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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "single" items or entities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -1.30
    -1.11
    Individual
    -1.03
     propOrder
    -0.99
     Individual
    -0.98
     individuale
    -0.98
     INDIVIDUAL
    -0.98
    Geplaatst
    -0.97
    تقاوى
    -0.97
     BorderRadius
    -0.96
    POSITIVE LOGITS
     poly
    0.51
    ch
    0.51
    fer
    0.50
    er
    0.49
    LY
    0.49
     ל
    0.49
    mathcal
    0.48
    cke
    0.48
    ers
    0.47
    fillText
    0.47
    Act Density 0.015%

    No Known Activations