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

    Neuronpedia

    INDEX
    Explanations

    numerical values and operations related to addition and subtraction

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    .
    -0.45
     immor
    -0.41
     agenti
    -0.41
     Pantheon
    -0.39
     ringing
    -0.38
    nende
    -0.38
     Seminary
    -0.37
     Marches
    -0.37
     vot
    -0.36
     Caspar
    -0.35
    POSITIVE LOGITS
     незавершена
    1.20
     ModelExpression
    1.12
    AddTagHelper
    0.97
    kháu
    0.90
     kaynağından
    0.90
     InputDecoration
    0.89
     كومونز
    0.89
    DeleteBehavior
    0.86
     GenerationType
    0.86
     linkovi
    0.86
    Act Density 0.054%

    No Known Activations