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

    Neuronpedia

    INDEX
    Explanations

    names of notable individuals and their associated titles or roles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    FFECT
    -0.51
    dijk
    -0.49
     Rak
    -0.48
    ĭ
    -0.48
    mio
    -0.48
    ">{{$
    -0.48
    ätte
    -0.47
    isma
    -0.47
    glers
    -0.47
     Dage
    -0.47
    POSITIVE LOGITS
     &___
    0.81
     nahilalakip
    0.80
    SharedCtor
    0.68
    Viited
    0.67
     CreateTagHelper
    0.67
     PhpStorm
    0.64
     للاسماء
    0.64
    +#+#
    0.62
    ConstraintMaker
    0.60
     Générale
    0.59
    Act Density 0.031%

    No Known Activations