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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating roles or functions of objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chofe
    -0.68
    IUrlHelper
    -0.63
     EEC
    -0.61
     Sanger
    -0.60
     Monfieur
    -0.58
    DataAnnotations
    -0.58
     chopsticks
    -0.58
     intonation
    -0.58
     quæ
    -0.58
     ſaid
    -0.57
    POSITIVE LOGITS
     a
    0.77
     part
    0.75
     an
    0.72
     dijadikan
    0.70
     basis
    0.67
    ]^{-
    0.63
     menjadi
    0.62
    LEncoder
    0.62
     source
    0.61
     direct
    0.61
    Act Density 0.367%

    No Known Activations