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

    Neuronpedia

    INDEX
    Explanations

    references to completeness or entirety within a context

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

    full, complete, entire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hen
    -0.34
     tick
    -0.33
     Tre
    -0.32
    penup
    -0.32
     <
    -0.31
     Gal
    -0.31
    }.\
    -0.31
     Tra
    -0.31
     wind
    -0.30
    kk
    -0.30
    POSITIVE LOGITS
    完整
    0.88
    Full
    0.86
     completos
    0.85
     completo
    0.84
     Full
    0.83
     complètes
    0.83
    完整的
    0.83
     FULL
    0.81
     inteiro
    0.79
    FULL
    0.79
    Act Density 0.096%

    No Known Activations