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

    Neuronpedia

    INDEX
    Explanations

    references to a "center" or "central" concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.60
     يتيمه
    -0.57
    uminense
    -0.57
    ########.
    -0.57
    psack
    -0.57
    ('../../../
    -0.54
    InputTagHelper
    -0.53
    mentaires
    -0.53
    std
    -0.51
    ../../../
    -0.50
    POSITIVE LOGITS
     centrales
    1.03
     centrale
    1.03
     center
    1.00
    centerX
    0.98
    centerY
    0.95
     centering
    0.93
     centre
    0.92
     centrality
    0.90
     centrally
    0.90
     central
    0.89
    Act Density 0.164%

    No Known Activations