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

    Neuronpedia

    INDEX
    Explanations

    references to specific weapons, namely "sword" and "gun"

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     connexes
    -0.61
     <>",
    -0.60
     mengen
    -0.57
     الحره
    -0.56
    idopsis
    -0.56
    醐
    -0.56
     afield
    -0.55
     JUGA
    -0.54
    Reducers
    -0.52
    sinon
    -0.51
    POSITIVE LOGITS
    xhtml
    3.67
     XHTML
    0.85
    InstrumentedTest
    0.59
     ivelany
    0.56
    AnchorTagHelper
    0.55
    InputTagHelper
    0.55
    AlterField
    0.52
    XOR
    0.51
    ftagPool
    0.50
    ManagedBean
    0.49
    Act Density 0.002%

    No Known Activations