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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection or admiration, particularly using the word "lovely."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.69
     Witherspoon
    -0.69
     titoli
    -0.64
     Dink
    -0.60
     Biggs
    -0.58
     Vito
    -0.58
     Freeport
    -0.58
     sekali
    -0.56
    yki
    -0.56
    enumi
    -0.55
    POSITIVE LOGITS
     lovely
    1.12
    lovely
    0.99
     Lovely
    0.92
    Lovely
    0.90
    RegistryLite
    0.70
     pleasant
    0.69
     nice
    0.69
     QtCore
    0.67
     nicest
    0.67
     unpleasant
    0.65
    Act Density 0.050%

    No Known Activations