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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.88
     aggressiveness
    -0.67
    Pronunciation
    -0.64
     sév
    -0.63
    Bronnen
    -0.60
     elbows
    -0.60
     unsuccessfully
    -0.58
     azért
    -0.58
     ketat
    -0.58
     interesa
    -0.58
    POSITIVE LOGITS
     wonderful
    1.87
    wonderful
    1.69
    Wonderful
    1.69
     Wonderful
    1.65
     marvelous
    1.47
     lovely
    1.38
     amazing
    1.33
     marvellous
    1.32
     beautiful
    1.31
     wonderfully
    1.26
    Act Density 0.106%

    No Known Activations