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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "wear" and its variations related to clothing or accessories

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    goose
    -0.73
     Robles
    -0.69
    ciutto
    -0.68
    время
    -0.68
    (',')
    -0.67
     Polen
    -0.65
     Pritchard
    -0.65
     McG
    -0.64
    来不及
    -0.64
    gge
    -0.63
    POSITIVE LOGITS
     Wear
    1.08
     wear
    1.03
     Worn
    1.03
     worn
    0.97
     wears
    0.97
    Wear
    0.96
     WEAR
    0.94
     wearer
    0.91
     Wearing
    0.84
     élas
    0.84
    Act Density 0.012%

    No Known Activations