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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and the accompanying phrases that convey context, particularly quotations and dialog

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etag
    -0.07
    лÑĸд
    -0.07
    _dot
    -0.07
     kolej
    -0.07
    dü
    -0.07
    cak
    -0.07
     unut
    -0.07
    OOT
    -0.07
    رش
    -0.07
    _simps
    -0.07
    POSITIVE LOGITS
     "
    0.08
     '
    0.07
     «
    0.07
     "[
    0.06
    undi
    0.06
     “
    0.06
     \"
    0.06
     '[
    0.06
     half
    0.06
     ‘
    0.06
    Act Density 0.005%

    No Known Activations