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

    Neuronpedia

    INDEX
    Explanations

    references to facial expressions and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.59
     nakalista
    -0.55
     pleaſure
    -0.51
    saraba
    -0.46
    isContained
    -0.46
    contentLoaded
    -0.45
    fourths
    -0.45
     jura
    -0.44
     &___
    -0.43
    脚注の使い方
    -0.43
    POSITIVE LOGITS
     face
    4.03
    face
    3.48
     faces
    3.44
     Face
    3.41
    Face
    3.33
     FACE
    3.11
    FACE
    2.95
    faces
    2.94
     faced
    2.89
     Faces
    2.83
    Act Density 0.921%

    No Known Activations