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

    Neuronpedia

    INDEX
    Explanations

    the presence of the `<bos>` token, indicating the beginning of a new segment or thought in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MergeFrom
    -0.77
    WithIOException
    -0.75
    featureID
    -0.75
    buttonBar
    -0.70
    ]));
    -0.70
     للاسماء
    -0.65
     resourceCulture
    -0.65
    EndContext
    -0.65
    CppCodeGen
    -0.64
    SerializedSize
    -0.63
    POSITIVE LOGITS
     quæ
    0.62
     ejus
    0.47
     third
    0.47
    ÂN
    0.47
    makeText
    0.45
    ✠
    0.43
     eorum
    0.43
    embatan
    0.42
    third
    0.41
    벌
    0.41
    Act Density 0.166%

    No Known Activations