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

    Neuronpedia

    INDEX
    Explanations

    references to data metrics and empirical results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.43
    ,
    -0.36
     fer
    -0.28
     U
    -0.28
    Παραπομπές
    -0.28
    .
    -0.28
     跳转至
    -0.28
     Britain
    -0.28
     ab
    -0.28
    Collegamenti
    -0.27
    POSITIVE LOGITS
    QMetaType
    0.68
    msgTypes
    0.66
     للاسماء
    0.65
    +#+#
    0.61
     houſe
    0.59
     esterni
    0.58
    المناصب
    0.57
     Chaldean
    0.57
    Personensuche
    0.57
     témoig
    0.57
    Act Density 1.682%

    No Known Activations