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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "made" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Voss
    -0.92
     Monfieur
    -0.83
     Mosca
    -0.82
    UseVisualStyle
    -0.79
     betweenstory
    -0.74
     umgangssprach
    -0.74
     uninsured
    -0.73
     velours
    -0.72
     Osorio
    -0.72
     Roumanie
    -0.71
    POSITIVE LOGITS
     made
    1.81
    Made
    1.73
     Made
    1.72
    made
    1.70
     MADE
    1.66
    MADE
    1.54
     gemaakt
    1.08
     faite
    1.04
     Hecho
    1.00
     hechas
    0.92
    Act Density 0.085%

    No Known Activations