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

    Neuronpedia

    INDEX
    Explanations

    the concept of favorites and beloved items

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

    favorites and classics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -0.42
    ↵
    -0.38
    /
    -0.36
    _
    -0.35
    checkIf
    -0.33
    }")]
    -0.33
    }}/>
    -0.32
    -0.32
    "));
    -0.32
    CHAPTER
    -0.32
    POSITIVE LOGITS
     favorites
    1.45
     Favorites
    1.35
     favourites
    1.35
    favorites
    1.13
    favourites
    1.10
    Favorites
    1.05
     faves
    1.04
     classics
    1.03
    ourites
    0.95
     favoris
    0.88
    Act Density 0.007%

    No Known Activations