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

    Neuronpedia

    INDEX
    Explanations

    parentheses and related formatting symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itespace
    -0.13
    wcs
    -0.13
    ãģŁãģĹ
    -0.12
    صاÙĦ
    -0.12
     fod
    -0.12
     Ged
    -0.12
    etto
    -0.12
    uyu
    -0.12
    MLE
    -0.12
    pcl
    -0.12
    POSITIVE LOGITS
     TG
    0.48
     CG
    0.48
     SG
    0.48
     RG
    0.48
     LG
    0.48
    CG
    0.47
     FG
    0.47
     IG
    0.47
    EG
    0.46
     AG
    0.46
    Act Density 0.089%

    No Known Activations