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

    Neuronpedia

    INDEX
    Explanations

    references to additional elements or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.81
     Eſ
    -0.72
     houſe
    -0.66
     Houſe
    -0.65
     Diſ
    -0.64
    titu
    -0.63
     étoient
    -0.61
     Reſ
    -0.60
     viſ
    -0.59
     preſent
    -0.59
    POSITIVE LOGITS
     extra
    1.26
     additional
    1.17
     tambahan
    1.13
    additional
    1.07
     added
    1.06
     zusätzlichen
    1.01
    extra
    1.00
     thêm
    0.97
     Additional
    0.97
     ADDITIONAL
    0.97
    Act Density 0.595%

    No Known Activations