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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ciutat
    -0.63
    resz
    -0.59
     null
    -0.58
     pitié
    -0.57
     sèche
    -0.57
    őt
    -0.56
     unmarked
    -0.54
    shub
    -0.53
     solaire
    -0.51
     effray
    -0.50
    POSITIVE LOGITS
    httphttps
    0.88
    +#+
    0.87
    ########.
    0.77
    ⓧ
    0.75
     referenties
    0.72
    :]:
    0.70
    argout
    0.69
    resizingMask
    0.68
    webElementXpaths
    0.67
    elemField
    0.66
    Act Density 0.003%

    No Known Activations