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

    Neuronpedia

    INDEX
    Explanations

    procedural phrases related to "how-to" instructions or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.80
    InjectAttribute
    -0.59
    PerformLayout
    -0.57
    mobileqq
    -0.57
    WaitGroup
    -0.56
     kaarangay
    -0.53
    eratops
    -0.53
    orteur
    -0.53
     Référence
    -0.53
    subplots
    -0.52
    POSITIVE LOGITS
     accomplish
    1.34
     accomplished
    1.25
     achieved
    1.24
     logr
    1.24
     accomplishing
    1.20
     achieve
    1.12
    achieved
    1.10
     achievable
    1.02
     achieves
    1.00
     accomplishment
    1.00
    Act Density 0.492%

    No Known Activations