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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ù
    -0.16
    ocup
    -0.16
    ovÃŃ
    -0.15
    /tcp
    -0.15
    lsi
    -0.14
     erb
    -0.14
    áºŃn
    -0.14
    valu
    -0.14
     Tuy
    -0.14
    dü
    -0.14
    POSITIVE LOGITS
     ÑģоÑģÑĤ
    0.20
     жÑĥÑĢн
    0.18
     vyp
    0.17
     Ñģб
    0.17
     оÑĤв
    0.17
     vyd
    0.17
     Ents
    0.16
     dÃŃl
    0.16
     докÑĥм
    0.16
     lit
    0.16
    Act Density 0.037%

    No Known Activations