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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and sentence connectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     is
    -0.57
     &&
    -0.54
     S
    -0.52
    ?
    -0.51
    ...
    -0.48
     $
    -0.48
     [
    -0.47
     ...
    -0.47
     can
    -0.47
     |
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.90
     pinulongan
    0.90
     autorytatywna
    0.90
    GEBURTSDATUM
    0.87
    IsContent
    0.87
     myſelf
    0.81
     متعلقه
    0.81
     estekak
    0.77
    SourceChecksum
    0.76
    RenderAtEndOf
    0.76
    Act Density 0.420%

    No Known Activations