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

    Neuronpedia

    INDEX
    Explanations

    sentences that start with a special token or represent the beginning of a new segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.45
    ↵↵
    -0.41
    string
    -0.41
    련
    -0.41
     Hatfield
    -0.41
    bdd
    -0.41
     podla
    -0.40
    zí
    -0.39
    ной
    -0.39
    tele
    -0.38
    POSITIVE LOGITS
    awtextra
    0.92
     doInBackground
    0.89
     intptr
    0.88
    
    0.88
     مشين
    0.87
     {}));
    0.87
    enumii
    0.83
     itſelf
    0.83
    ViewFeatures
    0.82
     HttpNotFound
    0.82
    Act Density 0.031%

    No Known Activations