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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destul
    -0.37
     quieras
    -0.37
     schre
    -0.35
    ніципа
    -0.35
     vys
    -0.35
     Schle
    -0.35
     bună
    -0.35
    höhe
    -0.34
     leads
    -0.34
     annoncé
    -0.34
    POSITIVE LOGITS
     honored
    1.05
     grateful
    1.01
     proud
    0.97
     humbled
    0.91
     privileged
    0.90
     thankful
    0.88
     honoured
    0.88
     pleased
    0.78
     thrilled
    0.76
     glad
    0.76
    Act Density 0.218%

    No Known Activations