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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the token <bos> which indicates the beginning of a new segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fjspx
    -0.90
     незавершена
    -0.81
    sizeCache
    -0.76
    клопе
    -0.75
    ConstraintMaker
    -0.73
     propOrder
    -0.72
     Meksiku
    -0.72
    Sucesor
    -0.71
     ModelExpression
    -0.71
     tartalomajánló
    -0.70
    POSITIVE LOGITS
    مراجع
    0.52
     active
    0.51
    ="#"><
    0.49
    //
    0.48
    WebMethod
    0.47
    Šaltiniai
    0.47
     pre
    0.47
     INSEE
    0.44
    POLE
    0.42
    🧰
    0.42
    Act Density 0.071%

    No Known Activations