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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and equalities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    copyFrom
    -0.56
     Tre
    -0.51
     везе
    -0.50
    ulose
    -0.49
     Ver
    -0.47
     Sel
    -0.47
     فريبيس
    -0.47
    الحياه
    -0.47
     emb
    -0.46
    dataProvider
    -0.46
    POSITIVE LOGITS
     itſelf
    0.62
     Monfieur
    0.62
     autorytatywna
    0.61
     poffible
    0.60
    RectangleBorder
    0.59
     againſt
    0.59
     becauſe
    0.58
     kaynağından
    0.58
     ſtate
    0.58
     themſelves
    0.58
    Act Density 0.017%

    No Known Activations