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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or topics in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     si
    -0.48
    디오
    -0.47
     bis
    -0.43
     val
    -0.43
     T
    -0.42
    ni
    -0.42
     (
    -0.42
     D
    -0.42
    na
    -0.41
    ,
    -0.41
    POSITIVE LOGITS
     doInBackground
    0.94
     للاسماء
    0.94
    +:+
    0.91
     estimés
    0.91
    __":
    0.90
    SBATCH
    0.90
     typelib
    0.90
    
    0.89
    UnknownFields
    0.88
    findpost
    0.88
    Act Density 0.046%

    No Known Activations