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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "full" indicating completeness or entirety

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

    full and complete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     évêque
    -0.44
     préférence
    -0.35
     amitié
    -0.33
     dizem
    -0.32
     lembra
    -0.32
    AutoScaleMode
    -0.31
     dominio
    -0.31
    iocene
    -0.31
     säger
    -0.31
     faim
    -0.30
    POSITIVE LOGITS
     full
    0.90
     complete
    0.73
     FULL
    0.73
     Full
    0.73
    Full
    0.72
    full
    0.72
    完整
    0.71
    完整的
    0.70
     fully
    0.68
     lengkap
    0.67
    Act Density 0.012%

    No Known Activations