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

    Neuronpedia

    INDEX
    Explanations

    phrases related to additional information and various categories or types

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.86
     CreateTagHelper
    -0.83
     Monfieur
    -0.81
    LabelTagHelper
    -0.81
     auffi
    -0.80
     propOrder
    -0.80
     Majefty
    -0.79
     pleaſure
    -0.79
     avoient
    -0.79
     myſelf
    -0.78
    POSITIVE LOGITS
     nữa
    0.54
     pop
    0.52
    気
    0.51
     additional
    0.50
     Pop
    0.50
     Additional
    0.49
    Additional
    0.48
     p
    0.47
     pe
    0.46
     tambahan
    0.46
    Act Density 0.212%

    No Known Activations