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

    Neuronpedia

    INDEX
    Explanations

    terms related to imitation and mimicking behaviors or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iParam
    -0.59
     rencontré
    -0.53
     Enlight
    -0.53
    apimachinery
    -0.53
     fVar
    -0.50
     antaranya
    -0.49
     fallu
    -0.49
     motivasi
    -0.49
     daarmee
    -0.48
    grano
    -0.46
    POSITIVE LOGITS
     imitation
    1.15
     imit
    1.15
     imitating
    1.14
     imitate
    1.12
     mimic
    1.11
     imitated
    1.04
    Imit
    1.04
     mimicking
    1.01
     Imit
    0.99
     mimics
    0.99
    Act Density 0.460%

    No Known Activations