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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quantitative comparisons or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sähkö
    -0.53
    Gab
    -0.53
     dég
    -0.52
     need
    -0.51
     for
    -0.51
    물
    -0.51
     khong
    -0.51
    bbean
    -0.50
    gage
    -0.50
     собою
    -0.49
    POSITIVE LOGITS
    ConstraintMaker
    1.10
    CloseOperation
    1.07
    AddTagHelper
    1.00
    Geplaatst
    0.95
    tothe
    0.91
    IntoConstraints
    0.86
    DebuggerNonUser
    0.84
    ArgsConstructor
    0.81
     المعيارى
    0.81
    ulipas
    0.81
    Act Density 0.362%

    No Known Activations