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

    Neuronpedia

    INDEX
    Explanations

    references to historical military conflicts, especially related to World War II

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.90
     >=",
    -0.90
     asiatique
    -0.87
     vettoriale
    -0.79
     végétale
    -0.76
    IntoConstraints
    -0.75
    ंदीखरीदारी
    -0.74
    دانشنامهٔ
    -0.72
     étoit
    -0.71
     africain
    -0.70
    POSITIVE LOGITS
    jspx
    0.57
    locaust
    0.55
    ETY
    0.54
     metav
    0.53
    Subview
    0.52
    ParallelGroup
    0.51
     betweenstory
    0.50
    CoV
    0.49
     pod
    0.48
    Originally
    0.48
    Act Density 0.063%

    No Known Activations