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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation marks or brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äł
    -0.15
    odcast
    -0.15
    bakan
    -0.14
    abay
    -0.14
    codes
    -0.14
    README
    -0.14
     Princip
    -0.14
    olumn
    -0.14
    tam
    -0.14
    á»Ļc
    -0.14
    POSITIVE LOGITS
     citation
    0.21
    ubat
    0.17
     cita
    0.17
     needed
    0.16
    بØŃ
    0.16
    nb
    0.15
     needing
    0.15
    arez
    0.15
     Starr
    0.14
    mony
    0.14
    Act Density 0.012%

    No Known Activations