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

    Neuronpedia

    INDEX
    Explanations

    words or phrases denoting significant changes or selections

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.67
     Arhivirano
    -0.64
     Heeren
    -0.63
     Италијани
    -0.62
     newArray
    -0.56
    اعمال
    -0.56
    ✭✭
    -0.54
     MaterialApp
    -0.53
     visibility
    -0.52
    EditorBrowsable
    -0.52
    POSITIVE LOGITS
    URUS
    0.60
    ImageContext
    0.54
     originales
    0.52
     disponibilités
    0.52
    LAHOMA
    0.52
    lück
    0.50
     للاسماء
    0.50
    ện
    0.50
    lewati
    0.49
    irected
    0.49
    Act Density 0.001%

    No Known Activations