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

    Neuronpedia

    INDEX
    Explanations

    statements of truth or correctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.98
    MLLoader
    -0.81
    tagHelperRunner
    -0.78
    AnchorStyles
    -0.69
     يتيمه
    -0.66
    BorderFactory
    -0.60
     aufnehmen
    -0.60
    ArrowToggle
    -0.59
     entrevist
    -0.58
     AssemblyProduct
    -0.58
    POSITIVE LOGITS
     true
    1.12
     truth
    1.10
     TRUE
    1.00
     correct
    0.99
     untrue
    0.98
     truths
    0.96
     True
    0.96
     đúng
    0.89
     Correct
    0.89
     FALSE
    0.88
    Act Density 0.220%

    No Known Activations