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

    Neuronpedia

    INDEX
    Explanations

    references to machine learning methods and related technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arella
    -0.15
    ulas
    -0.14
    esco
    -0.14
     Middleton
    -0.14
     Crosby
    -0.13
     Karlov
    -0.13
    ults
    -0.13
    å½¹
    -0.13
    geist
    -0.13
     sal
    -0.13
    POSITIVE LOGITS
    udd
    0.16
    otta
    0.16
    337
    0.15
    eneric
    0.15
    dee
    0.15
    anza
    0.15
    upa
    0.14
    _stderr
    0.14
    bers
    0.14
    aments
    0.14
    Act Density 0.009%

    No Known Activations