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

    Neuronpedia

    INDEX
    Explanations

    dates and references to versioning information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.94
     faſt
    -0.93
     ſtate
    -0.90
     purpoſe
    -0.86
     ſch
    -0.83
     raiſ
    -0.82
     leaſt
    -0.81
     ſame
    -0.79
     ſta
    -0.78
     ſmall
    -0.78
    POSITIVE LOGITS
    rungsseite
    0.75
     استنادى
    0.68
    Transkript
    0.59
     estekak
    0.53
    Hochspringen
    0.53
    abestanden
    0.52
    Especially
    0.51
     ko
    0.50
    Weblinks
    0.50
     "..\..\
    0.50
    Act Density 0.997%

    No Known Activations