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

    Neuronpedia

    INDEX
    Explanations

    the beginning of text or document sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the beginning of sentences or sections, often marked by special tokens or newlines.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
     ourselves
    -0.53
     lệ
    -0.50
     myself
    -0.47
    erías
    -0.46
     am
    -0.46
    Distribuzione
    -0.45
     AssemblyProduct
    -0.45
    eti
    -0.43
    ิด
    -0.43
    اید
    -0.43
    POSITIVE LOGITS
     himself
    0.91
    himself
    0.82
     لينك
    0.77
     conmigo
    0.76
    principalColumn
    0.76
     herself
    0.72
    他自己
    0.71
     Himself
    0.69
     his
    0.69
     kanyang
    0.68
    Act Density 0.386%

    No Known Activations