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

    Neuronpedia

    INDEX
    Explanations

    the conjunctions that indicate relationships or connections between ideas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     private
    -0.51
     
    -0.47
    PRIVATE
    -0.44
     Reverso
    -0.44
     backs
    -0.43
    lowers
    -0.43
    balleur
    -0.41
     others
    -0.41
     conto
    -0.41
     bels
    -0.40
    POSITIVE LOGITS
    MigrationBuilder
    0.97
    AccessorTable
    0.88
     <=",
    0.86
    ConstraintMaker
    0.85
    StructEnd
    0.82
    BagConstraints
    0.80
    AddTagHelper
    0.77
    addCriterion
    0.75
     мәкал
    0.75
    Vidite
    0.74
    Act Density 0.080%

    No Known Activations