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

    Neuronpedia

    INDEX
    Explanations

    comparative language and phrases that indicate a degree of improvement or comparison between subjects

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

    comparative, completion, outcome, estimation, weakened, usage, tribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.67
    transQ
    -0.59
     betweenstory
    -0.58
    脚注の使い方
    -0.58
     esternos
    -0.58
    WriteAttribute
    -0.56
    styleType
    -0.55
     CURIAM
    -0.55
    awtextra
    -0.55
     queſta
    -0.55
    POSITIVE LOGITS
     disambiguazione
    0.47
    niów
    0.38
     آزاد
    0.38
    is
    0.36
    sw
    0.35
     acredita
    0.35
    om
    0.35
    StreamReader
    0.35
    ,
    0.35
     сем
    0.34
    Act Density 0.207%

    No Known Activations