     give
    0.51
     collaboratively
    0.51
    Act Density 0.012%

    No Known Activations