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

    Neuronpedia

    INDEX
    Explanations

    negative integers associated with specific matrix operations or transformations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     -
    -0.56
     disambiguazione
    -0.54
    ukone
    -0.47
    DispatchToProps
    -0.47
    /-
    -0.45
    chism
    -0.44
     –
    -0.44
      
    -0.44
    σκ
    -0.43
     proce
    -0.43
    POSITIVE LOGITS
     ostavi
    0.70
     onAnimation
    0.69
    RectangleBorder
    0.67
    +#+#
    0.63
     zove
    0.62
    canActivate
    0.61
    zufügen
    0.60
     nhãn
    0.60
    +][
    0.59
     virgin
    0.59
    Act Density 0.035%

    No Known Activations